AI agents call search_vectors to retrieve information from LanceDB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a similarity search operation on vectors stored in a database table. It retrieves or queries data without creating, modifying, deleting, or executing arbitrary operations. This is a classic Read operation with minimal security risk—the blast radius of misuse is limited to unauthorized data access or information disclosure.
From the tool's definition Tool name 'search_vectors' combined with description 'Search vectors in a table' indicates a query/retrieval operation. No side effects, data modification, or deletion mentioned.
Documented attack patterns abuse exactly the kind of access search_vectors gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LanceDB MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_vectors:
{
"version": "1",
"default": "deny",
"tools": {
"search_vectors": {}
}
}search_vectors is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search vectors in a table. It is categorised as a Read tool in the LanceDB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the LanceDB MCP Server MCP server in PolicyLayer and add a rule for search_vectors: 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 MCP Server. Nothing to install.
search_vectors 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_vectors 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_vectors. 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_vectors is provided by the LanceDB MCP Server MCP server (ryanlisse/lancedb_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from LanceDB MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 LanceDB MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.