Langbase MCP for AI Agents

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Langbase MCP or direct API to deploy agents, trigger workflows, monitor executions, and manage collaborative AI projects through natural language.

Langbase logoLangbase
Api Key

Langbase is a serverless AI developer platform for building, collaborating, and deploying AI agents and applications. It streamlines composable AI workflows so teams can move fast without infrastructure headaches.

20 Tools

Try Langbase now

Type what you want done — sign in and watch it run live in the Tool Router playground.

TOOL ROUTER PLAYGROUND
Langbase
Try asking
TOOLS

Supported Tools

Every Langbase action and event your agent gets out of the box.

Append Thread Messages

Tool to add new messages to an existing conversation thread.

Check API Health

Tool to check the health status of the Langbase API service.

Split Content into Chunks

Tool to split content into smaller chunks.

Create Thread

Tool to create a new conversation thread.

Delete Thread

Tool to delete a thread that is no longer needed to manage conversation history.

Delete Thread Message

Tool to delete a specific message from a conversation thread.

List Documents in Memory

Tool to list documents in a specific memory.

Get Pipe Details

Tool to retrieve details of a specific pipe by owner and name.

Get Thread Details

Tool to retrieve details of a specific conversation thread.

List Available Models

Tool to get available AI models supported by Langbase.

List Thread Messages

Tool to list all messages in a conversation thread.

List Execution Traces

Tool to get execution traces for debugging and monitoring pipe runs.

Create Memory

Tool to create a new memory.

Delete Memory

Tool to delete a specific memory.

List Memories

Tool to list all memory objects.

Create a new pipe

Tool to create a new pipe.

List all pipes

Tool to list all pipes.

Update an existing pipe

Tool to update an existing pipe's configuration on Langbase.

Update Thread Metadata

Tool to update an existing thread's metadata.

Update Thread Message

Tool to update an existing message in a conversation thread.

SETUP GUIDE

Connect Langbase MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/openai @ai-sdk/mcp
Install the Composio SDK and Claude Agent SDK
2

Create Tool Router Session

typescript
import { Composio } from '@composio/core';

const composio = new Composio({ apiKey: 'your-api-key' });

console.log("Creating Tool Router session...");
const { mcp } = await composio.create('your-user-id');
console.log(`Tool Router session created: ${mcp.url}`);
Initialize the Composio client and create a Tool Router session
3

Connect to AI Agent

typescript
import { openai } from '@ai-sdk/openai';
import { experimental_createMCPClient as createMCPClient } from '@ai-sdk/mcp';
import { generateText, stepCountIs } from 'ai';

const client = await createMCPClient({
  transport: {
    type: 'http',
    url: mcp.url,
    headers: { 'x-api-key': 'your-composio-api-key' }
  }
});

const tools = await client.tools();

const { text } = await generateText({
  model: openai('gpt-4o'),
  tools,
  messages: [{ role: 'user', content: 'List all pipes in Langbase and show their API keys' }],
  stopWhen: stepCountIs( 5 )
});

console.log(`Agent: ${text}`);
Use the MCP server with your AI agent
SETUP GUIDE

Connect Langbase API Tool with your Agent

1

Install Composio

typescript
npm install @composio/openai
Install the Composio SDK
2

Initialize Composio and Create Tool Router Session

typescript
import OpenAI from 'openai';
import { Composio } from '@composio/core';
import { OpenAIResponsesProvider } from '@composio/openai';

const composio = new Composio({
  provider: new OpenAIResponsesProvider(),
});
const openai = new OpenAI({});
const session = await composio.create('your-user-id');
Import and initialize Composio client, then create a Tool Router session
3

Execute Langbase Tools via Tool Router with Your Agent

typescript
const tools = session.tools;
const response = await openai.responses.create({
  model: 'gpt-4.1',
  tools: tools,
  input: [{
    role: 'user',
    content: 'List all memories for project Alpha'
  }],
});
const result = await composio.provider.handleToolCalls(
  'your-user-id',
  response.output
);
console.log(result);
Get tools from Tool Router session and execute Langbase actions with your Agent

Why Use Composio?

AI Native Langbase Integration

  • Supports both Langbase MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable tool execution
  • Rich coverage for deploying, triggering, and monitoring your Langbase AI agents

Managed Auth

  • Built-in API Key handling for secure Langbase access
  • Central place to manage and revoke Langbase credentials
  • Scoped per-user and per-environment credentials for easy rotation

Agent Optimized Design

  • Tools are tuned using real usage data to boost reliability and reduce agent errors
  • Comprehensive logs so you always know which agent deployed, triggered, or monitored which app

Enterprise Grade Security

  • Fine-grained RBAC to control which agents and users can access which Langbase projects
  • Scoped, least privilege access to Langbase deployments and APIs
  • Full audit trail of agent actions for review and compliance
FAQ

Frequently asked questions

Yes, Langbase requires you to configure your own API key credentials. Once set up, Composio handles secure credential storage and API request handling for you.

Yes! Composio's Tool Router enables agents to use multiple toolkits. Learn more.

Composio is SOC 2 and ISO 27001 compliant with all data encrypted in transit and at rest. Learn more.

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

Start with Langbase.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Langbase tool your agent needs.Free to start.

Start building