// SCAN REPORT

LanceDB Node

3 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 5 Jul 2026

1 can modify or destroy data

2 read-only

3 tools total

Community server · catalogue entry verified 05/07/2026

How to control LanceDB Node ↓

TOOL MAP

What LanceDB Node exposes to your agents

Read (2) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous LanceDB Node tools

Write · Medium vector_add This tool creates or modifies data in a vector database in a reversible manner.

1 of LanceDB Node's 3 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control LanceDB Node

PolicyLayer is an MCP gateway — it sits between your AI agents and LanceDB Node, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "vector_add": {
    "limits": [
      {
        "counter": "vector_add_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "list_tables": {
    "limits": [
      {
        "counter": "list_tables_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register LanceDB Node — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON LANCEDB NODE →

Instant setup, no code required.

FULL CATALOGUE

All 3 LanceDB Node tools

WRITE 1 tools

Write vector_add Add vectors with metadata to a LanceDB table. Creates the table if it doesn

READ 2 tools

Read list_tables List all tables in the LanceDB database. Read vector_search Search for similar vectors in a LanceDB table using either a direct vector or text that will be converted to a

FAQ

Questions about LanceDB Node

How do I prevent bulk modifications through LanceDB Node? +

The LanceDB Node server has 1 write tools including vector_add. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach LanceDB Node.

How many tools does the LanceDB Node MCP server expose? +

3 tools across 2 categories: Read, Write. 2 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on LanceDB Node? +

Register the LanceDB Node MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every LanceDB Node tool call.

Deterministic rules across all 3 LanceDB Node tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LANCEDB NODE →

Instant setup, no code required.

3 LanceDB Node tools catalogued and risk-classified — across an index of 43,000+ MCP servers.