Low Risk

callees

List the functions/methods a symbol directly calls (one hop out), each resolved to its definition file:line. The forward complement of usages (callers, one hop in) — use it to see what a function depends on before editing it. Static resolution: dynamic dispatch (callbacks, interface→impl, DI) and...

How to control callees ↓

What callees does on Local Rag

AI agents call callees 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 callees needs a policy

This is a pure information retrieval tool that performs static code analysis to identify call relationships. It queries an indexed codebase and returns read-only data about code structure. No data is created, modified, deleted, or executed. It is a code navigation aid for understanding dependencies before editing, not for making changes.

From the tool's definition Tool lists/retrieves information about function calls without modification — "List the functions/methods a symbol directly calls", "resolved to its definition file:line". No mutations or side effects. Static analysis only.

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

How to control callees

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 callees:

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

callees 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 callees

What does the callees tool do? +

List the functions/methods a symbol directly calls (one hop out), each resolved to its definition file:line. The forward complement of usages (callers, one hop in) — use it to see what a function depends on before editing it. Static resolution: dynamic dispatch (callbacks, interface→impl, DI) and calls into unindexed code won. 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 callees? +

Register the Local Rag MCP server in PolicyLayer and add a rule for callees: 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 callees? +

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

Can I rate-limit callees? +

Yes. Add a rate_limit block to the callees 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 callees completely? +

Set action: deny in the PolicyLayer policy for callees. 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 callees? +

callees 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.