query_internal_knowledge_base
AI agents call query_internal_knowledge_base to retrieve information from Local Search MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is used to query/search an internally-hosted knowledge base without modifying data. This is a typical read operation with no side effects. Even though the description is empty, the server's stated purpose (enabling offline search via BM25 algorithm) and the naming convention strongly indicate a retrieval-only function.
From the tool's definition Tool name 'query_internal_knowledge_base' and context of server providing 'offline Wikipedia search' and 'query Wikipedia' indicate data retrieval.
Attacks that exploit this kind of access
query_internal_knowledge_base. It is categorised as a Read tool in the Local Search MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Local Search MCP Server MCP server in PolicyLayer and add a rule for query_internal_knowledge_base: 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 Local Search MCP Server. Nothing to install.
query_internal_knowledge_base 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 query_internal_knowledge_base 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 query_internal_knowledge_base. 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.
query_internal_knowledge_base is provided by the Local Search MCP Server MCP server (yuzuponikemi/localsearch-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 →