Open a local PDF or plain-text file and return a cheap overview — page count,
AI agents call local_doc_info 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 reads and returns summary information (page count, likely other metadata) from local files. It performs no side effects, creates no data, executes no code, and makes no irreversible changes. It is a straightforward read operation analogous to 'get' or 'fetch' calls.
From the tool's definition Tool name 'local_doc_info' and description 'return a cheap overview — page count' indicate retrieval of metadata from existing local documents without modification, deletion, or code execution.
Attacks that exploit this kind of access
Open a local PDF or plain-text file and return a cheap overview — page count,. 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_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 Philosophy. Nothing to install.
local_doc_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 local_doc_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 local_doc_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.
local_doc_info 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 →