Low Risk

search_symbols

Find where a function, class, type, or interface is defined — by name, not semantics. Faster than grep for symbol lookup: searches the pre-built symbol index across all indexed files. Omit symbol to list all exports (filtered by type). Returns enrichment data: hasChildren, childCount, referenceCo...

How to control search_symbols ↓

What search_symbols does on Local Rag

AI agents call search_symbols 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.

Low Risk

Why search_symbols needs a policy

search_symbols is a read-only semantic search utility that retrieves information about code symbols and their usage patterns. It has no side effects, cannot modify code or data, and serves only to help agents locate and understand symbol definitions. The blast radius of misuse is minimal — an agent could perform unnecessary searches or gather metadata, but cannot alter the codebase or trigger external operations.

From the tool's definition Tool performs symbol lookup and searching across indexed files, returns metadata about symbols (hasChildren, childCount, referenceCount, isReexport).

Documented attack patterns abuse exactly the kind of access search_symbols gives an agent:

How to control search_symbols

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 search_symbols:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_symbols": {}
  }
}

search_symbols is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Local Rag — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about search_symbols

What does the search_symbols tool do? +

Find where a function, class, type, or interface is defined — by name, not semantics. Faster than grep for symbol lookup: searches the pre-built symbol index across all indexed files. Omit symbol to list all exports (filtered by type). Returns enrichment data: hasChildren, childCount, referenceCount, isReexport. Use usages next to see where the symbol is called. It is categorised as a Read tool in the Local Rag MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_symbols? +

Register the Local Rag MCP server in PolicyLayer and add a rule for search_symbols: 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.

What risk level is search_symbols? +

search_symbols is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit search_symbols? +

Yes. Add a rate_limit block to the search_symbols 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.

How do I block search_symbols completely? +

Set action: deny in the PolicyLayer policy for search_symbols. 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.

What MCP server provides search_symbols? +

search_symbols 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.

Enforce policy on every Local Rag tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.