Search a local PDF or text file for a keyword or regular expression and return only the
AI agents call local_doc_search to retrieve information from Philosophy 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 philosophy texts without modifying, executing, or deleting anything. Search operations are inherently read-only data access with no side effects or capability to alter state.
From the tool's definition Tool name 'local_doc_search' searches for keywords/regex in local documents; tool description explicitly states 'return only the' (matching text), indicating read-only retrieval.
Attacks that exploit this kind of access
Search a local PDF or text file for a keyword or regular expression and return only the. It is categorised as a Read tool in the Philosophy MCP Server, which means it retrieves data without modifying state.
Register the Philosophy MCP server in PolicyLayer and add a rule for local_doc_search: 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 Philosophy. Nothing to install.
local_doc_search 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 local_doc_search 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 local_doc_search. 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.
local_doc_search is provided by the Philosophy MCP server (sea9401/philosophy-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 →