Evaluate individual chunk relevance scores using semantic similarity and LLM assessment
AI agents call rag.measure_chunk_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 performs evaluation and scoring of RAG (Retrieval-Augmented Generation) chunk relevance. It retrieves metrics through semantic similarity computation and LLM-based assessment but does not create, modify, delete, or execute external operations. The blast radius of misuse is minimal—incorrect relevance scores affect retrieval quality but not data integrity, financial systems, or system execution.
From the tool's definition Tool name and description indicate it 'Evaluate[s] individual chunk relevance scores' using 'semantic similarity and LLM assessment'. These are read-only assessment operations with no modification, deletion, or execution of external commands.
Attacks that exploit this kind of access
Evaluate individual chunk relevance scores using semantic similarity and LLM assessment. 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.measure_chunk_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.measure_chunk_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.measure_chunk_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.measure_chunk_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.measure_chunk_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 →