Files
LangBot/docs/en/deploy/mcp/readme.md
T
e37ab48921 Feat/mcp (#66)
* feat: add zh mcp docs

* fix: error in docs for mcp

* Remove MCP Ecosystem integration link from config

Removed the 'Integrating Complete MCP Ecosystem in LangBot' link and commented it out for future reference.

* perf: add mcp get method

* perf: docs

---------

Co-authored-by: wangcham <[email protected]>
Co-authored-by: Junyan Qin <[email protected]>
2025-11-04 21:35:27 +08:00

38 lines
1.4 KiB
Markdown

# Using MCP Servers
LangBot supports SSE mode MCP servers. You can add MCP servers to leverage the tool calling capabilities in large language models for better handling of LLM requests.
:::info
MCP service only supports SSE mode.
- MCP servers recommended acquisition channel: [Composio MCP](https://mcp.composio.dev/)
:::
## Enable Function Calling for Models
As shown in the image, enable the `Function Calling` feature for the model.
<img width="400px" src="/assets/image/zh/deploy/mcp/mcp_01.png" alt="enable function call" />
## Create MCP Server
Click `Plugin Management`, then `MCP Management`, as shown:
<img width="1000px" src="/assets/image/zh/deploy/mcp/mcp02.png" alt="server page" />
Click `Add` in the top right corner, then `Create MCP Server`,
<img width="400px" src="/assets/image/zh/deploy/mcp/mcp03.png" alt="create new mcp server" />
For example, to use the Fetch HTML server, fill in the corresponding URL, click `Test` to test the MCP server, and click `Submit` to add the server.
After adding, click the switch on the card to connect to the MCP server. Click the card to view the MCP server details:
<img width="400px" src="/assets/image/zh/deploy/mcp/mcp05.png" alt="detailed server" />
## Effect
You need to select `Local Agent` as the runner in the pipeline settings and use a model that supports function calling.
<img width="1000px" src="/assets/image/zh/deploy/mcp/mcp04.png" alt="dialog with mcp" />