Low Risk

docs_search_docs

docs_search_docs

How to control docs_search_docs ↓

AI agents call docs_search_docs to retrieve information from McpDocServer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

This tool searches documentation, which is a retrieval operation with no side effects. The empty description reduces confidence slightly, but the naming convention, server context (documentation server), and sibling tools all indicate a read operation for querying/searching documents. No modification, deletion, or execution capabilities are implied.

From the tool's definition Tool name 'docs_search_docs' combined with server description indicating 'keyword searching' and 'document detail retrieval' capabilities. Sibling tools include 'docs_list_docs' and 'docs_get_doc_detail', establishing a read-only documentation query pattern.

Documented attack patterns abuse exactly the kind of access docs_search_docs gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and McpDocServer, and nothing reaches the server without passing your rules. This is the rule we recommend for docs_search_docs:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "docs_search_docs": {}
  }
}

docs_search_docs is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register McpDocServer — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the docs_search_docs tool do? +

docs_search_docs. It is categorised as a Read tool in the McpDocServer MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on docs_search_docs? +

Register the McpDocServer MCP server in PolicyLayer and add a rule for docs_search_docs: 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 McpDocServer. Nothing to install.

What risk level is docs_search_docs? +

docs_search_docs is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit docs_search_docs? +

Yes. Add a rate_limit block to the docs_search_docs 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.

How do I block docs_search_docs completely? +

Set action: deny in the PolicyLayer policy for docs_search_docs. 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.

What MCP server provides docs_search_docs? +

docs_search_docs is provided by the McpDocServer MCP server (ruan11223344/mcpdocserver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every McpDocServer tool call.

Deterministic rules across all 3 McpDocServer tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

3 McpDocServer tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.