list_thoughts

THE RISK

Low Risk

Why list_thoughts needs a policy

This is a straightforward read operation that queries and enumerates existing thought files from a directory structure. It has no ability to create, modify, delete, or execute anything. The blast radius of misuse is negligible since an agent can only view metadata about thoughts, not expose sensitive content at scale or cause damage.

From the tool's definition Tool description explicitly states it 'Lists all thought files' and 'Shows available brain dump files' — pure data retrieval with no modification or side effects.

Documented attack patterns abuse exactly the kind of access list_thoughts gives an agent:

POLICY

How to control list_thoughts

PolicyLayer is an MCP gateway — it sits between your AI agents and Project MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for list_thoughts:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "list_thoughts": {}
  }
}

list_thoughts is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Project MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Project MCP tools

Destructive delete_task Permanently deletes a task from todos/. Use with caution - this cannot be undone. Consider Destructive remove_from_backlog Removes an item from BACKLOG.md without promoting it. Use for tasks that are no longer nee Execute lint_project_docs Validates project documentation against standards. Checks for required files, valid frontm Write init_project Initializes the .project/ directory with all standard files following strict templates. Cr Write sync_todo_index Syncs the parent TODO.md file with all tasks. Generates a dashboard view with tasks organi Write add_decision Adds a single architecture decision record (ADR) to DECISIONS.md. Creates a structured ent Write add_roadmap_milestone Adds a milestone or phase to ROADMAP.md. Creates a structured entry with title, descriptio Write add_to_backlog Adds a single item to BACKLOG.md. Use this for quick task creation without bulk import. It

All 42 Project MCP tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about list_thoughts

What does the list_thoughts tool do? +

Lists all thought files in the .project/thoughts/ directory structure. Shows available brain dump files organized by category. It is categorised as a Read tool in the Project MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list_thoughts? +

Register the Project MCP server in PolicyLayer and add a rule for list_thoughts: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Project MCP. Nothing to install.

What risk level is list_thoughts? +

list_thoughts is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit list_thoughts? +

Yes. Add a rate_limit block to the list_thoughts rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block list_thoughts completely? +

Set action: deny in the PolicyLayer policy for list_thoughts. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides list_thoughts? +

list_thoughts is provided by the Project MCP server (pouyanafisi/project-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Project MCP tool call.

Start from Project MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →