eval_relevance

eval_relevance

Server Multivon multivon-ai/multivon-mcp
Category Read
Risk class Low
Parameters 00 required

What eval_relevance does on Multivon

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

Why eval_relevance needs a policy

Based on the tool name and sibling tools, this appears to be an evaluation/scoring tool that reads and assesses relevance of outputs. Empty description lowers confidence. Sibling tools like eval_faithfulness, eval_bias, eval_context_recall suggest a pattern of read-only evaluation metrics. No evidence of write, execute, or destructive behavior.

From the tool's definition Tool name 'eval_relevance' and server description 'evaluation tools'; description is empty or uninformative.

Questions about eval_relevance

What does the eval_relevance tool do? +

eval_relevance. It is categorised as a Read tool in the Multivon MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on eval_relevance? +

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

What risk level is eval_relevance? +

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

Can I rate-limit eval_relevance? +

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

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

eval_relevance is provided by the Multivon MCP server (multivon-ai/multivon-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.