search_local_docs
AI agents call search_local_docs to retrieve information from MCP Local Context 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 data from local documentation without modifying, deleting, or executing code. It fits the Read category as it enables searching and accessing documents with no side effects. The empty description reduces confidence slightly, but the server's stated purpose (RAG capabilities, document access/search) and sibling tools' patterns confirm this classification.
From the tool's definition Tool name 'search_local_docs' and server context describe a RAG system for accessing local documents. Sibling tools include 'list_local_docs', 'get_local_doc', and 'semantic_search', all of which are clearly Read operations.
Attacks that exploit this kind of access
search_local_docs. It is categorised as a Read tool in the MCP Local Context MCP Server, which means it retrieves data without modifying state.
Register the MCP Local Context MCP server in PolicyLayer and add a rule for search_local_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 Local Context. Nothing to install.
search_local_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_local_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_local_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_local_docs is provided by the MCP Local Context MCP server (steedmonteiro/mcp-local-context). 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 →