Read a bounded slice of a local PDF or text file — a page range starting at page_from — and
AI agents call local_doc_read 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 or queries document data (reading a page range from a file) with no side effects. It matches the Read category definition: retrieves data without reversible or irreversible modifications. The bounded nature (explicit page range) and read-only operation pose minimal risk. Low severity because the worst outcome is information disclosure of already-public philosophy texts.
From the tool's definition Tool name 'local_doc_read' and description 'Read a bounded slice of a local PDF or text file — a page range starting at page_from' indicates retrieval of document content with no modification or side effects.
Attacks that exploit this kind of access
Read a bounded slice of a local PDF or text file — a page range starting at page_from — and. 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_read: 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_read 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_read 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_read. 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_read 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 →