search-knowledge
AI agents call search-knowledge to retrieve information from Better Qdrant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the tool name and functional context strongly indicate this performs a read-only search operation against the knowledge base without modifying data. This follows the pattern of typical semantic search tools that query stored embeddings and return results. No side effects are expected from a search operation.
From the tool's definition Tool name 'search-knowledge' indicates a query/retrieval operation. Context shows sibling tools include 'store-knowledge', 'delete-knowledge', and 'get-knowledge-by-id', positioning this as the retrieval counterpart.
Attacks that exploit this kind of access
search-knowledge. It is categorised as a Read tool in the Better Qdrant MCP Server, which means it retrieves data without modifying state.
Register the Better Qdrant 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 Better Qdrant. 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 Better Qdrant MCP server (jtsang4/better-qdrant-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 →