Skip to content

DreamAgent MCP server

io.github.nivethaug/dreamagentnivethaugstreamable-httpv1.0.0Scanned

Build and deploy websites, Telegram and Discord bots from chat via the DreamAgent platform.

24 tools: 7 can delete or cancel things, 4 change things and 13 only read.

Tools: 7 delete, 0 irreversible, 4 write, 13 read.

Tools listed without sign-in. Remote posture

With Anlyon

7 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 DreamAgent MCP server can do

The DreamAgent MCP server is published by the GitHub account nivethaug. It has 24 tools. It can delete or cancel things (7 tools: dreamagent_edit_file, dreamagent_write_file, dreamagent_delete_file, dreamagent_build_publish and 3 more) and create or change data (4 tools: dreamagent_commit_push, dreamagent_create_project, dreamagent_create_session and dreamagent_release_project_lock). 13 tools only read.

7 tools read private data (dreamagent_list_global_integrations, dreamagent_list_files, dreamagent_read_file and 4 more); 3 tools bring in text other people can write (dreamagent_list_sessions, dreamagent_get_chat_status and dreamagent_screenshot_website); 2 tools can send data out of your system (dreamagent_build_publish and dreamagent_screenshot_website). 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 12 findings, 4 of them high severity (credentials-mention, sensitive-path and long-description). 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 1.0.0.

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.

24 tools

Deletes or cancels 7Claude Code: deny
  • dreamagent_build_publishWRITE ACTION — build & publish a DreamAgent project: rebuilds the app from the current source files and pushes the new version live.Can send data outNo findings

    Why it is in this group

    • The name "dreamagent_build_publish" says "publish": a word for a change that another call does not undo.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • outboundThe name "dreamagent_build_publish" says "publish": it sends or publishes something to other people.
    Description, as the server wrote it
    WRITE ACTION — build & publish a DreamAgent project: rebuilds the app from the current source files and pushes the new version live. Use after finishing file edits (dreamagent_write_file) so the user's changes go live. Requires a paid plan. ASYNCHRONOUS: kick-off returns immediately; check dreamagent_get_project_status until the project reports 'ready'. confirm must be true to execute.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
  • dreamagent_cancel_chatDESTRUCTIVE — stops an AI edit that is currently running.No findings

    Why it is in this group

    • The name "dreamagent_cancel_chat" says "cancel": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    DESTRUCTIVE — stops an AI edit that is currently running. Use ONLY when the user explicitly asks to stop/cancel the active edit. After cancellation, do NOT claim the requested change was completed — report that it was stopped. Returns 'Cancellation requested: <backend message>' — e.g. 'Query cancelled', 'Cancellation requested' (durable run), or 'No active query found'. Afterwards poll dreamagent_get_chat_status / dreamagent_get_edit_progress until run_status reports 'cancelled'.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
  • dreamagent_chatWRITE ACTION — builds, modifies, or fixes an EXISTING project with a natural-language instruction.No findings

    Why it is in this group

    • The description's first verb is "write": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    WRITE ACTION — builds, modifies, or fixes an EXISTING project with a natural-language instruction. Use ONLY when the user clearly asks for a change ("add X", "fix Y", "change the theme"). If the user is only asking for advice, analysis, review, or suggestions ("what could be improved?", "review my bot"), do NOT call this — answer from the project's info instead; a review request is not an edit. Describe ONLY the desired change — DreamAgent's AI automatically handles code, tests, rebuild, and redeployment. Completed changes are saved and committed automatically. ASYNCHRONOUS: returns immediately with the session_key; monitor with dreamagent_get_edit_progress (or dreamagent_get_chat_status with the returned session key) until a terminal state. A run has succeeded only once run_status reaches 'completed'. Each edit consumes AI usage from the account's plan. ERRORS: failures are returned as tool errors. If the edit was rejected before starting, the message says 'the edit was NOT started' plus the reason — HTTP 402 insufficient usage allowance, 409 another edit already active, 423 session lock held by another session, 404 wrong project id, 401 no account connected. ONE EDIT AT A TIME: the API rejects a second concurrent edit on the same project (409); check progress and wait for the current edit. SUPERPOWERS: projects can use the account's enabled add-on AI tools. To add or use one, name the feature in the message — DreamAgent's agent knows the enabled tools and wires the integration, UI and job handling automatically. Check the catalog with dreamagent_list_superpowers; disabled tools are enabled at dreamagent.cloud → Superpowers.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
  • dreamagent_delete_fileWRITE ACTION — delete one source file from a DreamAgent project.2 findings

    Why it is in this group

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

    Findings

    • High

      The description refers to ".env".

      Matched text

      description: "...Agent project. Hidden/credential files (.env, .git, keys) are rejected. By default t..."

      What this check looks for
    • Info

      The description mentions "credential".

      Matched text

      description: "...file from a DreamAgent project. Hidden/credential files (.env, .git, keys) are rejected...."

      What this check looks for
    Description, as the server wrote it
    WRITE ACTION — delete one source file from a DreamAgent project. Hidden/credential files (.env, .git, keys) are rejected. By default the deletion is immediately committed and pushed (so it is recorded in session history & version history) — deleted files stay recoverable via git history / version restore. confirm must be true to execute.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
  • dreamagent_design_modeWRITE ACTION — redesign a website project's UI to match a design image.No findings

    Why it is in this group

    • The description's first verb is "write": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    WRITE ACTION — redesign a website project's UI to match a design image. Website projects only. The image (screenshot, mockup, or generated design) is the design spec; DreamAgent's AI reads it and redesigns the project's frontend to match it. confirm must be true to execute.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
  • dreamagent_edit_fileWRITE ACTION — make SMALL targeted changes to an EXISTING file in a DreamAgent project via exact search/replace.No findings

    Why it is in this group

    • The name "dreamagent_edit_file" says "edit": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    WRITE ACTION — make SMALL targeted changes to an EXISTING file in a DreamAgent project via exact search/replace. PREFERRED over dreamagent_write_file for editing existing files: you send only the changed fragments (never the whole file) — cheaper, immune to payload size/safety blocks in the calling client, and cannot corrupt unchanged code. Use dreamagent_write_file only to CREATE files or for full rewrites. Read the file first (dreamagent_read_file) and copy each 'find' text EXACTLY as it appears — whitespace and indentation must match. All edits are validated BEFORE anything is saved; if any 'find' fails to match, the file is left untouched and the error tells you which edit and why.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
  • dreamagent_write_fileWRITE ACTION — overwrite or create one source file in a DreamAgent project with the exact content given.2 findings

    Why it is in this group

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

    Findings

    • High

      The description refers to ".env".

      Matched text

      description: "...e the project, hidden/credential files (.env, .git, keys) are rejected, content is s..."

      What this check looks for
    • Info

      The description mentions "credential".

      Matched text

      description: "...: path stays inside the project, hidden/credential files (.env, .git, keys) are rejected,..."

      What this check looks for
    Description, as the server wrote it
    WRITE ACTION — overwrite or create one source file in a DreamAgent project with the exact content given. For CHANGING an existing file, prefer dreamagent_edit_file (small targeted find→replace edits — no need to send the whole file). By default the write is immediately committed and pushed to the project's GitHub repo and recorded in its session history & version history (so the user can restore/revert). Changes go live after the project is rebuilt (dreamagent_build_publish). MULTI-FILE EDITS: pass auto_commit=false on each write, then call dreamagent_commit_push once at the end — one commit and one history entry for the whole batch. GUARDS (enforced server-side, the same as the in-app code editor): path stays inside the project, hidden/credential files (.env, .git, keys) are rejected, content is scanned for malware/shell signatures and blocked, 2MB size cap. Failed scans return the reason. The user can undo damage by editing in the DreamAgent editor or restoring a previous version from version history — still, prefer precise minimal diffs.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
Changes things 4Claude Code: ask
  • dreamagent_commit_pushWRITE ACTION — commit ALL pending changes in a DreamAgent project and push them to its private GitHub repo.No findings

    Why it is in this group

    • The name "dreamagent_commit_push" says "commit": a word for a change.
    Description, as the server wrote it
    WRITE ACTION — commit ALL pending changes in a DreamAgent project and push them to its private GitHub repo. The commit gets its own entry in the project's session history and version history, so the user can restore/revert to it in the DreamAgent dashboard. Use it to (a) commit several MCP writes/deletes as ONE version — write and delete with auto_commit=false first — or (b) retry a commit after a failure. Chat-driven edits commit automatically; this tool is for direct file changes made through MCP.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_create_projectWRITE ACTION — creates a new DreamAgent project (website, Telegram bot, Discord bot, or AI agent).3 findings

    Why it is in this group

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

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...execute. When several telegram/discord credentials are saved, the one to use is selected v..."

      What this check looks for
    • Info

      The input schema at properties.bot_token_integration_id.description mentions "credential".

      Matched text

      inputSchema.properties.bot_token_integration_id.description: "...ED for telegrambot & discordbot — saved-credential ID (see dreamagent_list_global_integrat..."

      What this check looks for
    • Info

      The description is 3,787 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...omatically at build time. Check what is enabled with dreamagent_list_superpowers."

      What this check looks for
    Description, as the server wrote it
    WRITE ACTION — creates a new DreamAgent project (website, Telegram bot, Discord bot, or AI agent). confirm must be true to execute. When several telegram/discord credentials are saved, the one to use is selected via bot_token_integration_id (see dreamagent_list_global_integrations). CREATION IS ASYNCHRONOUS: after calling, check dreamagent_get_project_status repeatedly until the project is 'ready' or 'failed' (bots ~2-5 min, websites longer). CREDENTIALS: raw bot tokens are never accepted in chat or as inputs. For Telegram/Discord bots you MUST pass bot_token_integration_id — the ID of a saved credential from dreamagent_list_global_integrations. If none is saved, direct the user to dreamagent.cloud → Settings → Global Integrations. Other saved keys can be imported via global_integration_ids. Credentials are stored as project secrets and are never exposed back. DESCRIPTION = the refined creation brief describing WHAT should be built (see the structure notes below). THREE.JS / WEBGL SIGNAL: if the site genuinely needs real 3D/WebGL (3D scenes, games, product configurators, 3D visualization), the description MUST contain the exact word "three.js" (e.g. "Includes interactive 3D scenes built with three.js") — the platform installs the 3D stack based on that word. Include it ONLY when genuinely needed; regular websites must never include it. When included, also mention the 3D usage in one clause of the description. Create a concise but complete description of WHAT should be built: - product vision and target audience - user experience and core functionality - design/tone direction - important features and behavior - final expected result Do not include implementation details such as: - technology stack - architecture - database/API implementation - authentication implementation - deployment - CI/CD - testing commands Infer reasonable defaults when missing details are non-critical. Ask for clarification only when missing information materially affects the requested functionality, scope, credentials, or expected result. Prefer the following structure and constraints for each project type, but do not override explicit user requirements: Website: - Project Vision - Design Style - Pages - Hero Experience - Core Features - UI Components - Mobile Experience - Final Expectation - Prefer up to 4 pages unless the user clearly requires more. Telegram bot: - Bot Purpose - Commands - User Flow - Optional AI Features - Integrations when required - Final Expectations - Prefer a compact command set; always include /start and /help unless the user's explicit requirements conflict. Discord bot: - Bot Purpose - Slash Commands - Events - Permissions - Optional AI Features - Final Expectations - Prefer a compact command set; include /help where appropriate. Agent (recurring/scheduled automation with OAuth actions): - Purpose (what it monitors or automates) - Data Sources (which connected OAuth services: YouTube, GitHub, Discord, Notion, X, Google Sheets, Slack — or public APIs) - Schedule (e.g., every 5 minutes / hourly / daily at 9am) and/or Event Triggers (incoming webhook) - Conditions (when to act — thresholds, keywords, state changes) - Delivery Channels (Telegram, Discord, Slack, email — optional) - Final Expectation - Use concrete schedules; note that agents keep persistent state between runs and can call any connected OAuth integration. - Agents do NOT need a bot token unless they deliver via Telegram/ Discord (then a saved credential is required as for bots). SUPERPOWERS: the account may have add-on AI tools enabled. If the requested product uses one, reflect the FEATURE in the description — DreamAgent wires the tool integration automatically at build time. Check what is enabled with dreamagent_list_superpowers.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_create_sessionCreate a new development session for a project — a separate conversation with its own context.No findings

    Why it is in this group

    • The name "dreamagent_create_session" says "create": a word for a change.
    Description, as the server wrote it
    Create a new development session for a project — a separate conversation with its own context. Use when the user wants to start a distinct development topic. A new session does NOT replace or affect the existing project — earlier sessions remain available.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_release_project_lockRECOVERY-ONLY — releases a project's editing lock when a stale or abandoned session blocks new modifications.No findings

    Why it is in this group

    • The name "dreamagent_release_project_lock" says "lock": a word for a change.
    Description, as the server wrote it
    RECOVERY-ONLY — releases a project's editing lock when a stale or abandoned session blocks new modifications. NOT a normal editing step, and NEVER a way to bypass an actively running edit. The lock state is not machine-readable from here: to judge staleness, check dreamagent_get_edit_progress — if no edit is active but dreamagent_chat still fails with a lock error, the lock is stale. Confirm with the user before releasing if they may have the project open elsewhere.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
Only reads 13Show 13 read-only tools
  • dreamagent_get_chat_statusCheck the progress and final status of a specific AI development session using its session key.Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe name "dreamagent_get_chat_status" says "get" and "chat": it reads messages.
    • untrusted-inputThe name "dreamagent_get_chat_status" says "get" and "chat": it reads messages, which other people can write.
    Description, as the server wrote it
    Check the progress and final status of a specific AI development session using its session key. Use this to monitor an asynchronous edit until it completes, fails, or is cancelled — keep checking until a terminal state. The session key comes from dreamagent_chat or dreamagent_list_sessions and is an identifier, not a secret. Returns (actual fields): 'active=', 'run_status=', 'next_after=' (cursor for the next check), optional 'new_output:' (text produced since the last check), then either "Still working — poll again" or a terminal 'done=true' line: finished (with the final output tail), 'the edit was NOT started: <reason>' (rejected early, e.g. HTTP 402 insufficient credits), or 'stream error' (the connection to the run broke — the server-side run may still have finished; verify with dreamagent_get_edit_progress). run_status values: queued | running | cancel_requested | completed | failed | cancelled | interrupted | unknown.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_get_edit_progressCheck the latest AI edit progress for a project using its project identifier — no session key needed: the project id retrieves the session holding the latest edit.No findings

    Why it is in this group

    • The name "dreamagent_get_edit_progress" says "get": a word for reading.
    Description, as the server wrote it
    Check the latest AI edit progress for a project using its project identifier — no session key needed: the project id retrieves the session holding the latest edit. Use when the user asks whether their edit is finished, when the session key isn't available (e.g. a new conversation), and BEFORE starting any new edit. Returns (actual fields): 'session_key=' (the identifier of the session this progress comes from), 'edit_active=', 'run_status=', 'chunks=' (output size so far), optional 'recent_output (tail):', and a terminal 'result:' line: finished (with the final output tail), 'the edit was NOT started: <reason>' (rejected early, e.g. HTTP 402 insufficient credits), 'stream error', or 'no run is currently active'. run_status values: queued | running | cancel_requested | completed | failed | cancelled | interrupted | unknown. Distinct from dreamagent_get_project_status: project status = creation/deployment state (creating/ready/failed); edit progress = current AI modification state; chat status (dreamagent_get_chat_status) monitors one specific session by its session key. If edit_active is true, do NOT launch another edit for the same project.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_get_file_diffGit diff of one project file against the last commit — shows the pending (not yet live) changes.Reads private dataNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe name "dreamagent_get_file_diff" says "get" and "file": it reads files.
    • private-dataThe description's first sentence says "file": it reads files.
    • private-dataThe input names a file (input.file_path), and the tool reads: it reads files.
    Description, as the server wrote it
    Git diff of one project file against the last commit — shows the pending (not yet live) changes. Free, read-only. Use after edits to review exactly what changed before rebuilding.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_get_project_statusCheck a project's creation/deployment state.No findings

    Why it is in this group

    • The name "dreamagent_get_project_status" says "get": a word for reading.
    Description, as the server wrote it
    Check a project's creation/deployment state. Terminal states are 'ready' (built and live) and 'failed'; while a project is being created it reports progressive phases such as 'creating', 'building', 'deploying', or 'ai_provisioning' — treat any non-terminal status as still building. Use after dreamagent_create_project (poll until ready or failed) and whenever the user asks whether a project is ready or live. NOTE: this reports the PROJECT's build/deploy state — NOT AI edit progress. For edits use dreamagent_get_edit_progress.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_list_commitsVersion history of a DreamAgent project — recent commits (hash, message, status, timestamp) from its persistent commit log, newest first.Reads private dataNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe name "dreamagent_list_commits" says "list" and "commit": it reads repositories.
    • private-dataThe description's first sentence says "commit": it reads repositories.
    Description, as the server wrote it
    Version history of a DreamAgent project — recent commits (hash, message, status, timestamp) from its persistent commit log, newest first. Use it to review what changed and when; the user can restore any version from the DreamAgent dashboard version-history UI (mention the short hash so they can find it).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_list_filesList the file tree of a DreamAgent project (source files only — hidden files like .env are excluded).Reads private data1 finding

    Why it is in this group

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

    What it can reach

    • private-dataThe name "dreamagent_list_files" says "list" and "file": it reads files.
    • private-dataThe description's first sentence says "list" and "file": it reads files.

    Findings

    • High

      The description refers to ".env".

      Matched text

      description: "...(source files only — hidden files like .env are excluded). Use before reading or ed..."

      What this check looks for
    Description, as the server wrote it
    List the file tree of a DreamAgent project (source files only — hidden files like .env are excluded). Use before reading or editing a file to find the correct path.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_list_global_integrationsList the user's saved credentials (Global Integrations).Reads private data1 finding

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "list" and "credential": it reads secrets.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "List the user's saved credentials (Global Integrations). Saved credentia..."

      What this check looks for
    Description, as the server wrote it
    List the user's saved credentials (Global Integrations). Saved credentials are referenced by ID when creating projects: bot_token_integration_id for bot tokens, global_integration_ids for other keys. Secret values are never returned — only IDs and metadata (type, key name, verified, title). New credentials are added at dreamagent.cloud → Settings → Global Integrations.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_list_project_envList a project's environment variables with their details.1 finding

    Why it is in this group

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

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...he user's Global Integrations — API-key credentials and connected OAuth services (dreamagen..."

      What this check looks for
    Description, as the server wrote it
    List a project's environment variables with their details. Shows each key's name, title, description, docs URL, and category — values are masked (secrets are never returned). Use to see which integrations a project already has before adding more, or to answer "what keys does my project have?". These are PROJECT-SPECIFIC variables — distinct from the user's Global Integrations — API-key credentials and connected OAuth services (dreamagent_list_global_integrations).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_list_projectsList the user's DreamAgent projects.No findings

    Why it is in this group

    • The name "dreamagent_list_projects" says "list": a word for reading.
    Description, as the server wrote it
    List the user's DreamAgent projects. Returns each project's name, ID, type, status, and live domain (when available). Project names resolve to IDs here.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_list_sessionsList a project's development sessions (conversation threads).Reads private dataReads text others write1 finding

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "list" and "conversation": it reads messages.
    • untrusted-inputThe description's first sentence says "list" and "conversation": it reads messages, which other people can write.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...a session; it is not an authentication credential or a secret."

      What this check looks for
    Description, as the server wrote it
    List a project's development sessions (conversation threads). Returns each session's identifier (session key) and context so you can select, continue, or monitor a specific development session — pass the session key to dreamagent_chat to continue that thread or to dreamagent_get_chat_status to monitor it. The session key is a reference used to address a session; it is not an authentication credential or a secret.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_list_superpowersList the account's add-on tools (Superpowers) with their enabled state.No findings

    Why it is in this group

    • The name "dreamagent_list_superpowers" says "list": a word for reading.
    Description, as the server wrote it
    List the account's add-on tools (Superpowers) with their enabled state. Read-only; no usage consumed. Tools shown as enabled can be used from the user's projects through dreamagent_chat by naming the feature in the message.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_read_fileRead a source file from a DreamAgent project.Reads private data1 finding

    Why it is in this group

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

    What it can reach

    • private-dataThe name "dreamagent_read_file" says "read" and "file": it reads files.
    • private-dataThe description's first sentence says "read" and "file": it reads files.
    • private-dataThe input names a file (input.file_path), and the tool reads: it reads files.

    Findings

    • High

      The description refers to ".env".

      Matched text

      description: "...x" or "telegram/main.py". Hidden files (.env) and binaries are not readable."

      What this check looks for
    Description, as the server wrote it
    Read a source file from a DreamAgent project. file_path is the project-relative path (from dreamagent_list_files), e.g. "src/pages/Home.tsx" or "telegram/main.py". Hidden files (.env) and binaries are not readable.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
  • dreamagent_screenshot_websiteWEBSITE PROJECTS ONLY — capture a screenshot of a DreamAgent-hosted page by URL: a deployed project's domain (e.g.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "dreamagent_screenshot_website" says "screenshot": a word for reading.

    What it can reach

    • untrusted-inputThe name "dreamagent_screenshot_website" says "screenshot" and "website": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "website": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    WEBSITE PROJECTS ONLY — capture a screenshot of a DreamAgent-hosted page by URL: a deployed project's domain (e.g. my-app.dreamagent.cloud or a connected custom domain) or dreamagent.cloud itself. Best for checking a project's live pages after edits or deploys and reviewing layouts — returns the PNG as an MCP image content block PLUS a public URL. Non-DreamAgent URLs are rejected (this is enforced both here and by the host firewall). No project id needed — just the URL. Only public http(s) pages; private/internal hosts are rejected.

    Annotations the server declares

    • readOnlyHint: true
    • 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.

42 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 text others write3
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
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__dreamagent__dreamagent_build_publish",
      "mcp__dreamagent__dreamagent_screenshot_website"
    ]
  }
}

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, 19:08 UTC, unchanged since Oct 22, 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
11
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.dreamagent.cloud/.well-known/oauth-protected-resource/mcp
Authorization servers
https://mcp.dreamagent.cloud
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 11 tools that change things (7 destructive, 4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.dreamagent.cloud/mcp: tools/list returned 24 tools to an anonymous client, including dreamagent_edit_file (destructive), dreamagent_write_file (destructive), dreamagent_delete_file (destructive), dreamagent_build_publish (destructive), dreamagent_design_mode (destructive) and 6 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

4 high8 info
Show 6 more findings

History

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

  1. Tools11 changed.~11 changedView diff
  2. Tools1 changed.~1 changedView diff

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http dreamagent https://mcp.dreamagent.cloud/mcp
claude mcp add --transport http dreamagent https://mcp.dreamagent.cloud/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__dreamagent__dreamagent_list_projects",
      "mcp__dreamagent__dreamagent_list_global_integrations",
      "mcp__dreamagent__dreamagent_list_project_env",
      "mcp__dreamagent__dreamagent_list_superpowers",
      "mcp__dreamagent__dreamagent_list_files",
      "mcp__dreamagent__dreamagent_read_file",
      "mcp__dreamagent__dreamagent_get_file_diff",
      "mcp__dreamagent__dreamagent_list_commits",
      "mcp__dreamagent__dreamagent_get_project_status",
      "mcp__dreamagent__dreamagent_list_sessions",
      "mcp__dreamagent__dreamagent_get_chat_status",
      "mcp__dreamagent__dreamagent_get_edit_progress"
    ],
    "ask": [
      "mcp__dreamagent__dreamagent_commit_push",
      "mcp__dreamagent__dreamagent_create_project",
      "mcp__dreamagent__dreamagent_create_session",
      "mcp__dreamagent__dreamagent_release_project_lock",
      "mcp__dreamagent__dreamagent_screenshot_website"
    ],
    "deny": [
      "mcp__dreamagent__dreamagent_edit_file",
      "mcp__dreamagent__dreamagent_write_file",
      "mcp__dreamagent__dreamagent_delete_file",
      "mcp__dreamagent__dreamagent_build_publish",
      "mcp__dreamagent__dreamagent_design_mode",
      "mcp__dreamagent__dreamagent_chat",
      "mcp__dreamagent__dreamagent_cancel_chat"
    ]
  }
}

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 dreamagent. Review it before you use it.

Capability tags behind 9 rules
  • mcp__dreamagent__dreamagent_list_global_integrations private-data
  • mcp__dreamagent__dreamagent_list_files private-data
  • mcp__dreamagent__dreamagent_read_file private-data
  • mcp__dreamagent__dreamagent_get_file_diff private-data
  • mcp__dreamagent__dreamagent_list_commits private-data
  • mcp__dreamagent__dreamagent_build_publish outbound
  • mcp__dreamagent__dreamagent_list_sessions private-data, untrusted-input
  • mcp__dreamagent__dreamagent_get_chat_status private-data, untrusted-input
  • mcp__dreamagent__dreamagent_screenshot_website untrusted-input, outbound

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/io.github.nivethaug/dreamagent/verify?hash=4d8ff5371d8c47b1416255e0e0e65f410bdcf7718d54e2d74da412bd6b71aecd" | jq -e '.changed == false'

Pinned hash 4d8ff5371d8c, from Nov 20, 2026, 05:17 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.nivethaug/dreamagent/changes.xml

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

Badge

Anlyon Radar badge for io.github.nivethaug/dreamagent
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.nivethaug/dreamagent.svg)](https://radar.anlyon.com/servers/io.github.nivethaug/dreamagent)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:42 UTC.

DreamAgent MCP server: questions and answers

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

Is the DreamAgent MCP server safe?

No scan can promise that. What its definitions show: 24 tools, 11 of which can change, send or delete something, and 12 findings (4 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the DreamAgent MCP server delete data?

Yes. 7 tools can delete, cancel or revoke something: dreamagent_edit_file, dreamagent_write_file, dreamagent_delete_file, dreamagent_build_publish, dreamagent_design_mode, dreamagent_chat and 1 more.

Can the DreamAgent 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 DreamAgent MCP server have?

24 tools: 7 destructive, 4 write, 13 read. dreamagent_edit_file, dreamagent_write_file, dreamagent_delete_file, dreamagent_build_publish, dreamagent_design_mode, dreamagent_chat, dreamagent_cancel_chat, dreamagent_commit_push and 16 more.

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

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

Does the DreamAgent 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): dreamagent_build_publish and dreamagent_screenshot_website.

Has the DreamAgent 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.