Visualize how files relate to each other — imports, exports, and fan-in/fan-out. Faster than reading import statements across many files. Use
AI agents call project_map 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.
The tool performs analysis and visualization of existing code structure. It reads dependency and relationship data to present a map, which is a passive retrieval operation with no side effects. No code execution, data modification, deletion, or financial operations occur. This is clearly a Read category tool.
From the tool's definition Tool 'project_map' visualizes file relationships (imports, exports, fan-in/fan-out) and is explicitly contrasted as 'faster than reading import statements' — it retrieves and queries structural metadata about code organization without modifying, deleting, or…
Documented attack patterns abuse exactly the kind of access project_map 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 project_map:
{
"version": "1",
"default": "deny",
"tools": {
"project_map": {}
}
}project_map 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.
Visualize how files relate to each other — imports, exports, and fan-in/fan-out. Faster than reading import statements across many files. Use. 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 project_map: 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.
project_map 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 project_map 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 project_map. 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.
project_map 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.