AI agents call read_relevant_files to retrieve information from Mcp Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries file data to support analysis. It has no side effects, does not modify or delete files, does not execute code, and does not involve financial operations. The read-only nature and selective file loading (avoiding full project load) confirm the Read category.
From the tool's definition Tool name 'read_relevant_files' and description 'Read the files most relevant to a task without loading the whole' explicitly indicate retrieval of file content with no modification or execution.
Attacks that exploit this kind of access
Read the files most relevant to a task without loading the whole. It is categorised as a Read tool in the Mcp Flow MCP Server, which means it retrieves data without modifying state.
Register the Mcp Flow MCP server in PolicyLayer and add a rule for read_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 Mcp Flow. Nothing to install.
read_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 read_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 read_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.
read_relevant_files is provided by the Mcp Flow MCP server (remimenguy/mcp-flow). 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 →