mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-11-01 05:15:22 +08:00
Xiaoyu SuandJunyan Chin
310c566148
* 重构文档结构：移除 docs 目录，调整文件组织结构 * Reorder "插件 SDK API" section in docs.json * Refactor and clarify various documentation sections * Refine warnings and info boxes across multiple docs * Refactor and simplify Japanese documentation content * Update package.json to include mintlify as a dependency and add pnpm-lock.yaml for dependency management * Update blog link and add description in docs.json --------- Co-authored-by: Junyan Chin <[email protected]>
26 lines
1.4 KiB
Plaintext
26 lines
1.4 KiB
Plaintext
---
|
|
title: "MCP Ecosystem Details"
|
|
---
|
|
|
|
The [MCP Protocol](https://modelcontextprotocol.io/) is a protocol that describes the interaction between applications and LLMs, and has been adopted by various products. LangBot can act as an MCP Client to connect to MCP Servers, providing extensive tools for LLMs to use during conversations with users.
|
|
|
|
## Finding MCP Servers
|
|
|
|
To use MCP tools in LangBot, you need to find and connect to existing MCP Servers.
|
|
There are two types of MCP Servers in the market:
|
|
|
|
- Executable files implemented in Node or Python, communicating with LangBot through `stdio` (standard input/output)
|
|
- Web services based on HTTP protocol, communicating with LangBot through HTTP protocol
|
|
|
|
<Info title="- You can check existing MCP Servers in the [MCP Server List](https://github.com/punkpeye/awesome-mcp-servers).">
|
|
- For online hosted MCP Servers, you can find them at [Composio MCP](https://mcp.composio.dev/).
|
|
- To write your own MCP Server, you can refer to the [MCP Protocol Documentation](https://modelcontextprotocol.io/quickstart/server) and [MCP Server Examples](https://modelcontextprotocol.io/examples).
|
|
|
|
</Info>
|
|
|
|
## Configuring MCP Server
|
|
|
|
Please refer to the [System Settings Documentation](/en/deploy/settings.html)
|
|
|
|
After configuration, you can use the `!func` command in chat to view registered MCP tools. When chatting with models that support Function Calling, LangBot will automatically call MCP tools.
|