Get the actual content of the most relevant code chunks — individual functions, classes, or sections — with exact line ranges for navigation. Smarter than grep: finds code by meaning, not just string matching. Multiple chunks from the same file can appear. Use this instead of search + Read when y...
AI agents call read_relevant to retrieve information from Local Rag 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 code content based on semantic search without modifying, executing, or deleting any data. It returns code chunks with line ranges for navigation—a straightforward read operation analogous to viewing file contents. No reversible modifications, command execution, financial transactions, or destructive operations are performed.
From the tool's definition Tool name 'read_relevant' and description 'Get the actual content of the most relevant code chunks' explicitly retrieves code content with 'no side effects' and 'Use this instead of search + Read when you need the content itself'.
Documented attack patterns abuse exactly the kind of access read_relevant gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Local Rag, and nothing reaches the server without passing your rules. This is the rule we recommend for read_relevant:
{
"version": "1",
"default": "deny",
"tools": {
"read_relevant": {}
}
}read_relevant is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the actual content of the most relevant code chunks — individual functions, classes, or sections — with exact line ranges for navigation. Smarter than grep: finds code by meaning, not just string matching. Multiple chunks from the same file can appear. Use this instead of search + Read when you need the content itself. Pass extensions/dirs/excludeDirs to scope the search. It is categorised as a Read tool in the Local Rag MCP Server, which means it retrieves data without modifying state.
Register the Local Rag MCP server in PolicyLayer and add a rule for read_relevant: 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 Local Rag. Nothing to install.
read_relevant 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 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. 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 is provided by the Local Rag MCP server (thewinci/mimirs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Local Rag, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
29 Local Rag tools catalogued and risk-classified — across an index of 43,000+ MCP servers.