// SCAN REPORT

Celery MCP

8 tools. 3 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

3 can modify or destroy data

5 read-only

8 tools total

Community server · catalogue entry verified 29/06/2026

How to control Celery MCP ↓

TOOL MAP

What Celery MCP exposes to your agents

Read (5) Write / Execute (2) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Celery MCP tools

Destructive · High revoke_task Revoking a task is an irreversible action that terminates job execution and cannot be undone. Execute · High initialize_celery_connection Initializing a Celery connection establishes a control channel to a distributed task execution system. Execute · High send_task Sending a task to Celery triggers execution of arbitrary registered tasks on remote workers.

3 of Celery MCP's 8 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Celery MCP

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

Deny destructive operations

{
  "revoke_task": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

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

Cap read operations

{
  "get_active_tasks": {
    "limits": [
      {
        "counter": "get_active_tasks_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 Celery MCP — 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 CELERY →

Instant setup, no code required.

FULL CATALOGUE

All 8 Celery MCP tools

DESTRUCTIVE 1 tools

Destructive revoke_task Revoke (cancel) a task.

EXECUTE 2 tools

Execute initialize_celery_connection Initialize connection to Celery broker and backend. Execute send_task Send a task to the Celery queue.

READ 5 tools

Read get_active_tasks Get information about active (running) tasks. Read get_scheduled_tasks Get information about scheduled tasks in the queue. Read get_task_status Get the status of a Celery task. Read get_worker_stats Get statistics about Celery workers. Read list_registered_tasks List all registered task names in the Celery app.

EXPLORE

Related servers

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

FAQ

Questions about Celery MCP

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

Yes. The Celery MCP server exposes 1 destructive tools including revoke_task. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How many tools does the Celery MCP server expose? +

8 tools across 4 categories: Destructive, Execute, Read, Write. 5 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Celery MCP? +

Register the Celery 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 Celery MCP tool call.

Deterministic rules across all 8 Celery MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CELERY →

Instant setup, no code required.

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