How to Use the Turso MCP in LangChain

Q: How does Turso help with LangChain database provisioning?

The createdatabase tool lets your AI client provision a new, distributed libSQL database right within the chain. It requires you to pass the organization slug, database name, and target group for setup.

Q: Can I audit token usage in my LangChain workflows using Turso?

Yes, your agent can use listdatabasetokens to see all active JWT tokens. You'll also find tools like listorganizations to understand the root tenant structure where those databases live.

Q: What is the best way to track database changes with Turso and LangChain?

You should chain together listdatabases and getdatabasedetails. This pattern allows your agent to check existing state before running a write operation, preventing accidental data loss.

Build multi-step reasoning agents that manage distributed databases with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Turso MCP to LangChain

Create your Vinkius account to connect Turso to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Turso with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage DB State in Chains

The `create_database` tool lets your agent provision a new, massively distributed Serverless SQLite database using just the organization slug, name, and target group. Your multi-step reasoning pipeline can then immediately use `list_databases` to confirm the creation. Since every MCP tool call is a link in the chain, you'll get full visibility into how your agent manages database lifecycle operations.

Secure Token Management

Need secure access for a specific job? Use `create_database_token` to mint a connection JWT tied only to one target DB. This keeps credentials isolated, which is critical for complex chains. The agent can also call `list_database_tokens` or, if necessary, `rotate_database_tokens` to revoke all old tokens across an entire database instance. It's built for controlled data access.

Systematic DB Discovery

To figure out what databases exist in your environment, the agent calls `list_databases`, which enumerates the complete libSQL Edge Database registry. Furthermore, you can use `get_database_details` to inspect specific architectural traits of any target instance. This allows your ReAct agent to make informed decisions about where and how it should run its next query.

Setup guide

Set up Turso MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Turso tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "turso-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Turso transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Turso. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Turso now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Turso MCP in LangChain

The `create_database` tool lets your AI client provision a new, distributed libSQL database right within the chain. It requires you to pass the organization slug, database name, and target group for setup.

Yes, your agent can use `list_database_tokens` to see all active JWT tokens. You'll also find tools like `list_organizations` to understand the root tenant structure where those databases live.

This MCP Server handles core database metadata, including full libSQL Edge Database registry entries and secure `Database Connection Tokens`. It's all about managing the state of your distributed databases.

Yes. The underlying MCP Server supports aggregating tools from multiple sources, letting you build larger, more complex agent pipelines that touch several data backends.

You should chain together `list_databases` and `get_database_details`. This pattern allows your agent to check existing state before running a write operation, preventing accidental data loss.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript