Assess relevance of retrieved documents to the query using semantic similarity and LLM judges
AI agents call rag.evaluate_retrieval_relevance to retrieve information from ContextForge MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes documents to assess their relevance to a query. It reads data, applies analysis logic (semantic similarity and LLM judgment), and returns an assessment. No data is created, modified, deleted, or irreversibly changed. No external operations, financial transactions, or code execution on the host system occurs. This is purely an analytical Read operation on retrieved content.
From the tool's definition Tool description indicates 'assess relevance of retrieved documents' and 'evaluate...retrieval', which are query and analysis operations with no data modification or side effects.
Attacks that exploit this kind of access
Assess relevance of retrieved documents to the query using semantic similarity and LLM judges. It is categorised as a Read tool in the ContextForge MCP Gateway MCP Server, which means it retrieves data without modifying state.
Register the ContextForge MCP Gateway MCP server in PolicyLayer and add a rule for rag.evaluate_retrieval_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 ContextForge MCP Gateway. Nothing to install.
rag.evaluate_retrieval_relevance 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 rag.evaluate_retrieval_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.
Set action: deny in the PolicyLayer policy for rag.evaluate_retrieval_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.
rag.evaluate_retrieval_relevance is provided by the ContextForge MCP Gateway MCP server (jrmatherly/mcp-context-forge). 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 →