AI agents call read_doc to retrieve information from Mcp Docs 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 static documentation content. It performs read-only access to reference materials, implementation recipes, and API documentation without creating, modifying, deleting, or executing operations. The action is purely informational retrieval with no side effects or system state changes.
From the tool's definition Tool name 'read_doc' and description 'Fetch the full content of a doc, SDK README, recipe, or other entry' indicate retrieval of documentation and reference material with no modification or side effects.
Attacks that exploit this kind of access
Fetch the full content of a doc, SDK README, recipe, or other entry by. It is categorised as a Read tool in the Mcp Docs MCP Server, which means it retrieves data without modifying state.
Register the Mcp Docs MCP server in PolicyLayer and add a rule for read_doc: 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 Mcp Docs. Nothing to install.
read_doc 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 read_doc 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 read_doc. 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.
read_doc is provided by the Mcp Docs MCP server (prosodyai/mcp-docs). 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 →