Trac

27 tools. 13 can modify or destroy data without limits.

4 destructive tools with no built-in limits. Policy required.

Last updated:

13 can modify or destroy data
14 read-only
27 tools total

Community server · catalogue entry verified 30/06/2026

How to control Trac ↓

What Trac exposes to your agents

Read (14) Write / Execute (9) Destructive / Financial (4)
Critical Risk

The most dangerous Trac tools

13 of Trac's 27 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Trac

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

Deny destructive operations
{
  "milestone_delete": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "milestone_create": {
    "limits": [
      {
        "counter": "milestone_create_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "get_server_time": {
    "limits": [
      {
        "counter": "get_server_time_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Trac — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON TRAC →

Instant setup, no code required.

All 27 Trac tools

READ 14 tools
Read get_server_time Get current Trac server time for temporal reasoning and coordination. Returns server timestamp in both ISO 860 Read milestone_get Get milestone details by name. Returns name, due date, completion date, and description. Requires TICKET_VIEW Read milestone_list List all milestone names. Returns array of milestone names (e.g., [ Read ping Test Trac MCP server connectivity and return API version Read ticket_actions Get valid workflow actions for a ticket Read ticket_changelog Get ticket change history. Use this to investigate who changed what and when. Set raw=true to get comment cont Read ticket_fields Get all ticket field definitions (standard + custom fields). Returns field metadata including name, type, labe Read ticket_get Get full ticket details including summary, description, status, and owner. Use ticket_changelog for history. S Read ticket_search Search tickets with filtering by status, owner, and keywords. Returns ticket IDs with summaries. Read wiki_file_detect_format Detect the format of a local file (Markdown or TracWiki). Uses file extension first, then content-based heuris Read wiki_file_pull Pull a Trac wiki page to a local file. Fetches page content, converts to the requested format, and writes to t Read wiki_get Get wiki page content with Markdown output. Returns full content with metadata (version, author, modified date Read wiki_recent_changes Get recently modified wiki pages. Returns pages sorted by modification date (newest first). Useful for finding Read wiki_search Search wiki pages by content with relevance ranking. Returns snippets showing matched text. Set raw=true to ge

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Trac

Can an AI agent delete data through the Trac MCP server? +

Yes. The Trac server exposes 4 destructive tools including milestone_delete, ticket_batch_delete, ticket_delete. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Trac? +

The Trac server has 9 write tools including milestone_create, milestone_update, ticket_batch_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 Trac.

How many tools does the Trac MCP server expose? +

27 tools across 3 categories: Destructive, Read, Write. 14 are read-only. 13 can modify, create, or delete data.

How do I enforce a policy on Trac? +

Register the Trac 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 Trac tool call.

Deterministic rules across all 27 Trac tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.