Redmine

59 tools. 36 can modify or destroy data without limits.

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

Last updated:

36 can modify or destroy data
23 read-only
59 tools total

Community server · catalogue entry verified 03/07/2026

How to control Redmine ↓

What Redmine exposes to your agents

Read (23) Write / Execute (24) Destructive / Financial (12)
Critical Risk

The most dangerous Redmine tools

36 of Redmine's 59 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Redmine

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

Deny destructive operations
{
  "delete_attachment": {
    "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
{
  "add_membership": {
    "limits": [
      {
        "counter": "add_membership_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "get_attachment": {
    "limits": [
      {
        "counter": "get_attachment_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 Redmine — 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 REDMINE →

Instant setup, no code required.

All 59 Redmine tools

Related servers

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

Questions about Redmine

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

Yes. The Redmine server exposes 12 destructive tools including delete_attachment, delete_group, delete_issue. 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 Redmine? +

The Redmine server has 24 write tools including add_membership, add_user_to_group, add_watcher. 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 Redmine.

How many tools does the Redmine MCP server expose? +

59 tools across 3 categories: Destructive, Read, Write. 23 are read-only. 36 can modify, create, or delete data.

How do I enforce a policy on Redmine? +

Register the Redmine 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 Redmine tool call.

Deterministic rules across all 59 Redmine tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

59 Redmine 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.