search for documentation by query
AI agents call search-docs to retrieve information from MCP Doc Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation against documentation. It retrieves data based on keyword queries without modifying, deleting, or executing anything. The blast radius of misuse is minimal—an agent could only access documentation that is already publicly available on the official website. This is a classic Read category tool.
From the tool's definition Tool name is 'search-docs' and description states 'search for documentation by query'. Server description confirms it 'supports keyword searching and content retrieval from official website documentation.' No write, delete, execute, or financial operations…
Attacks that exploit this kind of access
search for documentation by query. It is categorised as a Read tool in the MCP Doc Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Doc Server MCP server in PolicyLayer and add a rule for 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 MCP Doc Server. Nothing to install.
search-docs 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-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.
Set action: deny in the PolicyLayer policy for 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.
search-docs is provided by the MCP Doc Server MCP server (shengwang-community/doc-mcp-server). 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 →