Low Risk

findOneTask

depth can be provided to request your task

How to control findOneTask ↓

What findOneTask does on Twenty MCP Server

AI agents call findOneTask to retrieve information from Twenty MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why findOneTask needs a policy

The tool is a query/lookup operation that retrieves a single task record from the CRM. The verb 'find' and lack of any mutation language (create, update, delete, modify) confirm this is a Read operation. Severity is low as it only accesses existing data without side effects. High confidence due to clear naming convention and context of a CRM data retrieval method.

From the tool's definition Tool name 'findOneTask' and description indicating it 'request[s] your task' indicates a data retrieval operation with no modification or side effects.

Documented attack patterns abuse exactly the kind of access findOneTask gives an agent:

How to control findOneTask

PolicyLayer is an MCP gateway — it sits between your AI agents and Twenty MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for findOneTask:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "findOneTask": {}
  }
}

findOneTask is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Twenty MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about findOneTask

What does the findOneTask tool do? +

depth can be provided to request your task. It is categorised as a Read tool in the Twenty MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on findOneTask? +

Register the Twenty MCP Server MCP server in PolicyLayer and add a rule for findOneTask: 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 Twenty MCP Server. Nothing to install.

What risk level is findOneTask? +

findOneTask is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit findOneTask? +

Yes. Add a rate_limit block to the findOneTask 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.

How do I block findOneTask completely? +

Set action: deny in the PolicyLayer policy for findOneTask. 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.

What MCP server provides findOneTask? +

findOneTask is provided by the Twenty MCP Server MCP server (jdu278/twenty-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Twenty MCP Server tool call.

Start from Twenty MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

219 Twenty MCP Server 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.