Medium Risk

index_files

Index files in a directory for semantic search. Without patterns, indexes the project from config and prunes deleted or now-excluded files. With patterns, refreshes or expands only matching files and leaves the rest of the index untouched.

How to control index_files ↓

What index_files does on Local Rag

AI agents use index_files to create or update resources in Local Rag — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Local Rag environment.

Medium Risk

Why index_files needs a policy

This tool creates or updates an index (a data structure stored persistently) based on files in a directory. It is a Write operation because it modifies the search index reversibly — files can be re-indexed or pruned. It also prunes deleted/excluded files from the index, but this is a side effect of a write/update operation rather than a destructive irreversible deletion of source data.

From the tool's definition Index files in a directory for semantic search... refreshes or expands only matching files and leaves the rest of the index untouched

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

How to control index_files

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 index_files:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "index_files": {
      "limits": [
        {
          "counter": "index_files_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

index_files stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. 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.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about index_files

What does the index_files tool do? +

Index files in a directory for semantic search. Without patterns, indexes the project from config and prunes deleted or now-excluded files. With patterns, refreshes or expands only matching files and leaves the rest of the index untouched. It is categorised as a Write tool in the Local Rag MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on index_files? +

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

index_files is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit index_files? +

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

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

index_files 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.