List all files that a given file imports (its dependencies). Shows the resolved import graph — what this file actually depends on. This is FILE-level, outward direction. Routing — reverse (files that import this one) is dependents; for a single symbol
AI agents call depends_on 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 performs semantic analysis and retrieval of dependency metadata from the codebase. It has no side effects, does not execute code, does not create or delete data, and does not modify files or state. It is a pure information retrieval operation analogous to 'get' or 'list', placing it squarely in the Read category with low severity.
From the tool's definition Tool 'depends_on' retrieves and queries import graph data — 'List all files that a given file imports' — with no modification, creation, deletion, or execution.
Documented attack patterns abuse exactly the kind of access depends_on 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 depends_on:
{
"version": "1",
"default": "deny",
"tools": {
"depends_on": {}
}
}depends_on 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.
List all files that a given file imports (its dependencies). Shows the resolved import graph — what this file actually depends on. This is FILE-level, outward direction. Routing — reverse (files that import this one) is dependents; for a single symbol. 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 depends_on: 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.
depends_on 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 depends_on 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 depends_on. 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.
depends_on 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.