Model Context Protocol (MCP)

Langdock’s implementation of the Model Context Protocol (MCP) enables seamless integration with external tools and services, providing powerful extensibility for AI agents and chat interactions.

What is MCP?

MCP is an open protocol that standardizes how applications provide context to LLMs.

Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.

MCP integrations in Langdock reuse the existing integration architecture with MCP-specific extensions, allowing the same action execution system to work for both traditional integrations and MCP servers.

Langdock MCP Key Features

Transport Types

• STREAMABLE_HTTP: HTTP-based transport with optional streaming support
• SSE (Server-Sent Events): Real-time communication transport for streaming data

Authentication Methods

• No Authentication: For public MCP servers that don’t require identification
• API Key Authentication: Simplified key-based authentication with automatic header formatting
• OAuth Authentication: Full OAuth 2.0 with DCR support for secure authorization flows
• Advanced OAuth Authentication: Full OAuth 2.0 without DCR support

Tool Integration

Automatic Discovery: MCP tools are automatically converted to Langdock actions, maintaining the same confirmation mechanisms and previews you’re familiar with.

Langdock as an MCP Server

Langdock also provides its own MCP server endpoint, allowing external AI clients to call your Langdock agents.

Langdock Agent MCP Server

Connect external AI clients to your Langdock agents via MCP

Getting Started

Different authentication methods have slightly different connection flows.

1. Enter URL

   Enter the endpoint URL of your MCP server.

2. Select Authentication Method

   Choose one of the four authentication types. Follow the respective guide below:

No Authentication & API Key Authentication

For public or API key-protected servers, simply enter the server URL (and API key if required).

OAuth Authentication

For servers supporting OAuth with PKCE, the connection process is straightforward:

1. Enter the server URL and select OAuth.
2. Click ”+ Add connection” to initiate the OAuth flow.

3. Once connected, a success popup will confirm the connection.
4. Click “Test connection” to verify access and see available tools.

5. Select the tools you want to use, then click “Save tools”

Advanced OAuth Authentication

For servers using OAuth without DCR, the process involves a few extra steps:

1. Enter the server URL and select Advanced OAuth 2.0.
2. Copy the OAuth redirect URL into your app’s API or developer settings.

3. Copy Client ID and Client Secret from your app into Langdock
4. Add Authorization URL (for permissions) and Token URL (for token exchange)
5. Define required OAuth scopes (space or comma-separated per your server’s documentation)

6. Test connection and save tools

---

Zapier MCP Configuration

For Zapier MCP servers, the URL has this format:

https://mcp.zapier.com/api/mcp/s/[your-api-key]/mcp

split your URL as follows:

• Server URL: https://mcp.zapier.com/api/mcp/mcp
• API Key: The encoded string after /s/ in your original URL

---

Related Documentation

• Integrations Overview - Learn about Langdock’s integration system
• Agent Actions - Understanding how actions work with agents

Additional Resources

• General introduction to MCP
• Deep Dive into Protocol Specification