RAGFlow API MCP Server,您可以搜索知识库并进行聊天。
下载MCP开发文档和RAGFlow API参考:
wget https://modelcontextprotocol.io/llms-full.txt -O docs/mcp-llms-full.txt
wget https://github.com/infiniflow/ragflow/raw/refs/heads/main/docs/references/python_api_reference.md -O docs/ragflow-python_api_reference.md
list_datasets
create_chat
chat
[TODO: 添加特定于您实现的配置详情]
.vscode/mcp.json
{
"servers": {
"ragflow-mcp-server": {
"command": "uvx",
"args": [
"ragflow-mcp-server",
"--api-key=ragflow-dhMzViYzJlMTM1NjExZjBiNWU5MDI0Mm",
"--base-url=http://172.16.33.66:8060"
]
}
}
}
config.yaml
mcpServers:
- name: RAGFlow Server
command: uvx
args:
- ragflow-mcp-server
- --api-key
- ragflow-dhMzViYzJlMTM1NjExZjBiNWU5MDI0Mm
- --base-url
- http://172.16.33.66:8060
在MacOS上:~/Library/Application\ Support/Claude/claude_desktop_config.json
在Windows上:%APPDATA%/Claude/claude_desktop_config.json
为了准备分发包:
uv sync
uv build
这将在dist/目录中创建源和轮子分布。
uv publish
注意:您需要通过环境变量或命令标志设置PyPI凭证:
--token 或 UV_PUBLISH_TOKEN--username/UV_PUBLISH_USERNAME 和 --password/UV_PUBLISH_PASSWORD由于MCP服务器通过标准输入输出运行,调试可能会很困难。为了获得最佳的调试体验,我们强烈建议使用MCP Inspector。
您可以通过以下命令使用npm启动MCP Inspector:
npx @modelcontextprotocol/inspector \
uv --directory /Users/junjian/GitHub/wang-junjian/ragflow-mc