Search for similar vectors in a LanceDB table using either a direct vector or text that will be converted to a vector using Ollama embedding.
AI agents call vector_search to retrieve information from LanceDB Node without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves data through vector similarity search without side effects. It accepts either a pre-computed vector or text input (converted to vector via Ollama), then returns matching results. This is purely a read operation with no ability to modify, delete, or execute code. Severity is low as misuse would only expose data already stored in the vector database.
From the tool's definition Tool description states 'Search for similar vectors' with no modification, deletion, or execution capability mentioned. This is a query operation returning search results from a vector database.
Attacks that exploit this kind of access
Search for similar vectors in a LanceDB table using either a direct vector or text that will be converted to a vector using Ollama embedding. It is categorised as a Read tool in the LanceDB Node MCP Server, which means it retrieves data without modifying state.
Register the LanceDB Node MCP server in PolicyLayer and add a rule for vector_search: 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 LanceDB Node. Nothing to install.
vector_search 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 vector_search 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 vector_search. 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.
vector_search is provided by the LanceDB Node MCP server (vurtnec/mcp-lancedb-node). 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 →