MotherDuck MCP connector for AI agents

MotherDuck MCP tools for AI agents

CALL ANY TOOL

12 tools covering ask, create, cancel.

motherduckmcp_ask_docs_question

Query official duckdb and motherduck documentation to answer

Query official duckdb and motherduck documentation to answer questions about sql syntax, features, and best practices.

Parameters

Name

Type

Required

Description

question

string

Required

Question about DuckDB or MotherDuck.

motherduckmcp_cancel_flight_run

Cancel an in-progress flight run. returns an error if the ru

motherduckmcp_create_flight

Create a new flight — a python entrypoint with optional depe

motherduckmcp_delete_dive

Permanently remove a dive from the motherduck workspace. thi

motherduckmcp_delete_flight

Permanently delete a flight, its versions, schedule, and run

motherduckmcp_dive_query

Execute a read-only duckdb sql query on behalf of a dive, at

motherduckmcp_edit_dive_content

Edit a dive's content by applying one or more text replaceme

motherduckmcp_edit_flight_source

Edit a flight's source code through one or more find-and-rep

motherduckmcp_get_dive_guide

Retrieve comprehensive instructions for creating motherduck

motherduckmcp_get_flight

Fetch a flight's metadata and version snapshot by uuid, incl

motherduckmcp_get_flight_guide

Retrieve the authoritative guide for working with motherduck

motherduckmcp_get_flight_run_logs

Fetch the logs and run record for a single flight run, combi

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="motherduckmcp")

mcp = MultiServerMCPClient({
    "motherduckmcp": {
        "url": "https://mcp.scalekit.com/motherduckmcp",
        "headers": {"Authorization": "Bearer " + token}
    }
})
tools = await mcp.get_tools()

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "motherduckmcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/motherduckmcp
// Pass: Authorization: Bearer + token

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "motherduckmcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/motherduckmcp
// Pass: Authorization: Bearer + token

from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="motherduckmcp")
# Connect to MCP at https://mcp.scalekit.com/motherduckmcp
# Pass: Authorization: Bearer + token

Try these prompts

Copy any prompt into your agent. Each maps directly to a MotherDuck tool. Click to copy, paste into your agent, done.

Get started

Copy the prompt

Copied

Render a MotherDuck Dive as a live, interactive MCP app inside the host client?

Copy the prompt

Copied

Update a Flight’s source code, dependencies, config, authentication tokens, secrets, name, or schedule?

Advanced

Copy the prompt

Copied

Make a Dive’s underlying data accessible to your organization by creating org-scoped shares for owned databases referenc?

Copy the prompt

Copied

Fuzzy search across the MotherDuck catalog (databases, schemas, tables, columns, shares) using Jaro-Winkler similarity s?

SEE HOW AUTH WORKS

Your users connect once. Their MotherDuck credentials stay vaulted, every call is scope-checked, and every action is logged.

Authorize

Your user connects

MotherDuck MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

MotherDuck MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

MotherDuck MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

MotherDuck MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other connectors.

ENGINEERING

DevOps assistant agent

Triage GitHub incidents, open Linear tickets, and notify the on-call channel in Slack with context already attached.

ENGINEERING

Auto-release notes agent

Group merged GitHub PRs by feature, fix, or chore and publish release notes per tag. No manual changelog grooming.

GitHub

View agent

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with identity, scope enforcement, and audit. Connectors follow.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential.

// shared token
 audit → bot_service_account

 // scalekit
 audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

One connector today. Ten tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access MotherDuck as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the MotherDuck OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in MotherDuck?
Yes. Pass a tool name filter to listScopedTools so the DevOps agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches MotherDuck.

What happens when a user revokes MotherDuck access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Which databases can DuckDB queries reach?
Only databases in the authorizing user's MotherDuck account. Queries, schema exploration, and visualizations run per user, so shared analytics never leak across tenant boundaries.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit