List all files that import a given file (reverse dependencies). Shows the blast radius before modifying a file — every file that would be affected by a change. This is FILE-level, inward direction. Routing — reverse (what this file imports) is depends_on; for finer SYMBOL-level blast radius use i...
AI agents call dependents 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 is a read-only analysis tool that queries code relationships without altering any data. It retrieves dependency information to inform decision-making but does not create, modify, delete, or execute anything. The purpose is semantic search and navigation, not action. Even though the information could inform risky decisions, the tool itself performs only a harmless query operation.
From the tool's definition Tool 'dependents' lists files that import a given file, showing reverse dependencies. Description explicitly states it 'shows the blast radius' and provides analysis only—'List all files' with no modification, deletion, or execution capability.
Documented attack patterns abuse exactly the kind of access dependents 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 dependents:
{
"version": "1",
"default": "deny",
"tools": {
"dependents": {}
}
}dependents 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 import a given file (reverse dependencies). Shows the blast radius before modifying a file — every file that would be affected by a change. This is FILE-level, inward direction. Routing — reverse (what this file imports) is depends_on; for finer SYMBOL-level blast radius use impact (transitive callers + tests) or usages (flat refs). 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 dependents: 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.
dependents 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 dependents 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 dependents. 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.
dependents 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.