Get information about server status and indexed content. Shows what directories and files are available for search. When to use this tool: - REQUIRED: Check available workspace names before using workspace parameter in search or similar_files tools - Check what content is already indexed before p...
AI agents call server_info 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 is a read-only introspection tool that queries metadata about the indexing system. It retrieves information (status, statistics, directory listings) with no side effects, reversible operations, or external execution. The lowest severity applies because even if misused by an AI agent, it only discloses information about what is indexed, posing minimal risk compared to write, execute, or destructive operations.
From the tool's definition Tool provides 'information about server status and indexed content' and 'Shows what directories and files are available for search.' It reports statistics and lists indexed directories without modifying, executing, or deleting anything.
Documented attack patterns abuse exactly the kind of access server_info 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 server_info:
{
"version": "1",
"default": "deny",
"tools": {
"server_info": {}
}
}server_info 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.
Get information about server status and indexed content. Shows what directories and files are available for search. When to use this tool: - REQUIRED: Check available workspace names before using workspace parameter in search or similar_files tools - Check what content is already indexed before performing searches - Verify system is working properly - See indexing statistics and status - Understand scope of available searchable content How it works: - Reports total indexed directories, files, and chunks - Shows database size and last indexing time - Lists all indexed directories with file counts - Lists all configured workspaces with their paths and file counts - Reports any errors or issues Examples: - Check workspaces before searching:. 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 server_info: 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.
server_info 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 server_info 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 server_info. 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.
server_info 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.