Skip to content

Fictura MCP server

co.fictura/mcpfictura.costreamable-httpv0.1.2Scanned

Paywalls, onboarding, subscription analytics, A/B tests, attribution and errors for mobile apps.

75 tools: 6 can delete or cancel things, 15 change things and 54 only read.

Tools: 6 delete, 0 irreversible, 15 write, 54 read.
  • Reads private data · 11
  • Reads text others write · 19
  • Can send data out · 3
  • 7 findings

Tools listed without sign-in. Remote posture

With Anlyon

6 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 Fictura MCP server can do

The Fictura MCP server is published by fictura.co, a domain the MCP Registry verified. It has 75 tools. It can delete or cancel things (6 tools: update_app_identity, create_inbound_filter, delete_inbound_filter, save_paywall_doc and 2 more) and create or change data (15 tools: create_tracking_link, check_entitlement, get_store_analytics, list_error_issues and 11 more). 54 tools only read.

11 tools read private data (search_docs, list_docs, read_doc and 8 more); 19 tools bring in text other people can write (get_app_setup, list_users, get_store_analytics and 16 more); 3 tools can send data out of your system (update_error_issue, update_error_issues and set_uptime_monitor). 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 7 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.

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

Last scanned Nov 11, 2026, version 0.1.2.

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.

75 tools

Deletes or cancels 6Claude Code: deny
  • create_inbound_filterDrop matching errors at ingest from now on (within 30 seconds): counted, never stored, grouped or alerted on.1 finding

    Why it is in this group

    • The name "create_inbound_filter" says "create": a word for a change.
    • The description's first verb is "drop": a word for removing or ending something.
    • The server marks it not destructive (destructiveHint: false), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "create_inbound_filter" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "create_inbound_filter" says "create": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Drop matching errors at ingest from now on (within 30 seconds): counted, never stored, grouped or alerted on. Use it for noise nobody will fix. Kinds as in list_inbound_filters; environment `simulator` drops events from simulators and emulators. Refuses an exact duplicate. Only works when the app allows MCP writes.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Add an inbound filter
  • delete_inbound_filterStop dropping what one inbound filter matches; new events land again within 30 seconds.No findings

    Why it is in this group

    • The name "delete_inbound_filter" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Stop dropping what one inbound filter matches; new events land again within 30 seconds. Events it already dropped are not recovered. Take the id from list_inbound_filters. Only works when the app allows MCP writes.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
    • title: Delete an inbound filter
  • editor_set_docReplaces the document in the person's open editor with the one given.No findings

    Why it is in this group

    • The name "editor_set_doc" says "set": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Replaces the document in the person's open editor with the one given. It is NOT saved: the person sees the change, can undo it, and saves it themselves. The document is validated first and refused with the problems if it does not parse. Needs an MCP key that can edit.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • title: Put a document on the paired editor's canvas
    • openWorldHint: false
  • save_onboarding_docReplaces a draft flow's document with the one given, as a new version (the dashboard's history shows it as `mcp: <note>` and can roll it back).No findings

    Why it is in this group

    • The name "save_onboarding_doc" says "save": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Replaces a draft flow's document with the one given, as a new version (the dashboard's history shows it as `mcp: <note>` and can roll it back). Refused for a live flow. Needs an MCP key that can edit. Translations, overrides and the exit setting are kept.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • title: Save a DRAFT onboarding flow's document
    • openWorldHint: false
  • save_paywall_docReplaces a draft paywall's document with the one given, as a new version (History in the dashboard shows it as `mcp: <note>` and can roll it back).No findings

    Why it is in this group

    • The name "save_paywall_doc" says "save": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Replaces a draft paywall's document with the one given, as a new version (History in the dashboard shows it as `mcp: <note>` and can roll it back). Refused for a live paywall — copy it in the dashboard first. Needs an MCP key that can edit. Products, translations and other settings are kept.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • title: Save a DRAFT paywall's document
    • openWorldHint: false
  • update_app_identitySaves what the app IS to Apple, Google and the web: the iOS bundle ID and Apple Team ID (which build the Universal Links file), the Android package and signing fingerprints (which …No findings

    Why it is in this group

    • The name "update_app_identity" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Saves what the app IS to Apple, Google and the web: the iOS bundle ID and Apple Team ID (which build the Universal Links file), the Android package and signing fingerprints (which build the App Links file), both store addresses and the website. Send only the fields you know. Every value is checked before saving, because a bad one makes links fail with no error anywhere. A value already saved is not overwritten unless replace_existing is true: changing a bundle ID on a live app breaks its links, so ask the person first. Needs read and edit access.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • title: Save this app's bundle ID, Team ID and store details
    • openWorldHint: false
Changes things 15Claude Code: ask
  • check_entitlementThe authoritative paid/not-paid verdict for one user, unified across Stripe, RevenueCat, App Store and Play — the same answer GET /api/v1/entitlements/{user_id} returns to a server…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
    The authoritative paid/not-paid verdict for one user, unified across Stripe, RevenueCat, App Store and Play — the same answer GET /api/v1/entitlements/{user_id} returns to a server. Note: `environment` is SANDBOX when the verdict rests on test purchases, so always check it before granting production access; a cancellation only flips will_renew (access runs to expires_at); and an unknown user is a valid 'none' answer, not an error.

    Annotations the server declares

    • readOnlyHint: true
    • title: Check whether a user is subscribed
    • destructiveHint: false
    • openWorldHint: false
  • create_onboarding_draftCreates a draft onboarding flow from a document you wrote (see get_onboarding_doc's reference).No findings

    Why it is in this group

    • The name "create_onboarding_draft" says "create": a word for a change.
    Description, as the server wrote it
    Creates a draft onboarding flow from a document you wrote (see get_onboarding_doc's reference). It is never made live: going live is done in the dashboard. Needs an MCP key that can edit.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • title: Create a new DRAFT onboarding flow
    • openWorldHint: false
  • create_paywall_draftCreates a draft paywall from a Studio template (template_key, from list_templates — the webview ones) or from a document you wrote.No findings

    Why it is in this group

    • The name "create_paywall_draft" says "create": a word for a change.
    Description, as the server wrote it
    Creates a draft paywall from a Studio template (template_key, from list_templates — the webview ones) or from a document you wrote. It is never made live: going live is done in the dashboard. Needs an MCP key that can edit.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • title: Create a new DRAFT Studio paywall
    • openWorldHint: false
  • get_store_analyticsStore-reported numbers synced from Appfigures: downloads, re-downloads, updates, uninstalls, store revenue after the store's cut (subscriptions, in-app purchases, ads), top countri…Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe description's first sentence says "store" and "review": it reads comments, which other people can write.

    Findings

    • Warn

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

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "get_store_analytics" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Store-reported numbers synced from Appfigures: downloads, re-downloads, updates, uninstalls, store revenue after the store's cut (subscriptions, in-app purchases, ads), top countries, the ratings snapshot, recent reviews with text, and category chart positions. Money is in micros of `currency`. Store revenue is a separate figure from RevenueCat revenue; never add the two. Returns connected: false when Appfigures is not set up.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get App Store and Google Play analytics (Appfigures)
    • destructiveHint: false
    • openWorldHint: false
  • list_error_issuesStart here to see what is broken: grouped issues from the backend and the app together, each with its source, level, status, event and user counts.Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe name "list_error_issues" says "list" and "issue": it reads issues, which other people can write.
    • untrusted-inputThe description's first sentence says "start" and "issue": it reads issues, which other people can write.

    Findings

    • Warn

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

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "list_error_issues" says "list": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Start here to see what is broken: grouped issues from the backend and the app together, each with its source, level, status, event and user counts. Newest activity first, unresolved only. Console lines from the app are hidden unless include_console is true. Pass next_cursor to read on.

    Annotations the server declares

    • readOnlyHint: true
    • title: List error issues
    • destructiveHint: false
    • openWorldHint: false
  • pair_editorConnects to the paywall editor a person has open, using the 6-character code shown under “Pair an agent” in the Studio.No findings

    Why it is in this group

    • The input takes a statement or command to run (input.code), which can change anything it can reach.
    Description, as the server wrote it
    Connects to the paywall editor a person has open, using the 6-character code shown under “Pair an agent” in the Studio. Returns a pairing_id for the editor_* tools. The code works once and for 10 minutes; a pairing lasts 24 hours or until either side stops it.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • title: Pair with an open Studio editor
    • openWorldHint: false
  • set_uptime_monitorSet or replace the URL Fictura pings every minute (three failures in a row mark it down and alert).Can send data outNo findings

    Why it is in this group

    • The name "set_uptime_monitor" says "set": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Set or replace the URL Fictura pings every minute (three failures in a row mark it down and alert). A new URL starts over as unknown. enabled false pauses it. Only works when the app allows MCP writes.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Set the uptime monitor
  • start_appsflyer_importImport everything AppsFlyer holds for this app: installs and the channel, campaign, adset and ad behind each one, in-app events and purchases, uninstalls, reinstalls, ad revenue an…Reads text others writeNo findings

    Why it is in this group

    • The name "start_appsflyer_import" 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
    Import everything AppsFlyer holds for this app: installs and the channel, campaign, adset and ad behind each one, in-app events and purchases, uninstalls, reinstalls, ad revenue and retargeting traffic. All twelve raw-data reports are walked; ones the AppsFlyer plan lacks are skipped, not failed. Runs in the background and keeps going after this call. mode 'auto' (default) only pulls the days since the last finished import when there is one, and walks the full history otherwise. 'full' re-walks everything. resume=true continues a failed or cancelled run from where it stopped. Safe to call while a run is going: it reports that run instead of starting another. Anything already imported is counted once. Check progress with get_appsflyer_import_status.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • title: Start the AppsFlyer import
  • unpair_editorStops this pairing.No findings

    Why it is in this group

    • The description's first verb is "stop": a word for a change.
    Description, as the server wrote it
    Stops this pairing. The editor shows that the agent left.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • title: End the pairing with the editor
    • openWorldHint: false
  • update_error_issueResolve, ignore or reopen an issue, assign it, set its priority, or add a note.Can send data outNo findings

    Why it is in this group

    • The name "update_error_issue" says "update": a word for a change.

    What it can reach

    • outboundThe name "update_error_issue" says "update" and "issue": it writes something other people read.
    Description, as the server wrote it
    Resolve, ignore or reopen an issue, assign it, set its priority, or add a note. Only works when the app allows MCP writes (Issues settings → Let MCP keys change issues).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Change an error issue
  • update_error_issuesThe same change on up to 100 issues: resolve, ignore or reopen them, assign them, set their priority, or add a note to each.Can send data outNo findings

    Why it is in this group

    • The name "update_error_issues" says "update": a word for a change.

    What it can reach

    • outboundThe name "update_error_issues" says "update" and "issue": it writes something other people read.
    Description, as the server wrote it
    The same change on up to 100 issues: resolve, ignore or reopen them, assign them, set their priority, or add a note to each. Answers per issue, with counts. Only works when the app allows MCP writes (Issues settings → Let MCP keys change issues).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
    • title: Change several error issues
  • update_tracing_settingsSet the share of traces the SDKs keep, and the hosts the app's SDK sends trace headers to (replacing the list).No findings

    Why it is in this group

    • The name "update_tracing_settings" says "update": a word for a change.
    Description, as the server wrote it
    Set the share of traces the SDKs keep, and the hosts the app's SDK sends trace headers to (replacing the list). A field you leave out keeps its value. SDKs read it from their config within a minute. Only works when the app allows MCP writes.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Change tracing settings
  • validate_onboarding_docRuns a document through the same parser, step-key check and renderer a save uses and reports what is wrong, if anything.1 finding

    Why it is in this group

    • The name "validate_onboarding_doc" says "validate": a word for reading.
    • The description's first verb is "run": 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 "validate_onboarding_doc" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "validate_onboarding_doc" says "validate": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Runs a document through the same parser, step-key check and renderer a save uses and reports what is wrong, if anything. Changes nothing.

    Annotations the server declares

    • readOnlyHint: true
    • title: Check an onboarding document without saving it
    • destructiveHint: false
    • openWorldHint: false
  • validate_paywall_docRuns a document through the same parser and renderer a save uses and reports what is wrong, if anything.1 finding

    Why it is in this group

    • The name "validate_paywall_doc" says "validate": a word for reading.
    • The description's first verb is "run": 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 "validate_paywall_doc" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "validate_paywall_doc" says "validate": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Runs a document through the same parser and renderer a save uses and reports what is wrong, if anything. Changes nothing.

    Annotations the server declares

    • readOnlyHint: true
    • title: Check a paywall document without saving it
    • destructiveHint: false
    • openWorldHint: false
Only reads 54Show 54 read-only tools
  • compare_releasesEvery route, screen and page seen in both releases, with count, p50, p95 and error rate in each, sorted by the extra time per minute release b spends against a: what got slower or …No findings

    Why it is in this group

    • The name "compare_releases" says "compare": a word for reading.
    Description, as the server wrote it
    Every route, screen and page seen in both releases, with count, p50, p95 and error rate in each, sorted by the extra time per minute release b spends against a: what got slower or faster. Also what appears in only one of them. Take release names from list_releases or get_tracing_health.

    Annotations the server declares

    • readOnlyHint: true
    • title: Compare two releases
    • destructiveHint: false
    • openWorldHint: false
  • editor_get_docThe document exactly as it is on the person's screen (unsaved changes included), which paywall it is, the screen they are on and the node they have selected, plus the document mode…Reads private dataNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe name "editor_get_doc" says "get" and "doc": it reads documents.
    • private-dataThe description's first sentence says "document": it reads documents.
    Description, as the server wrote it
    The document exactly as it is on the person's screen (unsaved changes included), which paywall it is, the screen they are on and the node they have selected, plus the document model reference. Read this before editor_set_doc and edit what you got — keep node ids, change only what was asked.

    Annotations the server declares

    • readOnlyHint: true
    • title: Read the document open in the paired editor
    • destructiveHint: false
    • openWorldHint: false
  • get_acquisition_report`roas` gives per-campaign spend, attributed installs/trials/paying users, revenue, CPI, CAC and ROAS, plus blended totals and explicitly-unattributed revenue — always keep attribut…No findings

    Why it is in this group

    • The name "get_acquisition_report" says "get": a word for reading.
    Description, as the server wrote it
    `roas` gives per-campaign spend, attributed installs/trials/paying users, revenue, CPI, CAC and ROAS, plus blended totals and explicitly-unattributed revenue — always keep attributed and blended figures apart when reporting these. `spend` gives raw daily ad-spend rows. `links` lists this app's tracking links.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get paid acquisition performance
    • destructiveHint: false
    • openWorldHint: false
  • get_ai_usageModel calls by model (gen_ai spans): calls, per minute, error rate, p50 to p99, total time, input and output tokens; and MCP tool calls by tool (mcp.server spans).No findings

    Why it is in this group

    • The name "get_ai_usage" says "get": a word for reading.
    Description, as the server wrote it
    Model calls by model (gen_ai spans): calls, per minute, error rate, p50 to p99, total time, input and output tokens; and MCP tool calls by tool (mcp.server spans). Prompt and completion text is never stored, so it is never here.

    Annotations the server declares

    • readOnlyHint: true
    • title: AI model and MCP tool calls
    • destructiveHint: false
    • openWorldHint: false
  • get_analyticsThis app's real numbers.No findings

    Why it is in this group

    • The name "get_analytics" says "get": a word for reading.
    Description, as the server wrote it
    This app's real numbers. `overview` gives headline metrics (users, trials, trial→paid rate, events by name, cancel reasons, 14-day activity). `funnel` gives the ordered conversion funnel with per-step drop-off. `cohorts` compares behaviour across billing outcomes — what converted users did that cancelled users didn't. Below ~100 users in a step the sample is too small to read. `stores` splits paying users, purchases and revenue by App Store / Google Play / web and by storefront country (last 28 days).

    Annotations the server declares

    • readOnlyHint: true
    • title: Get funnel, overview or cohort analytics
    • destructiveHint: false
    • openWorldHint: false
  • get_app_setupThe real values needed to wire the Fictura SDK into a codebase: the API base URL, this app's publishable SDK key (gk_…), and the RevenueCat webhook URL.Reads text others write2 findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.

    Findings

    • Info

      The title mentions "credentials".

      Matched text

      title: "Get this app's Fictura credentials and endpoints"

      What this check looks for
    • Info

      The annotations title mentions "credentials".

      Matched text

      annotations.title: "Get this app's Fictura credentials and endpoints"

      What this check looks for
    Description, as the server wrote it
    The real values needed to wire the Fictura SDK into a codebase: the API base URL, this app's publishable SDK key (gk_…), and the RevenueCat webhook URL. ALWAYS call this before generating integration code — never leave a placeholder API key in what you write. The SDK key is publishable and safe to commit in app source; it identifies the app, not a person.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get this app's Fictura credentials and endpoints
    • destructiveHint: false
    • openWorldHint: false
  • get_appsflyer_attribution_summaryWhat the AppsFlyer import brought in about where people came from: people with an imported attribution, split by media source (organic included) and acquisition vs retargeting, plu…No findings

    Why it is in this group

    • The name "get_appsflyer_attribution_summary" says "get": a word for reading.
    Description, as the server wrote it
    What the AppsFlyer import brought in about where people came from: people with an imported attribution, split by media source (organic included) and acquisition vs retargeting, plus the top campaigns. Filters on the install date. Imported verdicts never overwrite an attribution Fictura's own SDK resolved. For revenue and ROAS by source, use get_attribution_report with view=kpis.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • title: Summarize imported AppsFlyer attribution
    • destructiveHint: false
  • get_appsflyer_import_statusWhether AppsFlyer is connected, the latest import run (status, progress, rows imported, duplicates skipped, people created, date range covered, error if it stopped), and whether an…No findings

    Why it is in this group

    • The name "get_appsflyer_import_status" says "get": a word for reading.
    Description, as the server wrote it
    Whether AppsFlyer is connected, the latest import run (status, progress, rows imported, duplicates skipped, people created, date range covered, error if it stopped), and whether an import has ever finished. Call before start_appsflyer_import so a finished import is not offered again as though nothing had happened.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • title: Get AppsFlyer import status
    • destructiveHint: false
  • get_attribution_reportWhere installs and revenue actually came from.No findings

    Why it is in this group

    • The name "get_attribution_report" says "get": a word for reading.
    Description, as the server wrote it
    Where installs and revenue actually came from. `summary` is the headline attribution picture (installs, organic vs non-organic, revenue). `kpis` breaks the same window down by source, campaign, link or day. `installs` lists individual installs with their attribution. Defaults to the trailing 28 days.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get attribution, install and KPI reporting
    • destructiveHint: false
    • openWorldHint: false
  • get_endpoint_summaryEverything about one row of the Performance page, to answer 'why is this slow?': count, error rate, p50 to p99 and the change against the window before; where the time goes inside …Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "database": it reads databases.
    • untrusted-inputThe description's first sentence says "http": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Everything about one row of the Performance page, to answer 'why is this slow?': count, error rate, p50 to p99 and the change against the window before; where the time goes inside each request (database, HTTP and model calls, and the backend routes a screen waited on); what the slowest 10% have that the rest don't (release, status, device…) and which inner spans grow most in them; who calls a dependency; per-release numbers; sample traces (slowest, typical, fastest, failed: open them with get_trace); and the open issues on that route. op is like http.server, ui.load, ui.pageload, http.client, db, gen_ai, task; route is the route, screen, page, host or table as get_performance_overview lists it.

    Annotations the server declares

    • readOnlyHint: true
    • title: Explain one route, screen or dependency
    • destructiveHint: false
    • openWorldHint: false
  • get_error_eventOne occurrence: frames with source lines and variables, request, tags, contexts, breadcrumbs, causes and trace id.No findings

    Why it is in this group

    • The name "get_error_event" says "get": a word for reading.
    Description, as the server wrote it
    One occurrence: frames with source lines and variables, request, tags, contexts, breadcrumbs, causes and trace id. Pass issue_id for its latest event, or event_id. Use it to see why one error happened. Long events give up variables, then library frames, then breadcrumbs, and `truncated` says what went: call again with section to read that part whole.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get one error event in full
    • destructiveHint: false
    • openWorldHint: false
  • get_error_issueOne issue with its status, history, 30 days of daily counts and recent occurrences.Reads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe name "get_error_issue" says "get" and "issue": it reads issues, which other people can write.
    • untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.
    Description, as the server wrote it
    One issue with its status, history, 30 days of daily counts and recent occurrences. The newest occurrence has its stack and frames, the older ones are one-line summaries. Use it to see how an issue behaves over time. For a fix, get_error_issue_brief is shorter; for source lines and variables, use get_error_event.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get one error issue
    • destructiveHint: false
    • openWorldHint: false
  • get_error_issue_briefUse this first when asked to fix an error.Reads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe name "get_error_issue_brief" says "get" and "issue": it reads issues, which other people can write.
    Description, as the server wrote it
    Use this first when asked to fix an error. One issue condensed: in-app frames with their source lines, the request, tags, breadcrumbs before it, log lines from the same trace, facets (release, OS, device, route), cause chain, and a ready-to-use fix prompt.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get an issue brief and a fix prompt
    • destructiveHint: false
    • openWorldHint: false
  • get_error_settingsThis app's error settings (auto-resolve days, built-in noise rules, crash-free threshold, digest, code links, retention, whether MCP may write) and tracing settings (sample rate, h…No findings

    Why it is in this group

    • The name "get_error_settings" says "get": a word for reading.
    Description, as the server wrote it
    This app's error settings (auto-resolve days, built-in noise rules, crash-free threshold, digest, code links, retention, whether MCP may write) and tracing settings (sample rate, hosts that get trace headers). connection_can_write says whether this connection's write tools will work.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get error and tracing settings
    • destructiveHint: false
    • openWorldHint: false
  • get_experimentOne experiment with its variants and full Bayesian results.No findings

    Why it is in this group

    • The name "get_experiment" says "get": a word for reading.
    Description, as the server wrote it
    One experiment with its variants and full Bayesian results.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get one experiment
    • destructiveHint: false
    • openWorldHint: false
  • get_issue_activityWhat people and Fictura did to one issue, newest first: status changes, assignments, priority, notes with their text, tickets, regressions.Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "note": it reads notes.
    • untrusted-inputThe name "get_issue_activity" says "get" and "issue": it reads issues, which other people can write.
    • untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.
    Description, as the server wrote it
    What people and Fictura did to one issue, newest first: status changes, assignments, priority, notes with their text, tickets, regressions. Use it before changing an issue, to see who already looked at it.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get an issue's history
    • destructiveHint: false
    • openWorldHint: false
  • get_issue_tag_valuesHow often each value of one tag or facet appears on one issue in the last 30 days.Reads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe name "get_issue_tag_values" says "get" and "issue": it reads issues, which other people can write.
    • untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.
    Description, as the server wrote it
    How often each value of one tag or facet appears on one issue in the last 30 days. Use it to see where an issue concentrates: which release, route, device, logger or person. Leave out key to list the keys there are.

    Annotations the server declares

    • readOnlyHint: true
    • title: Count the values of one tag on an issue
    • destructiveHint: false
    • openWorldHint: false
  • get_jobsWork done outside requests: background tasks, queue publish and process, and cron runs, with counts, failures and timings; each cron with its last run, its usual gap, and late: tru…No findings

    Why it is in this group

    • The name "get_jobs" says "get": a word for reading.
    Description, as the server wrote it
    Work done outside requests: background tasks, queue publish and process, and cron runs, with counts, failures and timings; each cron with its last run, its usual gap, and late: true when it has not run for twice that gap.

    Annotations the server declares

    • readOnlyHint: true
    • title: Background tasks, queues and crons
    • destructiveHint: false
    • openWorldHint: false
  • get_mobile_vitalsThe mobile app's vitals from real devices: cold (and warm) app start, time to initial display (ttid) and full display (ttfd), slow and frozen frame percentages, and JS stall time; …No findings

    Why it is in this group

    • The name "get_mobile_vitals" says "get": a word for reading.
    Description, as the server wrote it
    The mobile app's vitals from real devices: cold (and warm) app start, time to initial display (ttid) and full display (ttfd), slow and frozen frame percentages, and JS stall time; overall, per screen (busiest first) and per release. Each with p50, p75, p95 and the sample count. platform ios, android or both (default).

    Annotations the server declares

    • readOnlyHint: true
    • title: Mobile vitals
    • destructiveHint: false
    • openWorldHint: false
  • get_onboarding_docThe JSON document a builder-made onboarding flow is made of, with its status and version, plus the reference to the document model.Reads private dataNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe name "get_onboarding_doc" says "get" and "doc": it reads documents.
    • private-dataThe description's first sentence says "document": it reads documents.
    Description, as the server wrote it
    The JSON document a builder-made onboarding flow is made of, with its status and version, plus the reference to the document model. Read this before save_onboarding_doc, and edit the document you got rather than writing one from scratch — keep step keys and node ids, change only what was asked.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get an onboarding flow's document
    • destructiveHint: false
    • openWorldHint: false
  • get_paywall_docThe JSON document a Studio (visual editor) paywall is made of, with its status and version, plus the reference to the document model.Reads private dataNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe name "get_paywall_doc" says "get" and "doc": it reads documents.
    • private-dataThe description's first sentence says "document": it reads documents.
    Description, as the server wrote it
    The JSON document a Studio (visual editor) paywall is made of, with its status and version, plus the reference to the document model. Read this before save_paywall_doc, and edit the document you got rather than writing one from scratch — keep node ids, change only what was asked. Prices are never typed: use {{ products.<slot>.price }} and the other product variables.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get a Studio paywall's document
    • destructiveHint: false
    • openWorldHint: false
  • get_performance_overviewHow fast the app is right now, backend and frontend: backend requests per minute, p95 and error rate against the window before; screen and page load times; then the routes that tak…Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "database": it reads databases.
    • untrusted-inputThe description's first sentence says "http": it reads web pages, which anyone can write.
    Description, as the server wrote it
    How fast the app is right now, backend and frontend: backend requests per minute, p95 and error rate against the window before; screen and page load times; then the routes that take the most total time, the slowest screens and pages, and the slowest dependencies (HTTP hosts, database tables). Start here, then open one with get_endpoint_summary.

    Annotations the server declares

    • readOnlyHint: true
    • title: Performance overview
    • destructiveHint: false
    • openWorldHint: false
  • get_push_configWhether push is set up and who could receive it: registered-device counts per billing cohort (all / paid / trial / free) and whether OneSignal is configured.No findings

    Why it is in this group

    • The name "get_push_config" says "get": a word for reading.
    Description, as the server wrote it
    Whether push is set up and who could receive it: registered-device counts per billing cohort (all / paid / trial / free) and whether OneSignal is configured. Returns counts and configuration only — never device tokens or individual recipients.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get push notification configuration
    • destructiveHint: false
    • openWorldHint: false
  • get_setup_statusWhere this app has got to: the six setup steps and which are really done, worked out from data that has arrived, then the billing state, every Fictura feature toggle and whether it…No findings

    Why it is in this group

    • The name "get_setup_status" says "get": a word for reading.
    Description, as the server wrote it
    Where this app has got to: the six setup steps and which are really done, worked out from data that has arrived, then the billing state, every Fictura feature toggle and whether it is on, and which third-party integrations (Stripe, RevenueCat, Slack, App Store Connect, …) are connected. Use it to check a setup step worked, and to check a feature is enabled before writing code that depends on it — a disabled tool is a server-side kill switch the SDK obeys.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get setup progress, integrations and feature status
    • destructiveHint: false
    • openWorldHint: false
  • get_setup_stepWhat to do for one of Fictura's six setup steps, ready to follow: the instructions, this app's real values (so there is nothing to fill in), the full text of that step's docs pages…Reads private dataNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "doc": it reads documents.
    Description, as the server wrote it
    What to do for one of Fictura's six setup steps, ready to follow: the instructions, this app's real values (so there is nothing to fill in), the full text of that step's docs pages, and how to check it worked. Call this when a person pastes a setup prompt, and follow what it returns rather than recalling the SDK from memory. Steps in order: install, connect, events, attribution, errors, performance.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get the instructions for one setup step
    • destructiveHint: false
    • openWorldHint: false
  • get_spanOne span in full: name, op, service, timing, status, every attribute, the errors that happened in it, and the log lines written while it ran.No findings

    Why it is in this group

    • The name "get_span" says "get": a word for reading.
    Description, as the server wrote it
    One span in full: name, op, service, timing, status, every attribute, the errors that happened in it, and the log lines written while it ran. Take the trace_id and span_id from get_trace.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get one span
    • destructiveHint: false
    • openWorldHint: false
  • get_surfaceThe full configuration of one paywall or onboarding flow, plus its version history.No findings

    Why it is in this group

    • The name "get_surface" says "get": a word for reading.
    Description, as the server wrote it
    The full configuration of one paywall or onboarding flow, plus its version history. Note that configs never contain price strings — prices resolve at render time from the PurchasesAdapter's packages, so never copy a price literal out of (or into) a config.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get one paywall or onboarding flow's config
    • destructiveHint: false
    • openWorldHint: false
  • get_traceOne trace (app → backend → dependencies) as a tree: names, services, start offsets, durations, HTTP status and errors, plus the error events linked to it.Reads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe description's first sentence says "http": it reads web pages, which anyone can write.
    Description, as the server wrote it
    One trace (app → backend → dependencies) as a tree: names, services, start offsets, durations, HTTP status and errors, plus the error events linked to it. Take the trace_id from an event or from search_traces. Use it to see where the time went or what failed first. Long traces page with next_cursor.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get one distributed trace
    • destructiveHint: false
    • openWorldHint: false
  • get_tracing_healthWho is sending traces in the last 24 hours: each service with its SDK and version, frontend or backend, last span, span count, average sample rate and environments; how many of the…No findings

    Why it is in this group

    • The name "get_tracing_health" says "get": a word for reading.
    Description, as the server wrote it
    Who is sending traces in the last 24 hours: each service with its SDK and version, frontend or backend, last span, span count, average sample rate and environments; how many of the app's traces reached a backend (joined traces: zero means the app is not sending traceparent to the API, or the backend is not traced); what ingest refused per day this week (invalid, rate limited, over the daily quota). The first tool to call when performance data looks missing.

    Annotations the server declares

    • readOnlyHint: true
    • title: Is tracing working?
    • destructiveHint: false
    • openWorldHint: false
  • get_tracking_planEvery event this app has ever sent, with volume, last-seen, and whether capture is switched off.No findings

    Why it is in this group

    • The name "get_tracking_plan" says "get": a word for reading.
    Description, as the server wrote it
    Every event this app has ever sent, with volume, last-seen, and whether capture is switched off. Use it before adding instrumentation so you reuse the existing event name instead of introducing a near-duplicate — the name chosen here is the same string an experiment later names as its primary metric.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get the event tracking plan
    • destructiveHint: false
    • openWorldHint: false
  • get_uptime_monitorThe URL Fictura pings every minute for this app, whether it is up or down, the last check, consecutive failures, when the current downtime started, and availability over 24 hours a…Reads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    The URL Fictura pings every minute for this app, whether it is up or down, the last check, consecutive failures, when the current downtime started, and availability over 24 hours and 7 days. monitor is null when none is set.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get the uptime monitor
    • destructiveHint: false
    • openWorldHint: false
  • get_userOne user's identity (every stitched device / account / RevenueCat id), event breakdown, churn state and recent activity.No findings

    Why it is in this group

    • The name "get_user" says "get": a word for reading.
    Description, as the server wrote it
    One user's identity (every stitched device / account / RevenueCat id), event breakdown, churn state and recent activity. Accepts the Fictura master user id, or any identifier the app knows them by — a device id, account id or RevenueCat id.

    Annotations the server declares

    • readOnlyHint: true
    • title: Get one user's full history
    • destructiveHint: false
    • openWorldHint: false
  • get_web_vitalsThe web app's Core Web Vitals from real browsers: a 0 to 100 performance score (LCP 30%, INP 30%, CLS 15%, FCP 15%, TTFB 10%, Google's thresholds), each vital's p75 with its good /…Reads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe name "get_web_vitals" says "get" and "web": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "web": it reads web pages, which anyone can write.
    Description, as the server wrote it
    The web app's Core Web Vitals from real browsers: a 0 to 100 performance score (LCP 30%, INP 30%, CLS 15%, FCP 15%, TTFB 10%, Google's thresholds), each vital's p75 with its good / needs improvement / poor counts, and pages ranked by opportunity (how much the score would rise if that page scored 100).

    Annotations the server declares

    • readOnlyHint: true
    • title: Web vitals
    • destructiveHint: false
    • openWorldHint: false
  • list_alert_rulesThis app's alert rules with their triggers, conditions, channels and throttles.No findings

    Why it is in this group

    • The name "list_alert_rules" says "list": a word for reading.
    Description, as the server wrote it
    This app's alert rules with their triggers, conditions, channels and throttles. defaults_active means no rule is enabled, so the built-in defaults listed there apply. Use it to see what will and won't alert.

    Annotations the server declares

    • readOnlyHint: true
    • title: List alert rules
    • destructiveHint: false
    • openWorldHint: false
  • list_campaignsCampaigns read live from a connected ad platform: status, daily budget and ad sets.No findings

    Why it is in this group

    • The name "list_campaigns" says "list": a word for reading.
    Description, as the server wrote it
    Campaigns read live from a connected ad platform: status, daily budget and ad sets. Returns a not_connected result rather than failing when the provider is not set up. This calls the provider's API, so prefer get_acquisition_report for historical numbers.

    Annotations the server declares

    • readOnlyHint: true
    • title: List live ad campaigns
    • destructiveHint: false
    • openWorldHint: false
  • list_creatorsCreator records with a 28-day funnel per creator (clicks, installs, trials, paying users) and the tracking links tagged to each.No findings

    Why it is in this group

    • The name "list_creators" says "list": a word for reading.
    Description, as the server wrote it
    Creator records with a 28-day funnel per creator (clicks, installs, trials, paying users) and the tracking links tagged to each.

    Annotations the server declares

    • readOnlyHint: true
    • title: List creators and their performance
    • destructiveHint: false
    • openWorldHint: false
  • list_dependenciesThe HTTP hosts and database tables the app's services call, by total time spent: calls, calls per minute, error rate, p50 to p99, 4xx and 5xx.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "list_dependencies" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "database": it reads databases.
    • untrusted-inputThe description's first sentence says "http": it reads web pages, which anyone can write.
    Description, as the server wrote it
    The HTTP hosts and database tables the app's services call, by total time spent: calls, calls per minute, error rate, p50 to p99, 4xx and 5xx. kind http, db or all (default). Open one with get_endpoint_summary (op http.client or db).

    Annotations the server declares

    • readOnlyHint: true
    • title: List dependencies by time spent
    • destructiveHint: false
    • openWorldHint: false
  • list_docsThe full documentation index — every page path, grouped by section, with a one-line description.Reads private dataNo findings

    Why it is in this group

    • The name "list_docs" says "list": a word for reading.

    What it can reach

    • private-dataThe name "list_docs" says "list" and "doc": it reads documents.
    Description, as the server wrote it
    The full documentation index — every page path, grouped by section, with a one-line description. Use it to find the right page when a search term is hard to guess. No API key required.

    Annotations the server declares

    • readOnlyHint: true
    • title: List Fictura documentation pages
    • destructiveHint: false
    • openWorldHint: false
  • list_error_alertsEvery error alert Fictura fired, newest first: when, which trigger, the issue and its source, the channels, and whether it was delivered.Reads text others writeNo findings

    Why it is in this group

    • The name "list_error_alerts" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.
    Description, as the server wrote it
    Every error alert Fictura fired, newest first: when, which trigger, the issue and its source, the channels, and whether it was delivered. Use it to check an alert went out, or what paged someone.

    Annotations the server declares

    • readOnlyHint: true
    • title: List alerts that fired
    • destructiveHint: false
    • openWorldHint: false
  • list_experimentsEvery experiment with status and, for running or finished ones, full Bayesian results — exposures, conversions, and the probability each variant is best.No findings

    Why it is in this group

    • The name "list_experiments" says "list": a word for reading.
    Description, as the server wrote it
    Every experiment with status and, for running or finished ones, full Bayesian results — exposures, conversions, and the probability each variant is best.

    Annotations the server declares

    • readOnlyHint: true
    • title: List experiments
    • destructiveHint: false
    • openWorldHint: false
  • list_inbound_filtersThis app's inbound filters: rules that drop a matching error at ingest, counted but never stored or alerted on.No findings

    Why it is in this group

    • The name "list_inbound_filters" says "list": a word for reading.
    Description, as the server wrote it
    This app's inbound filters: rules that drop a matching error at ingest, counted but never stored or alerted on. exc_type and release match exactly, message is a glob (* = anything, any case), environment is exact and `simulator` also drops simulator events. discarded_7d counts drops per reason.

    Annotations the server declares

    • readOnlyHint: true
    • title: List inbound filters
    • destructiveHint: false
    • openWorldHint: false
  • list_monitorsEvery performance monitor: what it watches (metric, ops, route), its threshold and window, and its state (ok, firing, no_data) with the last value read.No findings

    Why it is in this group

    • The name "list_monitors" says "list": a word for reading.
    Description, as the server wrote it
    Every performance monitor: what it watches (metric, ops, route), its threshold and window, and its state (ok, firing, no_data) with the last value read. A firing monitor has an open issue: issue_id opens with get_error_issue.

    Annotations the server declares

    • readOnlyHint: true
    • title: List performance monitors
    • destructiveHint: false
    • openWorldHint: false
  • list_releasesReleases from the app and the backend, newest first.No findings

    Why it is in this group

    • The name "list_releases" says "list": a word for reading.
    Description, as the server wrote it
    Releases from the app and the backend, newest first. App rows have crash-free sessions and users and adoption; backend rows have crash-free and error-free requests. Each row states its source. Use it to tell whether a release made things worse.

    Annotations the server declares

    • readOnlyHint: true
    • title: List releases and their health
    • destructiveHint: false
    • openWorldHint: false
  • list_store_productsThis app's auto-renewable subscriptions in App Store Connect: product id, billing period and Apple review state.Reads text others writeNo findings

    Why it is in this group

    • The name "list_store_products" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    This app's auto-renewable subscriptions in App Store Connect: product id, billing period and Apple review state. Use it to check that a paywall references a product that actually exists. Pass subscription_id to also fetch Apple's price ladder for that one product (Apple scopes price points per subscription, so there is no global list).

    Annotations the server declares

    • readOnlyHint: true
    • title: List App Store subscription products
    • destructiveHint: false
    • openWorldHint: false
  • list_surfacesEvery paywall and onboarding flow, what is actually being served at each placement (running experiment > live > none), and the valid placement names.No findings

    Why it is in this group

    • The name "list_surfaces" says "list": a word for reading.
    Description, as the server wrote it
    Every paywall and onboarding flow, what is actually being served at each placement (running experiment > live > none), and the valid placement names. IMPORTANT: read `placements` before writing a placement string into code. The list is configured ∪ observed, so a name that appears only under `observed` is usually a typo in the app — and a placement that does not exist renders nothing at all, with no error.

    Annotations the server declares

    • readOnlyHint: true
    • title: List paywalls, onboarding flows and placements
    • destructiveHint: false
    • openWorldHint: false
  • list_templatesThe one-click starter templates available for paywalls or onboarding flows, with the template key and what each looks like.No findings

    Why it is in this group

    • The name "list_templates" says "list": a word for reading.
    Description, as the server wrote it
    The one-click starter templates available for paywalls or onboarding flows, with the template key and what each looks like. Use this when asked to add a paywall so you pick a real template key rather than inventing one.

    Annotations the server declares

    • readOnlyHint: true
    • title: List built-in paywall and onboarding templates
    • destructiveHint: false
    • openWorldHint: false
  • list_usersThe app's users, most recently active first — each with an identity label, event count, last seen, and derived churn state (in_trial, converted, cancelled, expired, billing_issue, …Reads text others writeNo findings

    Why it is in this group

    • The name "list_users" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.
    Description, as the server wrote it
    The app's users, most recently active first — each with an identity label, event count, last seen, and derived churn state (in_trial, converted, cancelled, expired, billing_issue, grace_period, paused, refunded, none). Capped so a large app does not flood the context; `total` reports how many matched before the cap.

    Annotations the server declares

    • readOnlyHint: true
    • title: List users
    • destructiveHint: false
    • openWorldHint: false
  • read_docThe complete markdown of one documentation page.Reads private dataNo findings

    Why it is in this group

    • The name "read_doc" says "read": a word for reading.

    What it can reach

    • private-dataThe name "read_doc" says "read" and "doc": it reads documents.
    Description, as the server wrote it
    The complete markdown of one documentation page. Accepts a site-relative path such as '/implementation/welcome/sdk-quickstart' (a full docs.fictura.co URL works too). If the path is wrong, the closest real paths come back as suggestions. No API key required.

    Annotations the server declares

    • readOnlyHint: true
    • title: Read a Fictura documentation page
    • destructiveHint: false
    • openWorldHint: false
  • search_docsFull-text search across the Fictura docs, grouped by page.Reads private dataNo findings

    Why it is in this group

    • The name "search_docs" says "search": a word for reading.

    What it can reach

    • private-dataThe name "search_docs" says "search" and "doc": it reads documents.
    • private-dataThe description's first sentence says "doc": it reads documents.
    Description, as the server wrote it
    Full-text search across the Fictura docs, grouped by page. Use this before answering any 'how do I…' question about the SDK, API, paywalls, entitlements, links or webhooks — the docs are the source of truth and are regenerated on every code change. Returns page paths; pass one to read_doc for the full text. No API key required.

    Annotations the server declares

    • readOnlyHint: true
    • title: Search Fictura documentation
    • destructiveHint: false
    • openWorldHint: false
  • search_error_eventsSingle occurrences across issues, newest first, or counts with group_by.Reads text others writeNo findings

    Why it is in this group

    • The name "search_error_events" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.
    Description, as the server wrote it
    Single occurrences across issues, newest first, or counts with group_by. Use it to answer which release or route an error hits, whether a person hit it, or what failed in one trace. Open one with get_error_event.

    Annotations the server declares

    • readOnlyHint: true
    • title: Search error events
    • destructiveHint: false
    • openWorldHint: false
  • search_error_issuesFind an issue by text in its title or culprit, across every issue the app has.Reads text others writeNo findings

    Why it is in this group

    • The name "search_error_issues" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe name "search_error_issues" says "search" and "issue": it reads issues, which other people can write.
    • untrusted-inputThe description's first sentence says "find" and "issue": it reads issues, which other people can write.
    Description, as the server wrote it
    Find an issue by text in its title or culprit, across every issue the app has. Use it when you know the error message, exception type or function. Same filters and rows as list_error_issues.

    Annotations the server declares

    • readOnlyHint: true
    • title: Search error issues
    • destructiveHint: false
    • openWorldHint: false
  • search_logsApplication log lines from the backend SDK, newest first, or counts with group_by.No findings

    Why it is in this group

    • The name "search_logs" says "search": a word for reading.
    Description, as the server wrote it
    Application log lines from the backend SDK, newest first, or counts with group_by. Use it to see what happened around an error: pass trace_id for one request's lines, or q and level to search. Lines are kept 14 days, and the default range is the last 24 hours.

    Annotations the server declares

    • readOnlyHint: true
    • title: Search log lines
    • destructiveHint: false
    • openWorldHint: false
  • search_tracesWith no filters: every route and screen with its count, error rate, p50, p95 and slowest dependency.No findings

    Why it is in this group

    • The name "search_traces" says "search": a word for reading.
    Description, as the server wrote it
    With no filters: every route and screen with its count, error rate, p50, p95 and slowest dependency. With any filter: matching spans from the backend and the app, or count, avg, p50, p95 and errors with group_by. Use it to find what is slow or failing, then open one with get_trace. Spans are kept 30 days.

    Annotations the server declares

    • readOnlyHint: true
    • title: Search spans and slow routes
    • destructiveHint: false
    • openWorldHint: false

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.

627 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 3 outbound tools breaks every one.

Can send data out3
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__fictura__set_uptime_monitor",
      "mcp__fictura__update_error_issue",
      "mcp__fictura__update_error_issues"
    ]
  }
}

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, 18:23 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
31
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.fictura.co/.well-known/oauth-protected-resource/mcp
Authorization servers
https://dxdgawdmjnuwvbjdwelb.supabase.co/auth/v1
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 31 tools that change things (7 destructive, 24 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.fictura.co/mcp: tools/list returned 88 tools to an anonymous client, including update_app_identity (destructive), stop_experiment (destructive), create_inbound_filter (destructive), delete_inbound_filter (destructive), save_paywall_doc (destructive) and 26 more

    What this check looks for

Posture changes

  1. Nov 13, 2026
    • Tools that change things, listed without credentials: 15 to 31
  2. Nov 6, 2026
    • Tools that change things, listed without credentials: 13 to 15

Findings

Matches of fixed checks, with the text they matched.

5 warn2 info
  • The server marks "get_store_analytics" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "get_store_analytics" says "get": a word for reading.

    What this check looks for
  • The server marks "list_error_issues" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "list_error_issues" says "list": a word for reading.

    What this check looks for
  • The server marks "create_inbound_filter" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "create_inbound_filter" says "create": a word for a change.

    What this check looks for
  • The server marks "validate_paywall_doc" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "validate_paywall_doc" says "validate": a word for reading.

    What this check looks for
  • The server marks "validate_onboarding_doc" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "validate_onboarding_doc" says "validate": a word for reading.

    What this check looks for
  • The title mentions "credentials".

    Matched text

    title: "Get this app's Fictura credentials and endpoints"

    What this check looks for
Show 1 more finding

History

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

  1. PostureRemote posture changed. Tools that change things, listed without credentials: 15 -> 31.View diff
    • Tools that change things, listed without credentials: 15 to 31
  2. Tools31 added, 44 changed.+31 added~44 changedView diff
  3. PostureRemote posture changed. Tools that change things, listed without credentials: 13 -> 15.View diff
    • Tools that change things, listed without credentials: 13 to 15

Install

Pinned to version 0.1.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http fictura https://mcp.fictura.co/mcp
claude mcp add --transport http fictura https://mcp.fictura.co/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__fictura__search_docs",
      "mcp__fictura__list_docs",
      "mcp__fictura__read_doc",
      "mcp__fictura__get_app_setup",
      "mcp__fictura__get_setup_step",
      "mcp__fictura__get_setup_status",
      "mcp__fictura__get_analytics",
      "mcp__fictura__get_attribution_report",
      "mcp__fictura__list_users",
      "mcp__fictura__get_user",
      "mcp__fictura__get_tracking_plan",
      "mcp__fictura__list_surfaces",
      "mcp__fictura__get_surface",
      "mcp__fictura__list_templates",
      "mcp__fictura__list_experiments",
      "mcp__fictura__get_experiment",
      "mcp__fictura__get_acquisition_report",
      "mcp__fictura__list_campaigns",
      "mcp__fictura__list_creators",
      "mcp__fictura__get_link_infrastructure",
      "mcp__fictura__get_push_config",
      "mcp__fictura__list_store_products",
      "mcp__fictura__search_error_issues",
      "mcp__fictura__search_error_events",
      "mcp__fictura__get_error_event",
      "mcp__fictura__get_error_issue",
      "mcp__fictura__get_error_issue_brief",
      "mcp__fictura__get_issue_tag_values",
      "mcp__fictura__get_issue_activity",
      "mcp__fictura__search_logs",
      "mcp__fictura__search_traces",
      "mcp__fictura__get_trace",
      "mcp__fictura__list_error_alerts",
      "mcp__fictura__list_alert_rules",
      "mcp__fictura__list_releases",
      "mcp__fictura__list_inbound_filters",
      "mcp__fictura__get_uptime_monitor",
      "mcp__fictura__get_error_settings",
      "mcp__fictura__get_performance_overview",
      "mcp__fictura__get_endpoint_summary",
      "mcp__fictura__list_dependencies",
      "mcp__fictura__get_span",
      "mcp__fictura__get_ai_usage",
      "mcp__fictura__get_jobs",
      "mcp__fictura__compare_releases",
      "mcp__fictura__get_web_vitals",
      "mcp__fictura__get_mobile_vitals",
      "mcp__fictura__list_monitors",
      "mcp__fictura__get_tracing_health",
      "mcp__fictura__get_paywall_doc",
      "mcp__fictura__editor_get_doc",
      "mcp__fictura__get_onboarding_doc",
      "mcp__fictura__get_appsflyer_import_status",
      "mcp__fictura__get_appsflyer_attribution_summary"
    ],
    "ask": [
      "mcp__fictura__create_tracking_link",
      "mcp__fictura__check_entitlement",
      "mcp__fictura__get_store_analytics",
      "mcp__fictura__list_error_issues",
      "mcp__fictura__update_error_issue",
      "mcp__fictura__update_error_issues",
      "mcp__fictura__set_uptime_monitor",
      "mcp__fictura__update_tracing_settings",
      "mcp__fictura__validate_paywall_doc",
      "mcp__fictura__create_paywall_draft",
      "mcp__fictura__pair_editor",
      "mcp__fictura__unpair_editor",
      "mcp__fictura__validate_onboarding_doc",
      "mcp__fictura__create_onboarding_draft",
      "mcp__fictura__start_appsflyer_import"
    ],
    "deny": [
      "mcp__fictura__update_app_identity",
      "mcp__fictura__create_inbound_filter",
      "mcp__fictura__delete_inbound_filter",
      "mcp__fictura__save_paywall_doc",
      "mcp__fictura__editor_set_doc",
      "mcp__fictura__save_onboarding_doc"
    ]
  }
}

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 fictura. Review it before you use it.

Capability tags behind 29 rules
  • mcp__fictura__search_docs private-data
  • mcp__fictura__list_docs private-data
  • mcp__fictura__read_doc private-data
  • mcp__fictura__get_app_setup untrusted-input
  • mcp__fictura__get_setup_step private-data
  • mcp__fictura__list_users untrusted-input
  • mcp__fictura__get_store_analytics untrusted-input
  • mcp__fictura__list_store_products untrusted-input
  • mcp__fictura__list_error_issues untrusted-input
  • mcp__fictura__search_error_issues untrusted-input
  • mcp__fictura__search_error_events untrusted-input
  • mcp__fictura__get_error_issue untrusted-input
  • mcp__fictura__get_error_issue_brief untrusted-input
  • mcp__fictura__get_issue_tag_values untrusted-input
  • mcp__fictura__get_issue_activity private-data, untrusted-input
  • mcp__fictura__get_trace untrusted-input
  • mcp__fictura__list_error_alerts untrusted-input
  • mcp__fictura__update_error_issue outbound
  • mcp__fictura__update_error_issues outbound
  • mcp__fictura__get_uptime_monitor untrusted-input
  • mcp__fictura__set_uptime_monitor outbound
  • mcp__fictura__get_performance_overview private-data, untrusted-input
  • mcp__fictura__get_endpoint_summary private-data, untrusted-input
  • mcp__fictura__list_dependencies private-data, untrusted-input
  • mcp__fictura__get_web_vitals untrusted-input
  • mcp__fictura__get_paywall_doc private-data
  • mcp__fictura__editor_get_doc private-data
  • mcp__fictura__get_onboarding_doc private-data
  • mcp__fictura__start_appsflyer_import 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/co.fictura/mcp/verify?hash=7895b1759b88dbfffaa999848fce8f7863399cc0122c8a15ff7c8f0df66451c4" | jq -e '.changed == false'

Pinned hash 7895b1759b88, from Nov 11, 2026, 05:18 UTC.

Watch

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

https://radar.anlyon.com/servers/co.fictura/mcp/changes.xml

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

Badge

Anlyon Radar badge for co.fictura/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/co.fictura/mcp.svg)](https://radar.anlyon.com/servers/co.fictura/mcp)

Source: MCP Registry · repository. Synced Oct 29, 2026, 18:24 UTC.

Fictura MCP server: questions and answers

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

Is the Fictura MCP server safe?

No scan can promise that. What its definitions show: 75 tools, 21 of which can change, send or delete something, and 7 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 Fictura MCP server delete data?

Yes. 6 tools can delete, cancel or revoke something: update_app_identity, create_inbound_filter, delete_inbound_filter, save_paywall_doc, editor_set_doc and save_onboarding_doc.

Can the Fictura 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 Fictura MCP server have?

75 tools: 6 destructive, 15 write, 54 read. update_app_identity, create_inbound_filter, delete_inbound_filter, save_paywall_doc, editor_set_doc, save_onboarding_doc, create_tracking_link, check_entitlement and 67 more.

Does the Fictura MCP server need sign-in or OAuth?

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

Does the Fictura MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): update_error_issue, update_error_issues and set_uptime_monitor.

Has the Fictura MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.