Semantic search within a specific document. Use when you know which document to search but need to find specific information within it.
AI agents call search_in_doc to retrieve information from Documentation MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that retrieves and searches documentation content. It has no side effects, does not execute code or commands, does not modify or delete data, and poses no financial risk. The semantic search capability is a standard information retrieval function with minimal blast radius if misused—worst case being information disclosure of documentation already intended to be searchable.
From the tool's definition Tool performs 'semantic search within a specific document' to 'find specific information' without modifying data. No creation, deletion, execution, or financial operations are described.
Attacks that exploit this kind of access
Semantic search within a specific document. Use when you know which document to search but need to find specific information within it. It is categorised as a Read tool in the Documentation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Documentation MCP Server MCP server in PolicyLayer and add a rule for search_in_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 Documentation MCP Server. Nothing to install.
search_in_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 search_in_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 search_in_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.
search_in_doc is provided by the Documentation MCP Server MCP server (wuyuwenj/api-doc-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 →