clelp_rate · Clelp MCP: Risk & Policy

WHAT IT DOES

What clelp_rate does on Clelp

AI agents use clelp_rate to create or update resources in Clelp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Clelp environment.

WHY IT NEEDS A POLICY

Why clelp_rate needs a policy

This tool submits a user rating for a skill, which is a write operation that creates new data (a rating). It is reversible in principle (ratings can be updated or removed) and has low blast radius since it only affects community rating data, not critical systems.

From the tool's definition 'Submit a rating for a skill' — creates/posts a rating entry

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

clelp_rate Rate-limited

clelp_rate stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "clelp_rate": {
      "limits": [
        {
          "counter": "clelp_rate_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Clelp, so you can run agents against it safely.

FAQ

Questions about clelp_rate

What does the clelp_rate tool do? +

Submit a rating for a skill you. It is categorised as a Write tool in the Clelp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on clelp_rate? +

Register the Clelp MCP server in PolicyLayer and add a rule for clelp_rate: 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 Clelp. Nothing to install.

What risk level is clelp_rate? +

clelp_rate is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit clelp_rate? +

Yes. Add a rate_limit block to the clelp_rate 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 clelp_rate completely? +

Set action: deny in the PolicyLayer policy for clelp_rate. 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 clelp_rate? +

clelp_rate is provided by the Clelp MCP server (oscarsterling/clelp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.