AI agents call search_text to retrieve information from Astllm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from indexed files without any side effects. It is a search/discovery mechanism that returns matches but does not create, modify, execute, or delete anything. The capability to search comments and configuration values does not elevate risk beyond Read category, as the agent can only view the results, not act upon them.
From the tool's definition Tool performs 'full-text search across indexed file contents' to find 'string literals, comments, configuration values, or patterns'. The description explicitly indicates read-only operations with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Full-text search across indexed file contents. Useful for finding string literals, comments, configuration values, or patterns not captured as symbols. It is categorised as a Read tool in the Astllm MCP Server, which means it retrieves data without modifying state.
Register the Astllm MCP server in PolicyLayer and add a rule for search_text: 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.
search_text 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 search_text 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 search_text. 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.
search_text 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 →