// SCAN REPORT

Rabbitmq

123 tools. 39 can modify or destroy data without limits.

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

Last updated: 1 Jul 2026

39 can modify or destroy data

84 read-only

123 tools total

Verified server · catalogue entry verified 01/07/2026 · full schemas captured for 63 of 123 tools

How to control Rabbitmq ↓

TOOL MAP

What Rabbitmq exposes to your agents

Read (84) Write / Execute (20) Destructive / Financial (19)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Rabbitmq costs in tokens

7,293 tokens of tool definitions, loaded on every request

3.6% of a 200k context window

121 heaviest tool: put-operator-policy

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Rabbitmq tools

Destructive · High bulk-delete-users Deleting users is an irreversible destructive action that cannot be undone without recovery procedures. Destructive · High delete-binding-exchange-exchange The tool performs an irreversible deletion operation. Destructive · High delete-global-parameter This tool permanently deletes a global parameter from RabbitMQ, which cannot be undone without manual recovery or backup restoration. Destructive · High delete-binding-exchange-queue This tool permanently removes message routing configuration.

39 of Rabbitmq's 123 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Rabbitmq

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

Deny destructive operations

{
  "bulk-delete-users": {
    "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

{
  "create-binding-exchange-exchange": {
    "limits": [
      {
        "counter": "create-binding-exchange-exchange_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get-auth": {
    "limits": [
      {
        "counter": "get-auth_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 Rabbitmq — 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 RABBITMQ →

Instant setup, no code required.

FULL CATALOGUE

All 123 Rabbitmq tools

DESTRUCTIVE 19 tools

EXECUTE 4 tools

Execute hash-password Hash a password using RabbitMQ's internal hashing. Execute pause-queue Pause a queue Execute resume-queue Resume a queue Execute start-vhost-on-node Start or restart a virtual host on a node

WRITE 16 tools

Write create-binding-exchange-exchange Create a binding from one exchange to another. Write create-binding-exchange-queue Create a binding from an exchange to a queue. Write protect-vhost Protect a virtual host from deletion Write put-exchange Create or update an exchange. Write put-global-parameter Create or update a global parameter. Write put-operator-policy Create or update an operator policy for a vhost. Write put-parameter Create or update a parameter for a component in a vhost. Write put-policy Create or update a policy for a vhost. Write put-queue Create or update a queue Write put-user Create or update a user. Write put-vhost Create or update a virtual host Write put-vhost-limit Set a vhost limit for a vhost. Write set-permission Set permissions for a user in a vhost. Write set-topic-permission Set topic permissions for a user in a vhost. Write set-user-limit Set a user limit. Write unprotect-vhost Remove deletion protection from a virtual host

READ 84 tools

EXPLORE

Related servers

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

FAQ

Questions about Rabbitmq

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

Yes. The Rabbitmq server exposes 19 destructive tools including bulk-delete-users, delete-binding-exchange-exchange, delete-binding-exchange-queue. 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 Rabbitmq? +

The Rabbitmq server has 16 write tools including create-binding-exchange-exchange, create-binding-exchange-queue, protect-vhost. 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 Rabbitmq.

How many tools does the Rabbitmq MCP server expose? +

123 tools across 4 categories: Destructive, Execute, Read, Write. 84 are read-only. 39 can modify, create, or delete data.

How do I enforce a policy on Rabbitmq? +

Register the Rabbitmq 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 Rabbitmq tool call.

Deterministic rules across all 123 Rabbitmq tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON RABBITMQ →

Instant setup, no code required.

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