AI agents call read_doc to retrieve information from Mcp Rtfm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves documentation content. It has no side effects, does not modify data, execute code, or delete anything. The description explicitly names it as a read operation. The note that it is 'required before updating' confirms it is a prerequisite data-retrieval step, not the update itself. Minimal risk profile.
From the tool's definition Tool name is 'read_doc' and description states 'Read a documentation file' — clearly a retrieval operation with no modification or execution.
Documented attack patterns abuse exactly the kind of access read_doc gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Rtfm, and nothing reaches the server without passing your rules. This is the rule we recommend for read_doc:
{
"version": "1",
"default": "deny",
"tools": {
"read_doc": {}
}
}read_doc is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read a documentation file (required before updating). It is categorised as a Read tool in the Mcp Rtfm MCP Server, which means it retrieves data without modifying state.
Register the Mcp Rtfm 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 Rtfm. 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 Rtfm MCP server (ryanjoachim/mcp-rtfm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Mcp Rtfm tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
11 Mcp Rtfm tools catalogued and risk-classified — across an index of 42,500+ MCP servers.