evaluate_retrieval

THE RISK

Low Risk

Why evaluate_retrieval needs a policy

With no description available, I can only infer from the tool name. 'evaluate_retrieval' suggests assessing or scoring retrieval quality, which would be a read/analytical operation. However, given the empty description, confidence is very low.

From the tool's definition Tool name is 'evaluate_retrieval' but description is empty or uninformative.

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

POLICY

How to control evaluate_retrieval

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "evaluate_retrieval": {
      "limits": [
        {
          "counter": "evaluate_retrieval_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

evaluate_retrieval gets a rate cap, and everything else on the server is denied unless you say otherwise.

Create a free account and register Knowledge Rag — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

SET A RULE FOR THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Knowledge Rag tools

Destructive remove_document Remove a document from the knowledge base index. Mutating — removes index entries. If Write reindex_documents Index or reindex all documents in the knowledge base. Mutating — modifies the vector Write add_document add_document Write add_from_url Fetch content from a URL, convert to markdown, and add to the knowledge base. Mutatin Write update_document Update the content of an existing document in the knowledge base. Mutating — overwrit Read get_document get_document Read get_index_stats Get statistics and health metrics for the knowledge base index. Read-only. No side ef Read list_categories List all document categories with their document counts. Read-only. No side effects.

All 12 Knowledge Rag tools →

Other tools on other servers

Android Forensics ADB MCP Server generate_app_analysis_report Ethereum Tools add Math MCP Server complex_analysis_suite Crypto_MCP aes_encrypt

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Tool risk categories → How PolicyLayer classifies MCP tools by what they can do.
MCP tool → What an MCP tool is and how clients discover and call it.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about evaluate_retrieval

What does the evaluate_retrieval tool do? +

evaluate_retrieval. It is categorised as a Other tool in the Knowledge Rag MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on evaluate_retrieval? +

Register the Knowledge Rag MCP server in PolicyLayer and add a rule for evaluate_retrieval: 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 Knowledge Rag. Nothing to install.

What risk level is evaluate_retrieval? +

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

Can I rate-limit evaluate_retrieval? +

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

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

evaluate_retrieval is provided by the Knowledge Rag MCP server (lyonzin/knowledge-rag). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Knowledge Rag tool call.

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

CHECK YOUR STACK →