Skip to content

User Intuition MCP server

ai.userintuition/researchuserintuition.aistreamable-httpv1.6.5Scanned

Qualitative research with real people: AI-moderated interviews, 4M+ vetted panel, 80+ languages.

79 tools: 28 can delete or cancel things, 23 change things and 28 only read.

Tools: 28 delete, 0 irreversible, 23 write, 28 read.
  • Reads private data · 3
  • Reads text others write · 22
  • Can send data out · 2
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

28 tools here can delete or cancel things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the User Intuition MCP server can do

The User Intuition MCP server is published by userintuition.ai, a domain the MCP Registry verified. It has 79 tools. It can delete or cancel things (28 tools: customize_study, queue_customize_study, launch_panel, approve_panel_launch and 24 more) and create or change data (23 tools: create_study, review_study, estimate_panel, generate_report and 19 more). 28 tools only read.

3 tools read private data (view_research_answer, inspect_research_session and get_webhook); 22 tools bring in text other people can write (customize_study, queue_customize_study, launch_panel and 19 more); 2 tools can send data out of your system (send_participant_reward and test_webhook). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 2 findings (long-description and annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 20, 2026, version 1.6.5.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

79 tools

Deletes or cancels 28Claude Code: deny
  • approve_panel_launchMCP App button action.Reads text others writeNo findings

    Why it is in this group

    • The name "approve_panel_launch" says "approve": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    MCP App button action. Consumes one short-lived approval challenge, rechecks the saved study and price, then launches one paid panel cycle.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • title: Approve and Launch Panel
  • cancel_feasibility_requestWithdraw a pending feasibility request.No findings

    Why it is in this group

    • The name "cancel_feasibility_request" says "cancel": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Withdraw a pending feasibility request. A request already answered cannot be cancelled.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • title: Cancel Feasibility Request
  • cancel_research_analysisCancel one durable analysis run only when the user requests it.No findings

    Why it is in this group

    • The name "cancel_research_analysis" says "cancel": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Cancel one durable analysis run only when the user requests it. Existing results remain available for inspection.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • title: Cancel Research Analysis
  • cancel_research_deliverableCancel a queued or running research export.No findings

    Why it is in this group

    • The name "cancel_research_deliverable" says "cancel": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Cancel a queued or running research export. A cancelled worker cannot publish its file.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
    • title: Cancel Research Deliverable
  • clear_research_sourcesLegacy bulk removal: remove all sources from this research session without deleting the underlying studies or files.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Legacy bulk removal: remove all sources from this research session without deleting the underlying studies or files. Use only when the user requests clearing the session.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • title: Clear Research Session Sources
  • configure_external_panelCreate or replace a customer-supplied panel bridge on an owned BYOP study.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Create or replace a customer-supplied panel bridge on an owned BYOP study. Supply completion and screen-out redirect URLs; set the provider's respondent ID query parameter and placeholder if the defaults differ. Optional session, external study, quota-full, and technical-failure mappings are supported. Before sharing entry_url with the provider, call get_study, verify provisioning_status=provisioned, and have the human approve the current plan and URL mapping. This does not recruit respondents or launch the paid User Intuition Panel. Repeating the same PUT preserves the current entry token.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
    • title: Configure External Panel
  • create_participantsInvite people you recruit yourself by email, such as your customers, to a study (BYOP = bring your own participants).Reads text others writeNo findings

    Why it is in this group

    • The name "create_participants" says "create": a word for a change.
    • The description's first verb is "invite": a word for sending, and what is sent cannot be taken back.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Invite people you recruit yourself by email, such as your customers, to a study (BYOP = bring your own participants). Queues creation of 1–100 unique BYOP participants. Poll get_participant_job until succeeded, then list participants. Before creating participants, call get_study, require provisioning_status=provisioned, and verify or obtain explicit approval of the current plan. Carry a trusted unchanged approval forward using study_id and updated_at; changed plan or participant settings invalidate it. Invitation emails send unless silent is true.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • title: Create Participants
  • customize_studyDraft or revise a study's discussion guide, interview questions, screener, and audience from the research brief, one design turn per call.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Draft or revise a study's discussion guide, interview questions, screener, and audience from the research brief, one design turn per call. May fetch a researcher-provided concept URL. Clients that support MCP background tasks receive a task for turns without concept_image; wait on that task for the result. Calls with concept_image return the result directly. Put operational workflow constraints in execution_policy, never in message. Set decisions=agent only when the human delegated research-design choices; report assumptions and relay only remaining required questions. Otherwise use human mode and relay questions[]. If the client exposes an attached image as bytes or a readable local path, ask for a participant-facing label when missing, base64-encode the raw bytes, and send concept_image. Completed plans and setting changes are persisted. Then get_study, return the full saved plan for review, and obtain approval before invitations or paid launch.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • title: Design Interview Guide
  • delete_external_panelDisable the external-panel entry link for an owned BYOP study.Reads text others writeNo findings

    Why it is in this group

    • The name "delete_external_panel" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Disable the external-panel entry link for an owned BYOP study. Existing interviews remain; the provider can no longer send new respondents through this link. A repeated deletion returns 404.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • title: Delete External Panel Configuration
  • delete_interviewSoft-delete an interview owned by the authenticated user.No findings

    Why it is in this group

    • The name "delete_interview" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Soft-delete an interview owned by the authenticated user. Call only when the human explicitly requests deletion of this interview.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • title: Delete Interview
  • delete_participantSoft-delete one BYOP participant after the user explicitly requests it.No findings

    Why it is in this group

    • The name "delete_participant" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Soft-delete one BYOP participant after the user explicitly requests it. Deletion also removes its personal link. If interviews exist, the request returns a conflict unless the user separately approves deleting those interviews and cascade_interviews is true.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • title: Delete Participant
  • delete_research_outputPermanently delete an existing saved output (report, deck or video) in its session only when the user requests deletion.No findings

    Why it is in this group

    • The name "delete_research_output" says "delete": a word for removing or ending something.
    • The description says "Permanently delete".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Permanently delete an existing saved output (report, deck or video) in its session only when the user requests deletion. Read the output first.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • title: Delete Research Output
  • delete_research_sessionDelete one research session only when the user explicitly requests it.No findings

    Why it is in this group

    • The name "delete_research_session" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Delete one research session only when the user explicitly requests it.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • title: Delete Research Session
  • delete_studySoft-delete a study and its linked participants, interviews, and reports from normal reads.No findings

    Why it is in this group

    • The name "delete_study" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Soft-delete a study and its linked participants, interviews, and reports from normal reads. Participant links stop working. There is no public restore endpoint. Uploaded assets may have separate retention. Call only when the human explicitly requests deletion of this study.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • title: Delete Study
  • delete_webhookDeprecated compatibility tool.Reads text others writeNo findings

    Why it is in this group

    • The name "delete_webhook" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Deprecated compatibility tool. List webhooks, then use delete_webhook_by_id so deletion works through clients that omit DELETE request bodies. A repeated deletion returns 404.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • title: Delete Webhook by URL (Deprecated)
  • delete_webhook_by_idStop future deliveries to one registered webhook.Reads text others writeNo findings

    Why it is in this group

    • The name "delete_webhook_by_id" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Stop future deliveries to one registered webhook. A repeated deletion returns 404.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • title: Delete Webhook by ID
  • edit_research_outputApply the requested prompt to an existing report or PowerPoint in place.No findings

    Why it is in this group

    • The name "edit_research_output" says "edit": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Apply the requested prompt to an existing report or PowerPoint in place. Read the output first. Retains its ID and reuses saved evidence; default reports and Highlights cannot be edited. Poll inspect_research_session view=job and read the original output after success. Reuse the key on retry.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
    • title: Edit Research Output
  • launch_panelRecruit real interview participants from User Intuition's 4M+ vetted consumer panel.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Recruit real interview participants from User Intuition's 4M+ vetted consumer panel. If an owner or admin enabled automatic launches in Wallet, this tool launches one cycle within the workspace cap with a current estimate and idempotency key. Otherwise, the first call previews the saved plan and complete current panel estimate; nothing is spent until a human explicitly approves. For App clients, a human must click Approve and launch in the App. For clients without MCP Apps, return the saved plan and quote in chat, ask the human to confirm, then call this tool again with the returned chat_approval_nonce and human_confirmed=true. Never infer confirmation from a prior study or quote. The estimate must match the study, country, inputs, balance and price at approval time.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • title: Review Panel Launch
  • queue_customize_studyQueue one design turn that drafts or revises the study's discussion guide, questions, screener, and audience from the research brief.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Queue one design turn that drafts or revises the study's discussion guide, questions, screener, and audience from the research brief. May fetch a researcher-provided concept URL. Clients that support MCP background tasks receive a task to wait on; other clients receive a job ID and poll get_customize_study_job. Then call get_study and show the full saved plan for human review. Reuse an idempotency_key after an uncertain response. Native concept images require the synchronous customize_study tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • title: Queue Interview Guide Design
  • regenerate_external_panel_tokenReplace the external-panel entry token for an owned BYOP study.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "replace": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Replace the external-panel entry token for an owned BYOP study. The old provider link stops working immediately; update the provider with the returned entry_url. Supply a unique idempotency_key and reuse it after an uncertain response; inspect the current link with get_external_panel if the replay is stale.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • title: Regenerate External Panel Entry Token
  • remove_research_sourceRemove one source from a research session by the opaque ID returned by inspect_research_session.No findings

    Why it is in this group

    • The name "remove_research_source" says "remove": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Remove one source from a research session by the opaque ID returned by inspect_research_session. The underlying study or uploaded file is not deleted.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • title: Remove Research Source
  • remove_research_studyRemove one study source from a research session; the underlying study remains available in User Intuition.No findings

    Why it is in this group

    • The name "remove_research_study" says "remove": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Remove one study source from a research session; the underlying study remains available in User Intuition.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • title: Remove Study from Research Session
  • rotate_webhook_secretReplace a webhook signing secret.No findings

    Why it is in this group

    • The description's first verb is "replace": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Replace a webhook signing secret. The new secret is shown only in this response; update the receiver before relying on further deliveries.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
    • title: Rotate Webhook Secret
  • send_participant_rewardSend the configured incentive to a BYOP participant.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "send_participant_reward" says "send": a word for sending, and what is sent cannot be taken back.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "send_participant_reward" says "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Send the configured incentive to a BYOP participant. Check the participant and reward amount (byop_config.incentive_amount from get_study). For API keys requiring approval, the first call previews the reward. Show the reward, 5% transaction fee, and total to the human, then submit the returned chat_approval_nonce with human_confirmed=true only after explicit approval. Keys configured without approval can send directly when requested. For other connections, confirm the recipient and the cost including the 5% fee with the human. Reuse idempotency_key on uncertain retries.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
    • title: Send Participant Reward
  • stop_studyStop panel recruitment, close the target cycle, and settle/release the active reward hold.Reads text others writeNo findings

    Why it is in this group

    • The name "stop_study" says "stop": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Stop panel recruitment, close the target cycle, and settle/release the active reward hold. Call only after the human explicitly chooses to end this study's fieldwork.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
    • title: Stop Study Fieldwork
  • test_webhookSend a signed test event containing no participant or study data.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe description's first verb is "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Send a signed test event containing no participant or study data. This makes an outbound request to the registered URL.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • title: Test Webhook
  • update_participantChange the email, external customer ID, or customer metadata fields on one BYOP participant.Reads text others writeNo findings

    Why it is in this group

    • The name "update_participant" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Change the email, external customer ID, or customer metadata fields on one BYOP participant. Call get_participant first to verify the intended participant. Send email=null only when the user explicitly wants to clear it. Pass only fields to change.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
    • title: Update Participant
  • update_studyUpdate ordinary study metadata only, such as name, format, language, voice, or incentives.No findings

    Why it is in this group

    • The name "update_study" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Update ordinary study metadata only, such as name, format, language, voice, or incentives. Use customize_study—not this tool—for the research plan, audience targeting, screener questions, concept links, or concept images. Only supplied fields change. Active panel studies must be paused or stopped first. Call get_study first.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • title: Update Study
Changes things 23Claude Code: ask
  • add_all_research_studiesLegacy bulk selection: add every currently available study to this research session.No findings

    Why it is in this group

    • The name "add_all_research_studies" says "add": a word for a change.
    Description, as the server wrote it
    Legacy bulk selection: add every currently available study to this research session. Use sync_research_study for a selected study.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Add All Studies to Research Session
  • answer_researchFastest cited answer to one question across selected studies ("why did customers churn?").No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Fastest cited answer to one question across selected studies ("why did customers churn?"). For multi-turn follow-ups with clickable quote cards use chat_research_session. Uses indexed research across selected accessible studies. Returns generated statements with numbered citations to canonical content IDs, plus source details and index status. Use search_research to inspect the underlying records.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Answer Research
  • chat_research_sessionAsk a multi-turn question about your User Intuition studies and get an answer grounded in verified participant quotes.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Ask a multi-turn question about your User Intuition studies and get an answer grounded in verified participant quotes. Waits for the answer; use queue_research_chat to return immediately. If still running, returns the same durable job without cancelling it. For findings, feedback, comparisons and quotations from your User Intuition studies, use this tool; answers are grounded in document search over the session sources with verified quotations. Resolve ambiguous study names first. Reuse the selected research session; if absent create one with create_research_session and a stable retry key, inspect sources and add only missing requested studies. Do not resync unchanged sources or broaden the session silently. After completion always call view_research_answer to display the answer and clickable quote/recording cards inside this conversation, without redirecting to a dashboard; preserve the answer and citation labels. Poll inspect_research_session view=job. Set parent_job_id for a follow-up in the same session. Reuse the same idempotency_key and prompt after a timeout; sync and async share the job.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Chat with Research Session
  • create_research_sessionCreate a research session (a saved analysis workspace) for selected studies and uploaded sources.No findings

    Why it is in this group

    • The name "create_research_session" says "create": a word for a change.
    Description, as the server wrote it
    Create a research session (a saved analysis workspace) for selected studies and uploaded sources. Reuse the same idempotency key after an uncertain response.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Create Research Session
  • create_studyStart a qualitative research study with real people: AI-moderated in-depth interviews (user interviews, customer interviews, market research; the moderator probes and ladders, typi…1 finding

    Why it is in this group

    • The name "create_study" says "create": a word for a change.

    Findings

    • Info

      The description is 2,015 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...r chat as well as voice and video. Next: send the brief to queue_customize_study."

      What this check looks for
    Description, as the server wrote it
    Start a qualitative research study with real people: AI-moderated in-depth interviews (user interviews, customer interviews, market research; the moderator probes and ladders, typically 20–30 minutes), concept tests (packaging, claims, ad creative, designs), or prototype tests (clickable prototypes, websites, landing pages), by voice, video or chat in 80+ languages. Participants come from a 4M+ vetted consumer panel, your own customers by email, or synthetic respondents. Use for "interview N shoppers about X", "test this concept with real people", "why did customers churn / switch / buy", win-loss, onboarding. Not for multiple-choice surveys. Creates an in-depth-interview, concept-test, or prototype-test draft using ordinary metadata only. Choose recruiting_method from the brief: panel when User Intuition should recruit real participants, byop when the user will supply their own participants, or synthetic_respondents when the brief calls for simulated participants. Ask only if the recruiting method is unclear. Unless the human requests otherwise, use a voice interview in English with the male interviewer voice; these defaults are applied when interview_format, language, or voice are omitted. Synthetic respondents require chat. A prototype-test must use video or voice, never chat. Do not draft or pass the study plan, audience targeting, screener questions, concept links, or concept images here; they come from the user's natural-language research brief in the next call. For a concept test, pass an accessible attachment through customize_study.concept_image or include a publicly downloadable concept-image URL in the message, plus its participant-facing label, stimulus context, audience, and learning goals. For a prototype test, include the prototype URL, participant-facing label, intended tasks, audience, and learning goals. customize_study validates and attaches the asset. Voice configuration is kept for chat as well as voice and video. Next: send the brief to queue_customize_study.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Create Interview Study
  • create_webhookCreate a webhook for an account or one owned study.Reads text others writeNo findings

    Why it is in this group

    • The name "create_webhook" says "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Create a webhook for an account or one owned study. Choose interview, study lifecycle, participant lifecycle, or quota events. The signing secret is shown once; store it securely.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • title: Create Webhook
  • estimate_panelEstimate the cost and timeline of recruiting real interview participants from User Intuition's 4M+ vetted consumer panel for one study, without spending.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Estimate the cost and timeline of recruiting real interview participants from User Intuition's 4M+ vetted consumer panel for one study, without spending. Returns per-interview and total cost before any commitment. Read-only estimate for one Panel recruitment cycle. Returns per-interview and total credit cost, available balance and deficit, participant reward, card hold, recurrence, and a heuristic timeline. launch_panel shows this estimate for human App approval, or human chat confirmation in clients without Apps, before the paid request. The price and balance can change before launch; use submit_feasibility_request for low-incidence audiences.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Estimate Participant Recruitment
  • generate_reportQueue an AI analysis of completed interviews into a cited report (findings, themes, quotes).Reads text others writeNo findings

    Why it is in this group

    • The name "generate_report" says "generate": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Queue an AI analysis of completed interviews into a cited report (findings, themes, quotes). Clients that support MCP background tasks receive a task to wait on; other clients receive a job ID and poll get_report_job. Then call get_study_report. report.ready webhooks also signal completion.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • title: Generate Study Report
  • generate_research_outputQueue a report, native PowerPoint or saved Highlights video in a research session.No findings

    Why it is in this group

    • The name "generate_research_output" says "generate": a word for a change.
    Description, as the server wrote it
    Queue a report, native PowerPoint or saved Highlights video in a research session. Reuses saved reports and findings; no need to run exhaustive analysis first. Highlights follow default-report learning goals/quotes, with original audio when available and no artificial narration for chat studies; prompt does not select different quotes. Poll inspect_research_session view=job until succeeded; then read its output_id. Retry with the same key.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Generate Research Output
  • pause_studyPause a study while preserving its panel survey, target cycle, progress, and reward hold.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Pause a study while preserving its panel survey, target cycle, progress, and reward hold.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Pause Study Fieldwork
  • queue_report_slidesQueue an editable PowerPoint deck from the latest saved report.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Queue an editable PowerPoint deck from the latest saved report. Common text identifiers are masked by default. Poll get_report_slide_job for a private download URL, which expires after 15 minutes. The export is retained for seven days.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Queue Report Slides
  • queue_research_chatSame as chat_research_session but returns a job immediately; use when the answer may take longer than the client's tool timeout.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Same as chat_research_session but returns a job immediately; use when the answer may take longer than the client's tool timeout. For findings, feedback, comparisons and quotations from your User Intuition studies, use this tool; answers are grounded in document search over the session sources with verified quotations. Resolve ambiguous study names first. Reuse the selected research session; if absent create one with create_research_session and a stable retry key, inspect sources and add only missing requested studies. Do not resync unchanged sources or broaden the session silently. After completion always call view_research_answer to display the answer and clickable quote/recording cards inside this conversation, without redirecting to a dashboard; preserve the answer and citation labels. Poll inspect_research_session view=job. Set parent_job_id for a follow-up in the same session. Reuse the same idempotency_key and prompt after a timeout; sync and async share the job.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Queue Research Chat
  • queue_research_deliverableUse report_video for Highlights: generate one retained MP4 from the studies' default reports, with branded logo bookends, learning-goal chapters and their cited Quotes.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Use report_video for Highlights: generate one retained MP4 from the studies' default reports, with branded logo bookends, learning-goal chapters and their cited Quotes. Repeated requests return the saved video. No evidence selection is needed. Also supports an editable PowerPoint, an individual audio clip or a legacy audio reel ZIP from a completed/partial research analysis run. Use exact evidence_ids returned by get_research_analysis highlights; presentations include all findings. Audio requires explicit export instruction. Text masking defaults on. Poll get_research_deliverable, or wait on the MCP background task when the client supports tasks. Private links last 15 minutes; temporary audio and presentation files expire in seven days; report videos are retained while their source remains available. Reuse the idempotency key after a timeout.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Create Research Deliverable
  • rename_research_outputRename an existing saved output (report, deck or video) in its session.No findings

    Why it is in this group

    • The name "rename_research_output" says "rename": a word for a change.
    Description, as the server wrote it
    Rename an existing saved output (report, deck or video) in its session. Default reports cannot be renamed. Read the output first.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Rename Research Output
  • rename_research_sessionRename one research session without changing its sources or analysis.No findings

    Why it is in this group

    • The name "rename_research_session" says "rename": a word for a change.
    Description, as the server wrote it
    Rename one research session without changing its sources or analysis.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Rename Research Session
  • resume_research_analysisResume a paused or partial durable analysis run with an additional call allowance.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Resume a paused or partial durable analysis run with an additional call allowance. Poll get_research_analysis for the updated result.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • title: Resume Research Analysis
  • resume_studyResume a paused study and continue its preserved panel recruitment.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Resume a paused study and continue its preserved panel recruitment.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Resume Study Fieldwork
  • review_studyOpen an interactive, read-only view of the saved study plan and current fielding progress.1 finding

    Why it is in this group

    • The description's first verb is "open": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "review_study" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "open": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Open an interactive, read-only view of the saved study plan and current fielding progress. The view does not approve a plan or launch recruitment. Ask the human for approval separately before fieldwork.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Review Study Plan
  • start_research_analysisStart a durable analysis across the session sources.Reads text others writeNo findings

    Why it is in this group

    • The name "start_research_analysis" says "start": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Start a durable analysis across the session sources. exhaustive processes every eligible interview; quick retrieves verified evidence through document search; aggregate computes exact counts; explore runs bounded computation. Poll get_research_analysis. Prefer chat_research_session or queue_research_chat for questions and generate_research_output for saved outputs. Completed or partial runs can produce presentations, clips or reels; retain coverage and limitations. Reuse the idempotency key on uncertain retries.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • title: Start Research Analysis
  • submit_feasibility_requestRequest a recruitment quote for a low-incidence audience on an existing panel study.No findings

    Why it is in this group

    • The name "submit_feasibility_request" says "submit": a word for a change.
    Description, as the server wrote it
    Request a recruitment quote for a low-incidence audience on an existing panel study. Provide one target market, the audience criteria, the interview count, and the incidence rate. Check status here or open Recruit participants on the study dashboard to review and approve the quote. Submitting the request does not launch recruitment or charge the account. Reuse idempotency_key after an uncertain response.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Submit Feasibility Request
  • sync_research_studyAdd or resync one study in a research session.No findings

    Why it is in this group

    • The name "sync_research_study" says "sync": a word for a change.
    Description, as the server wrote it
    Add or resync one study in a research session. Inspect existing sources and add only the study the user requested.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Sync Study to Research Session
  • upload_research_sourceAttach external evidence to a research session: TXT, Markdown, CSV, JSON, text PDF or DOCX, up to 10 MB.No findings

    Why it is in this group

    • The name "upload_research_source" says "upload": a word for a change.
    Description, as the server wrote it
    Attach external evidence to a research session: TXT, Markdown, CSV, JSON, text PDF or DOCX, up to 10 MB. Send user-provided file bytes as base64. Uploading again creates another source; list sources after an uncertain response before retrying.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Upload Research Source
  • upload_research_templateUpload a template up to 5 MB: report Markdown/TXT/DOCX with {{title}} and/or {{findings}} placeholders; presentation 16:9 PPTX theme/layout.No findings

    Why it is in this group

    • The name "upload_research_template" says "upload": a word for a change.
    Description, as the server wrote it
    Upload a template up to 5 MB: report Markdown/TXT/DOCX with {{title}} and/or {{findings}} placeholders; presentation 16:9 PPTX theme/layout. Send raw file bytes as base64; pass the returned template id to generate_research_output. Repeated uploads create separate templates.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Upload Research Template
Only reads 28Show 28 read-only tools
  • download_research_outputRetrieve a saved report as Markdown, PowerPoint as PPTX/PDF, or Highlights as a short-lived private MP4 link.No findings

    Why it is in this group

    • The description's first verb is "retrieve": a word for reading.
    Description, as the server wrote it
    Retrieve a saved report as Markdown, PowerPoint as PPTX/PDF, or Highlights as a short-lived private MP4 link. Files return filename, mime_type and data_base64 (up to 64 MB); decode to an artifact rather than showing base64 to the user. Access is checked again. Preserve verified references; never invent download URLs.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Download Research Output
  • get_accountRead the effective workspace, role, billing plan, available credits, payment readiness, and incentive limits.No findings

    Why it is in this group

    • The name "get_account" says "get": a word for reading.
    Description, as the server wrote it
    Read the effective workspace, role, billing plan, available credits, payment readiness, and incentive limits. Check the plan before using Intelligence Hub tools. A payment method on file does not approve a Panel launch; use the current estimate and its MCP App for human approval.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Account
  • get_customize_study_jobPoll a queued study customization turn.No findings

    Why it is in this group

    • The name "get_customize_study_job" says "get": a word for reading.
    Description, as the server wrote it
    Poll a queued study customization turn. On succeeded, inspect result and call get_study to return the persisted plan. On failed, inspect the saved study before retrying.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Study Customization Job
  • get_external_panelRead the customer-supplied panel entry link, respondent ID parameters, and outcome redirects for one owned BYOP study.No findings

    Why it is in this group

    • The name "get_external_panel" says "get": a word for reading.
    Description, as the server wrote it
    Read the customer-supplied panel entry link, respondent ID parameters, and outcome redirects for one owned BYOP study. This is distinct from individual BYOP participants and paid User Intuition Panel recruitment.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get External Panel Configuration
  • get_feasibility_requestGet one feasibility request and its status or estimate.No findings

    Why it is in this group

    • The name "get_feasibility_request" says "get": a word for reading.
    Description, as the server wrote it
    Get one feasibility request and its status or estimate.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Feasibility Request
  • get_fielding_progressGet qualifying completions versus the current target, completed interview quality counts, and a rate-based expected finish when enough progress exists.No findings

    Why it is in this group

    • The name "get_fielding_progress" says "get": a word for reading.
    Description, as the server wrote it
    Get qualifying completions versus the current target, completed interview quality counts, and a rate-based expected finish when enough progress exists.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Fielding Progress
  • get_interviewGet one interview: transcript, participant details, recording links, screener answers, timing, stored format, current configured study language, and up to 100 spoken transcript seg…No findings

    Why it is in this group

    • The name "get_interview" says "get": a word for reading.
    Description, as the server wrote it
    Get one interview: transcript, participant details, recording links, screener answers, timing, stored format, current configured study language, and up to 100 spoken transcript segments bounded to about 20 KB of text. Use next_message_offset to fetch the next page. Each segment keeps its original turn ID and text_offset; system prompts and internal metadata are excluded.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Interview and Transcript
  • get_interview_usage_statsAggregate eligible non-test interview counts and billed units over a date range.No findings

    Why it is in this group

    • The name "get_interview_usage_stats" says "get": a word for reading.
    Description, as the server wrote it
    Aggregate eligible non-test interview counts and billed units over a date range. The backend resolves the default app and a 30-day UTC range when omitted. The response includes the applied scope.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Interview Usage
  • get_participantRead one BYOP participant, including its current status, personal interview link, interview count, and reward state.No findings

    Why it is in this group

    • The name "get_participant" says "get": a word for reading.
    Description, as the server wrote it
    Read one BYOP participant, including its current status, personal interview link, interview count, and reward state. Use it to verify the participant before changing their email, deleting the participant, or sending a reward. Panel respondents are not returned by this tool.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Participant
  • get_participant_jobPoll a participant batch.No findings

    Why it is in this group

    • The name "get_participant_job" says "get": a word for reading.
    Description, as the server wrote it
    Poll a participant batch. On success, list_participants for the study to retrieve the participants.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Participant Job
  • get_report_jobPoll an asynchronous report request.No findings

    Why it is in this group

    • The name "get_report_job" says "get": a word for reading.
    Description, as the server wrote it
    Poll an asynchronous report request. A succeeded job provides result_url; then fetch the report with get_study_report.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Report Job
  • get_report_slide_jobPoll an editable PowerPoint export.No findings

    Why it is in this group

    • The name "get_report_slide_job" says "get": a word for reading.
    Description, as the server wrote it
    Poll an editable PowerPoint export. A succeeded job returns a fresh private download URL valid for 15 minutes. The export expires after seven days.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Report Slide Job
  • get_research_analysisRead a run and verified claims, its evidence, eligible timed highlights, exports, source coverage or session history.No findings

    Why it is in this group

    • The name "get_research_analysis" says "get": a word for reading.
    Description, as the server wrote it
    Read a run and verified claims, its evidence, eligible timed highlights, exports, source coverage or session history. Follow next_cursor until exhausted. Evidence includes canonical transcript locators; audio eligibility requires a complete participant turn and owned recording. Authorization is checked on every read.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Inspect Research Analysis
  • get_research_deliverablePoll a research export.No findings

    Why it is in this group

    • The name "get_research_deliverable" says "get": a word for reading.
    Description, as the server wrote it
    Poll a research export. A succeeded job returns a fresh private download_url with source access rechecked at download. Expired or revoked sources cannot be downloaded.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Research Deliverable
  • get_studyGet the full persisted study, including the plan, audience targeting, screeners, and concept assets managed by customize_study.No findings

    Why it is in this group

    • The name "get_study" says "get": a word for reading.
    Description, as the server wrote it
    Get the full persisted study, including the plan, audience targeting, screeners, and concept assets managed by customize_study. Call before metadata updates and after customization to verify the result. After customization, return the complete persisted study_plan to the user in a readable form. Panel launch approval happens in the launch_panel MCP App, or explicit human chat confirmation when the client does not support Apps. Obtain explicit approval of the current plan before BYOP participant creation; retain study_id and updated_at so unchanged approval survives a resumed workflow. When provisioning_status is provisioned, include both returned links in the completion response. dashboard_url is the researcher management link. study_link is the live participant interview link, not a test or preview link; opening it starts the participant experience. The public API does not expose a separate researcher-preview URL.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Study
  • get_study_reportRead one study's finished report (findings, themes, quotes); does not answer new questions.No findings

    Why it is in this group

    • The name "get_study_report" says "get": a word for reading.
    Description, as the server wrote it
    Read one study's finished report (findings, themes, quotes); does not answer new questions. Returns a small overview by default. Set view to one section (study_findings, participant_profiles, participant_responses, evidence_coverage, recommended_next_steps, or references), or full when all data is needed. included_sections distinguishes omitted sections from empty ones. Findings include structured prevalence and source quotes when available.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Study Report
  • get_webhookGet a webhook by ID without revealing its signing secret.Reads private dataNo findings

    Why it is in this group

    • The name "get_webhook" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "get" and "secret": it reads secrets.
    Description, as the server wrote it
    Get a webhook by ID without revealing its signing secret.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Webhook
  • inspect_research_sessionRead research sessions (each a saved analysis workspace of selected studies and uploaded files), one session, its sources, chronological chat history, a background job, or saved ou…Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "inspect_research_session" says "inspect": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "read" and "file": it reads files.
    • untrusted-inputThe description's first sentence says "read" and "chat": it reads messages, which other people can write.
    Description, as the server wrote it
    Read research sessions (each a saved analysis workspace of selected studies and uploaded files), one session, its sources, chronological chat history, a background job, or saved outputs such as reports and slide decks. Set session_id except when view=sessions; job needs job_id, output needs output_id. Follow next_cursor unchanged as after. Job success includes answer/references or output_id; partial remains explicit. Read the existing output before editing it.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Inspect Research Session
  • list_feasibility_requestsList the account feasibility requests, newest first, in bounded pages.No findings

    Why it is in this group

    • The name "list_feasibility_requests" says "list": a word for reading.
    Description, as the server wrote it
    List the account feasibility requests, newest first, in bounded pages.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: List Feasibility Requests
  • list_interviewsList lightweight interview rows.No findings

    Why it is in this group

    • The name "list_interviews" says "list": a word for reading.
    Description, as the server wrote it
    List lightweight interview rows. Fetch an interview to get messages, recordings, and screener responses.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: List Interviews
  • list_organizationsList organizations you can access.No findings

    Why it is in this group

    • The name "list_organizations" says "list": a word for reading.
    Description, as the server wrote it
    List organizations you can access. Users can belong to multiple organizations. Search by organization name, active owner name, or owner email; returns IDs and owner contacts. Ask the human which organization to use, then supply organization_id on subsequent tools.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: List Organizations
  • list_participantsList participants (BYOP invitations) with each personal interview link, status and visible interview count.No findings

    Why it is in this group

    • The name "list_participants" says "list": a word for reading.
    Description, as the server wrote it
    List participants (BYOP invitations) with each personal interview link, status and visible interview count. These are study participations, not deduplicated people; use list_interviews(participant_id) for the sessions. Panel and open-link respondents are anonymous interviews.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: List Participants
  • list_studiesList lightweight studies, sorted by updated_at descending then ID.No findings

    Why it is in this group

    • The name "list_studies" says "list": a word for reading.
    Description, as the server wrote it
    List lightweight studies, sorted by updated_at descending then ID. Filter before pagination by provisioning status, recruiting method, creation date, or report availability. interview_count is completed visible non-test interviews; use get_study for the full plan, screeners, and targeting.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: List Studies
  • list_targeting_attributesSearch the panel targeting catalog by name or category.No findings

    Why it is in this group

    • The name "list_targeting_attributes" says "list": a word for reading.
    Description, as the server wrote it
    Search the panel targeting catalog by name or category. Use its qualification and option IDs when configuring a panel study. The full study response also resolves saved targeting to readable labels; age bands can be approximate.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: List Targeting Attributes
  • list_webhook_deliveriesList bounded delivery attempts, status codes, and coarse failure reasons without payloads.No findings

    Why it is in this group

    • The name "list_webhook_deliveries" says "list": a word for reading.
    Description, as the server wrote it
    List bounded delivery attempts, status codes, and coarse failure reasons without payloads.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: List Webhook Deliveries
  • list_webhooksList account webhooks and their study scopes.No findings

    Why it is in this group

    • The name "list_webhooks" says "list": a word for reading.
    Description, as the server wrote it
    List account webhooks and their study scopes. Signing secrets are never included.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: List Webhooks
  • search_researchSearch findings, participant responses, and study plans from your User Intuition study reports, across one or more studies.No findings

    Why it is in this group

    • The name "search_research" says "search": a word for reading.
    Description, as the server wrote it
    Search findings, participant responses, and study plans from your User Intuition study reports, across one or more studies. Results are grouped under studies[] with each study_id, index_status (ready, updating, or not_indexed), latest_report_id, indexed_report_id, and matching canonical content. No generated prose is returned. Pass next_cursor back with the same query, filters, and limit to continue; stop when it is null.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Search Research
  • view_research_answerShow the full answer in this MCP chat with clickable verified quotes and original recordings.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "view_research_answer" says "view": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "show" and "chat": it reads messages.
    • untrusted-inputThe description's first sentence says "show" and "chat": it reads messages, which other people can write.
    Description, as the server wrote it
    Show the full answer in this MCP chat with clickable verified quotes and original recordings. Use this to display the answer after research chat, rather than linking to an external dashboard. Use after chat_research_session or queue_research_chat; pending jobs can be checked here. Keep session_id and job_id for follow-ups. Set reference_label to read one cited quotation and its transcript/recording context. Preserves backend citation labels; never invent sources.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: View Research Answer

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

132 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.

Reads private data3
Reads files, mail, messages, databases, secrets, calendars or repositories.
Can send data out2
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__research__send_participant_reward",
      "mcp__research__test_webhook"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:28 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
51
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://mcp.userintuition.ai/.well-known/oauth-protected-resource/mcp
Authorization servers
https://mcp.userintuition.ai/
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 51 tools that change things (28 destructive, 23 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.userintuition.ai/mcp: tools/list returned 79 tools to an anonymous client, including customize_study (destructive), queue_customize_study (destructive), launch_panel (destructive), approve_panel_launch (destructive), create_participants (destructive) and 46 more

    What this check looks for

Posture changes

  1. Nov 13, 2026
    • HTTP status of an anonymous initialize: 401 to 200
    • tools/list served without credentials: no to yes
    • Tools that change things, listed without credentials: 0 to 51
    • Protocol version: none to 2025-06-18
    • WWW-Authenticate on 401: yes to not observed
    • resource_metadata in WWW-Authenticate: https://mcp.userintuition.ai/.well-known/oauth-protected-resource/mcp to none

Findings

Matches of fixed checks, with the text they matched.

1 warn1 info
  • The server marks "review_study" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "open": a word for a change.

    What this check looks for
  • The description is 2,015 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...r chat as well as voice and video. Next: send the brief to queue_customize_study."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools4 changed.~4 changedView diff
  2. Tools4 changed.~4 changedView diff
  3. PostureRemote posture changed. HTTP status of an anonymous initialize: 401 -> 200; tools/list served without credentials: no -> yes; Tools that change things, listed without credentials: 0 -> 51 (and 3 more).View diff
    • HTTP status of an anonymous initialize: 401 to 200
    • tools/list served without credentials: no to yes
    • Tools that change things, listed without credentials: 0 to 51
    • Protocol version: none to 2025-06-18
    • WWW-Authenticate on 401: yes to not observed
    • resource_metadata in WWW-Authenticate: https://mcp.userintuition.ai/.well-known/oauth-protected-resource/mcp to none

Install

Pinned to version 1.6.5. Values in angle brackets are yours to fill in.

claude mcp add --transport http research https://mcp.userintuition.ai/mcp
claude mcp add --transport http research https://mcp.userintuition.ai/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__research__get_customize_study_job",
      "mcp__research__get_study",
      "mcp__research__get_participant_job",
      "mcp__research__get_fielding_progress",
      "mcp__research__get_report_job",
      "mcp__research__get_study_report",
      "mcp__research__search_research",
      "mcp__research__view_research_answer",
      "mcp__research__list_studies",
      "mcp__research__list_organizations",
      "mcp__research__get_account",
      "mcp__research__get_report_slide_job",
      "mcp__research__list_participants",
      "mcp__research__get_participant",
      "mcp__research__list_interviews",
      "mcp__research__get_interview",
      "mcp__research__list_targeting_attributes",
      "mcp__research__get_research_analysis",
      "mcp__research__get_research_deliverable",
      "mcp__research__inspect_research_session",
      "mcp__research__download_research_output",
      "mcp__research__get_interview_usage_stats",
      "mcp__research__list_webhooks",
      "mcp__research__get_webhook",
      "mcp__research__list_webhook_deliveries",
      "mcp__research__get_external_panel",
      "mcp__research__list_feasibility_requests",
      "mcp__research__get_feasibility_request"
    ],
    "ask": [
      "mcp__research__create_study",
      "mcp__research__review_study",
      "mcp__research__estimate_panel",
      "mcp__research__generate_report",
      "mcp__research__answer_research",
      "mcp__research__chat_research_session",
      "mcp__research__pause_study",
      "mcp__research__resume_study",
      "mcp__research__queue_report_slides",
      "mcp__research__create_research_session",
      "mcp__research__rename_research_session",
      "mcp__research__sync_research_study",
      "mcp__research__start_research_analysis",
      "mcp__research__resume_research_analysis",
      "mcp__research__queue_research_deliverable",
      "mcp__research__upload_research_source",
      "mcp__research__queue_research_chat",
      "mcp__research__generate_research_output",
      "mcp__research__rename_research_output",
      "mcp__research__upload_research_template",
      "mcp__research__create_webhook",
      "mcp__research__submit_feasibility_request",
      "mcp__research__add_all_research_studies"
    ],
    "deny": [
      "mcp__research__customize_study",
      "mcp__research__queue_customize_study",
      "mcp__research__launch_panel",
      "mcp__research__approve_panel_launch",
      "mcp__research__create_participants",
      "mcp__research__update_study",
      "mcp__research__delete_study",
      "mcp__research__stop_study",
      "mcp__research__update_participant",
      "mcp__research__send_participant_reward",
      "mcp__research__delete_participant",
      "mcp__research__delete_interview",
      "mcp__research__delete_research_session",
      "mcp__research__remove_research_study",
      "mcp__research__remove_research_source",
      "mcp__research__cancel_research_analysis",
      "mcp__research__cancel_research_deliverable",
      "mcp__research__edit_research_output",
      "mcp__research__delete_research_output",
      "mcp__research__rotate_webhook_secret",
      "mcp__research__test_webhook",
      "mcp__research__delete_webhook_by_id",
      "mcp__research__delete_webhook",
      "mcp__research__configure_external_panel",
      "mcp__research__regenerate_external_panel_token",
      "mcp__research__delete_external_panel",
      "mcp__research__cancel_feasibility_request",
      "mcp__research__clear_research_sources"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as research. Review it before you use it.

Capability tags behind 23 rules
  • mcp__research__customize_study untrusted-input
  • mcp__research__queue_customize_study untrusted-input
  • mcp__research__launch_panel untrusted-input
  • mcp__research__approve_panel_launch untrusted-input
  • mcp__research__create_participants untrusted-input
  • mcp__research__generate_report untrusted-input
  • mcp__research__view_research_answer private-data, untrusted-input
  • mcp__research__pause_study untrusted-input
  • mcp__research__resume_study untrusted-input
  • mcp__research__stop_study untrusted-input
  • mcp__research__update_participant untrusted-input
  • mcp__research__send_participant_reward untrusted-input, outbound
  • mcp__research__start_research_analysis untrusted-input
  • mcp__research__resume_research_analysis untrusted-input
  • mcp__research__inspect_research_session private-data, untrusted-input
  • mcp__research__create_webhook untrusted-input
  • mcp__research__get_webhook private-data
  • mcp__research__test_webhook untrusted-input, outbound
  • mcp__research__delete_webhook_by_id untrusted-input
  • mcp__research__delete_webhook untrusted-input
  • mcp__research__configure_external_panel untrusted-input
  • mcp__research__regenerate_external_panel_token untrusted-input
  • mcp__research__delete_external_panel untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/ai.userintuition/research/verify?hash=dd659e62e8e031dc5af13ce620b2512a884237580920c3a61e163725b6d27064" | jq -e '.changed == false'

Pinned hash dd659e62e8e0, from Nov 20, 2026, 15:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/ai.userintuition/research/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for ai.userintuition/research
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.userintuition/research.svg)](https://radar.anlyon.com/servers/ai.userintuition/research)

Source: MCP Registry. Synced Nov 20, 2026, 15:17 UTC.

User Intuition MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the User Intuition MCP server safe?

No scan can promise that. What its definitions show: 79 tools, 51 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the User Intuition MCP server delete data?

Yes. 28 tools can delete, cancel or revoke something: customize_study, queue_customize_study, launch_panel, approve_panel_launch, create_participants, update_study and 22 more.

Can the User Intuition MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the User Intuition MCP server have?

79 tools: 28 destructive, 23 write, 28 read. customize_study, queue_customize_study, launch_panel, approve_panel_launch, create_participants, update_study, delete_study, stop_study and 71 more.

Does the User Intuition MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the User Intuition MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_participant_reward and test_webhook.

Has the User Intuition MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.