archive_thought

THE RISK

Medium Risk

Why archive_thought needs a policy

This tool modifies data by moving/relocating files to an archive location. While archival is typically reversible (the file still exists and could theoretically be restored), it removes data from active project view and affects project state. It's Write rather than Destructive because the data is not permanently deleted or overwritten.

From the tool's definition The tool archives a processed thought file by moving it to .project/thoughts/todos/.archive/, which is a reversible file operation.

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

POLICY

How to control archive_thought

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 archive_thought:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "archive_thought": {
      "limits": [
        {
          "counter": "archive_thought_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

archive_thought stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. 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.

LIMIT 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 →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about archive_thought

What does the archive_thought tool do? +

Archives a processed thought file by moving it to .project/thoughts/todos/.archive/. Use this after you. It is categorised as a Write tool in the Project MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on archive_thought? +

Register the Project MCP server in PolicyLayer and add a rule for archive_thought: 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 archive_thought? +

archive_thought is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit archive_thought? +

Yes. Add a rate_limit block to the archive_thought 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 archive_thought completely? +

Set action: deny in the PolicyLayer policy for archive_thought. 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 archive_thought? +

archive_thought 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 →