AI agents use index_folder to create or update resources in Astllm — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Astllm environment.
This tool reads source files and writes index/symbol data to storage. It creates new data (parsed ASTs and symbol indexes) and stores them, making it a Write operation. It is reversible (the index can be invalidated/deleted, as suggested by the sibling 'invalidate_cache' tool).
From the tool's definition Index a local source code folder. Recursively discovers source files, parses ASTs, and stores symbols for fast retrieval.
Attacks that exploit this kind of access
Index a local source code folder. Recursively discovers source files, parses ASTs, and stores symbols for fast retrieval. It is categorised as a Write tool in the Astllm MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Astllm MCP server in PolicyLayer and add a rule for index_folder: 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 Astllm. Nothing to install.
index_folder 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_folder 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_folder. 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_folder is provided by the Astllm MCP server (tluyben/astllm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →