AI agents call docs_rs_readme to retrieve information from Docs Rs MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves static documentation (README/overview) from a public crate registry. It has no side effects, cannot modify data, execute code, or delete resources. The only potential risk is information disclosure of public documentation, which is minimal. Confidence is high because the description unambiguously indicates a retrieval operation.
From the tool's definition Tool description states 'Get README/overview content' — a retrieval operation with no modification or execution. The broader server context (docs.rs search and documentation access) confirms it is a read-only documentation lookup.
Documented attack patterns abuse exactly the kind of access docs_rs_readme gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Docs Rs MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for docs_rs_readme:
{
"version": "1",
"default": "deny",
"tools": {
"docs_rs_readme": {}
}
}docs_rs_readme 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.
Get README/overview content of the specified crate. It is categorised as a Read tool in the Docs Rs MCP MCP Server, which means it retrieves data without modifying state.
Register the Docs Rs MCP server in PolicyLayer and add a rule for docs_rs_readme: 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 Docs Rs MCP. Nothing to install.
docs_rs_readme 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 docs_rs_readme 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 docs_rs_readme. 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.
docs_rs_readme is provided by the Docs Rs MCP server (nuskey8/docs-rs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Docs Rs MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 Docs Rs MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.