Mcpbuilder Ai

mcpbuilder-ai

Connect your apps to AI-powered MCP servers — in minutes, not months.

mcpbuilder-ai is the official SDK for MCP-Builder.ai, available for both Python and TypeScript. Stream chat responses, execute tools with consent handling, and manage authentication — all through a clean, callback-driven API over WebSockets.

Build your MCP server on the MCP-Builder.ai dashboard, grab your project token, and start talking to it from any app with just a few lines of code.

---

How It Works

┌─────────────────────┐         ┌──────────────────────────┐
│   Your Application  │  SDK    │   MCP-Builder.ai Cloud   │
│                     │ ─────►  │                          │
│  - Web frontend     │  WS     │  - MCP Server you built  │
│  - CLI tool         │ ◄─────  │  - Tool execution        │
│  - Backend service  │         │  - LLM orchestration     │
└─────────────────────┘         └──────────────────────────┘

1. Design your MCP server on mcp-builder.ai — configure tools, connect APIs, set up authentication.
2. Install the SDK (pip install mcpbuilder-ai / npm install mcpbuilder-ai).
3. Connect with your project token and deployment name.
4. Chat — stream tokens in real time, handle tool calls, manage consent flows.

---

Features

| | Python | TypeScript | |---|---|---| | Real-time token streaming | ✅ | ✅ | | Fluent callback API | ✅ | ✅ | | Tool consent handling | ✅ | ✅ | | Auto-reconnect with backoff | ✅ | ✅ | | Session & history management | ✅ | ✅ | | Security parameter overrides | ✅ | ✅ | | Full type safety | ✅ (type hints) | ✅ (TypeScript generics) | | ESM + CommonJS | — | ✅ |

---

Quick Start

TypeScript

npm install mcpbuilder-ai

import { MCPChatClient } from 'mcpbuilder-ai';

const client = new MCPChatClient({
  projectToken: 'your-project-token',
  deploymentName: 'my-deployment',
  cacheHistory: false,
});

client
  .onToken((token) => process.stdout.write(token))
  .onFinal((text, toolCalls) => console.log('\nDone!'))
  .onError((error) => console.error('Error:', error));

await client.connect();
await client.sendMessage('Hello, what can you do?');

Python

pip install mcpbuilder-ai

import asyncio
from mcpbuilder import MCPChatClient

async def main():
    client = MCPChatClient(
        project_token="your-project-token",
        deployment_name="my-deployment",
        cache_history=False,
    )

    client \
        .on_token(lambda t: print(t, end="", flush=True)) \
        .on_final(lambda text, tc: print("\nDone!")) \
        .on_error(lambda msg: print(f"Error: {msg}"))

    await client.connect()
    await client.send_message("Hello, what can you do?")

asyncio.run(main())

---

SDK Documentation

| SDK | Package | Docs | |-----|---------|------| | TypeScript | mcpbuilder-ai on npm | [TypeScript README](./typescript-sdk/README.md) | | Python | mcpbuilder-ai on PyPI | [Python README](./python-sdk/README.md) |

---

Integration Examples

The [examples](./examples/) directory contains ready-to-run projects showing how to connect to MCP servers built on MCP-Builder.ai:

| Example | Language | Description | |---------|----------|-------------| | [React MCP Chat](./examples/typescript/react-mcp-chat/) | TypeScript | React-based chat UI with streaming + tool consent | | [Simple Python CLI](./examples/python/simple-python-cli/) | Python | Terminal chat client with live token streaming |

> New to MCP-Builder.ai? Check the [Getting Started guide](./docs/getting-started.md) to create your first project and grab a project token.

---

Getting Started with MCP-Builder.ai

1. Sign up at mcp-builder.ai and open the dashboard.
2. Create a project — define your tools, connect external APIs, and configure authentication.
3. Deploy your MCP server with one click.
4. Copy the project token and deployment name from the dashboard.
5. Install the SDK and paste the credentials into your app — you're live.

---

Contributing

Contributions are welcome! Feel free to open issues or submit pull requests.

License

Apache-2.0 — see [LICENSE] for details.

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: MCP-Builder-ai
• Source: MCP-Builder-ai/mcpbuilder-ai
• License: Apache-2.0

Install and usage instructions live in the source repository linked above.