// SCAN REPORT

Tpm

18 tools. 7 can modify or destroy data without limits.

7 write tools that can modify data. Rate limits recommended.

Last updated: 29 Jun 2026

7 can modify or destroy data

11 read-only

18 tools total

Community server · catalogue entry verified 29/06/2026

How to control Tpm ↓

TOOL MAP

What Tpm exposes to your agents

Read (11) Write / Execute (7) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Tpm tools

Write · Low note_add This tool creates new note/comment records reversibly. Write · Low org_create This tool creates a new organizational entity in the local SQLite database. Write · Medium project_create This tool creates a new project record in the local SQLite database, which is a reversible Write operation. Write · Medium task_create This tool creates new task records, which is a reversible write operation.

7 of Tpm's 18 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Tpm

PolicyLayer is an MCP gateway — it sits between your AI agents and Tpm, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "note_add": {
    "limits": [
      {
        "counter": "note_add_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "info": {
    "limits": [
      {
        "counter": "info_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Tpm — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON TPM →

Instant setup, no code required.

FULL CATALOGUE

All 18 Tpm tools

WRITE 7 tools

Write note_add PROJECT MANAGEMENT (TPM): Add a note/comment to a ticket or task for context or decisions. Write org_create PROJECT MANAGEMENT: Create a new organization (rarely needed). Write project_create PROJECT MANAGEMENT: Create a new project under an organization. Write task_create task_create Write task_update PROJECT MANAGEMENT (TPM): Update a task Write ticket_create ticket_create Write ticket_update ticket_update

READ 11 tools

Read info Get information about the tracker MCP server: database location, stats, and usage. Read note_get PROJECT MANAGEMENT (TPM): Get full content of a specific note by ID. Read note_list PROJECT MANAGEMENT (TPM): List notes for an entity. Returns id, created_at, preview (first 100 chars). Use not Read org_list PROJECT MANAGEMENT: List all organizations. Usually only one org exists. Read project_list PROJECT MANAGEMENT: List projects in an organization. Read roadmap_view roadmap_view Read task_get task_get Read task_list PROJECT MANAGEMENT (TPM): List task IDs with status. Returns id, ticket_id, status only - use task_get for det Read ticket_get ticket_get Read ticket_list PROJECT MANAGEMENT: List ticket IDs with status/priority. Returns id, status, priority only - use ticket_get f Read ticket_search ticket_search

FAQ

Questions about Tpm

How do I prevent bulk modifications through Tpm? +

The Tpm server has 7 write tools including note_add, org_create, project_create. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Tpm.

How many tools does the Tpm MCP server expose? +

18 tools across 2 categories: Read, Write. 11 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Tpm? +

Register the Tpm MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Tpm tool call.

Deterministic rules across all 18 Tpm tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TPM →

Instant setup, no code required.

18 Tpm tools catalogued and risk-classified — across an index of 43,000+ MCP servers.