AI agents call search_knowledge_bases to retrieve information from Lens without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | Yes | Natural language search question or topic |
top_k | number | — | Maximum number of chunks to return |
knowledge_base_ids | string | Yes | Comma-separated list of KB UUIDs (from list_knowledge_bases) |
similarity_threshold | number | — | Minimum score 0-1 |
Parameters from the server's own tool schema.
This tool performs a read-only semantic search operation against knowledge bases. It retrieves and returns matching results based on a natural language query without creating, modifying, deleting, or executing any operations. The function is purely informational and has no destructive or operational side effects.
From the tool's definition Tool description states 'Search one or more knowledge bases by semantic similarity' with parameters for querying and selecting knowledge bases. The verb 'search' and the retrieval-focused operation indicate no data modification or side effects.
Risk signalsAccepts freeform code/query input (query)
Attacks that exploit this kind of access
Search one or more knowledge bases by semantic similarity. query: natural language; knowledge_base_ids: comma-separated UUIDs from list_knowledge_bases. It is categorised as a Read tool in the Lens MCP Server, which means it retrieves data without modifying state.
search_knowledge_bases accepts 4 parameters: query, top_k, knowledge_base_ids, similarity_threshold. Required: query, knowledge_base_ids. The full parameter table on this page comes from the server's own tool schema.
Register the Lens MCP server in PolicyLayer and add a rule for search_knowledge_bases: 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 Lens. Nothing to install.
search_knowledge_bases 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_bases 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_bases. 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_bases is provided by the Lens MCP server (lens-mcp-server). 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 →