List all registered task names in the Celery app.
AI agents call list_registered_tasks to retrieve information from Celery MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only enumeration of task metadata. While knowledge of available tasks could theoretically inform an attacker about capabilities, the tool itself performs no state-changing operations, executes no code, and creates no side effects. It is analogous to listing available functions in an API—a foundational read operation.
From the tool's definition Tool description states it 'List all registered task names' with no modifications or side effects. This is a query operation that retrieves information about available tasks without invoking or altering them.
Attacks that exploit this kind of access
List all registered task names in the Celery app. It is categorised as a Read tool in the Celery MCP MCP Server, which means it retrieves data without modifying state.
Register the Celery MCP server in PolicyLayer and add a rule for list_registered_tasks: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Celery MCP. Nothing to install.
list_registered_tasks is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_registered_tasks rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_registered_tasks. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_registered_tasks is provided by the Celery MCP server (joeyrubas/celery-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →