Rank the most relevant files for a natural-language task so the coding agent can open only a small subset.
AI agents call find_relevant_files to retrieve information from Project Context Map without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and ranks file metadata to help an agent identify which files to read next. It has no side effects, makes no modifications, executes no code, and incurs no financial impact. It is purely an informational/search utility, matching the 'Read' category definition of 'retrieves or queries data; no side effects'.
From the tool's definition Tool description states it 'Rank the most relevant files' and 'open only a small subset' — this is a search/ranking operation with no data modification, deletion, or code execution.
Attacks that exploit this kind of access
Rank the most relevant files for a natural-language task so the coding agent can open only a small subset. It is categorised as a Read tool in the Project Context Map MCP Server, which means it retrieves data without modifying state.
Register the Project Context Map MCP server in PolicyLayer and add a rule for find_relevant_files: 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 Project Context Map. Nothing to install.
find_relevant_files 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 find_relevant_files 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 find_relevant_files. 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.
find_relevant_files is provided by the Project Context Map MCP server (tamojit-123/project-context-map-mcp). 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 →