search_knowledge
AI agents call search_knowledge to retrieve information from Grounded Code MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite an empty description, the tool name 'search_knowledge' and context of a knowledge base retrieval server strongly suggest this performs read-only search/query operations without side effects. Sibling tools on the server (search, query, list operations) are all Read category. No evidence of data modification, deletion, execution, or financial operations.
From the tool's definition Tool name 'search_knowledge' combined with server purpose (retrieval access to knowledge base) and sibling tools (grounded_search, grounded_search_code, search_code_examples, grounded_query_graph) all indicate query/retrieval operations.
Attacks that exploit this kind of access
search_knowledge. It is categorised as a Read tool in the Grounded Code MCP MCP Server, which means it retrieves data without modifying state.
Register the Grounded Code MCP server in PolicyLayer and add a rule for search_knowledge: 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 Grounded Code MCP. Nothing to install.
search_knowledge 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_knowledge 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_knowledge. 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_knowledge is provided by the Grounded Code MCP server (michaelalber/grounded-code-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 →