search_across_docs
AI agents call search_across_docs to retrieve information from DevDocs MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries documentation data with no side effects. Search operations are inherently Read category. The low severity reflects that documentation retrieval has minimal blast radius—misuse would only expose information that is already public from DevDocs.io.
From the tool's definition Tool name 'search_across_docs' indicates a search operation across documentation. The server description emphasizes 'searching, content retrieval' as core functions.
Attacks that exploit this kind of access
search_across_docs. It is categorised as a Read tool in the DevDocs MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DevDocs MCP Server MCP server in PolicyLayer and add a rule for search_across_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 DevDocs MCP Server. Nothing to install.
search_across_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_across_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_across_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_across_docs is provided by the DevDocs MCP Server MCP server (javierdevcol/devdocs-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 →