Find files with content similar to a reference file. Uses semantic similarity to find related documents, code files, or any text content. When to use this tool: - Find documentation similar to a specific guide or README - Locate related code files, configuration files, or scripts - Discover alter...
AI agents call similar_files to retrieve information from Directory Indexer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs semantic search and retrieval of file information from an index. It only queries and returns data about similar files without modifying, deleting, or executing any content. The blast radius of misuse is limited to unintended information disclosure of already-indexed content, which is low severity.
From the tool's definition Tool description states it 'Find files with content similar to a reference file' and 'Analyzes the semantic content of the reference file' with 'Compares against all indexed files using vector similarity' and 'Returns files ranked by content similarity score'.
Documented attack patterns abuse exactly the kind of access similar_files gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Directory Indexer, and nothing reaches the server without passing your rules. This is the rule we recommend for similar_files:
{
"version": "1",
"default": "deny",
"tools": {
"similar_files": {}
}
}similar_files 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.
Find files with content similar to a reference file. Uses semantic similarity to find related documents, code files, or any text content. When to use this tool: - Find documentation similar to a specific guide or README - Locate related code files, configuration files, or scripts - Discover alternative implementations or approaches - Find files covering similar topics or concepts How it works: - Analyzes the semantic content of the reference file - Compares against all indexed files using vector similarity - Returns files ranked by content similarity score Examples: - Given. It is categorised as a Read tool in the Directory Indexer MCP Server, which means it retrieves data without modifying state.
Register the Directory Indexer MCP server in PolicyLayer and add a rule for similar_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 Directory Indexer. Nothing to install.
similar_files 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 similar_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.
Set action: deny in the PolicyLayer policy for similar_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.
similar_files is provided by the Directory Indexer MCP server (peteretelej/directory-indexer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Directory Indexer, 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.
7 Directory Indexer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.