Index directories to make their files searchable. Processes files to create vector embeddings for semantic search. When to use this tool: - User specifically requests indexing a directory as a knowledge base - Adding new documentation, code repositories, or file collections to search - Updating i...
AI agents use index to create or update resources in Directory Indexer — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Directory Indexer environment.
The 'index' tool creates and stores new data (vector embeddings and index records in a database) in a reversible manner. This is a Write operation rather than Read—while it accesses files to extract content, its primary purpose is to create and persist indexed data structures. It's not Destructive because indexing is reversible (the delete_index sibling tool confirms this).
From the tool's definition Tool description states it "Processes files to create vector embeddings" and "Stores in database for fast retrieval".
Documented attack patterns abuse exactly the kind of access index 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 index:
{
"version": "1",
"default": "deny",
"tools": {
"index": {
"limits": [
{
"counter": "index_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}index 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.
Free to start. No card required.
Index directories to make their files searchable. Processes files to create vector embeddings for semantic search. When to use this tool: - User specifically requests indexing a directory as a knowledge base - Adding new documentation, code repositories, or file collections to search - Updating index when many files have changed How it works: - Recursively scans directories for supported file types - Extracts text content and splits into chunks - Generates vector embeddings for semantic similarity - Stores in database for fast retrieval Examples: - Index documentation: [. It is categorised as a Write tool in the Directory Indexer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Directory Indexer MCP server in PolicyLayer and add a rule for index: 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.
index is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the index 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 index. 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.
index 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.