mcp_argo_pipeline
MCP server to dispatch Argo WorkflowTemplates according to pipeline configurations, supporting multiple pipelines, authentication, and remote access.
README
mcp_argo_pipeline — 按 Pipeline 调度 Argo WorkflowTemplate 的 MCP
| 文件 | 内容 |
|---|---|
pipelines.yaml |
pipeline、templates、instructions、kubeconfig、port、namespace |
auth.yaml |
各 pipeline 多 Bearer(username / unit) |
入口仅 server.py(通过 MCP_PIPELINE 选择流程)。
快速开始
依赖由 uv 管理(pyproject.toml + uv.lock)。
cd mcp/mcp_argo_pipeline
cp pipelines.yaml.example pipelines.yaml
cp auth.yaml.example auth.yaml
uv sync # 生成/更新 .venv(也可交给 start_serve.sh 自动 sync)
本地 Cursor(stdio)
{
"mcpServers": {
"argo-sirna": {
"command": ".../mcp/mcp_argo_pipeline/.venv/bin/python",
"args": [".../mcp/mcp_argo_pipeline/server.py"],
"env": { "MCP_PIPELINE": "sirna" }
}
}
}
启动时校验 kubeconfig 与模板可访问性;排障可设 MCP_SKIP_STARTUP_CHECKS=1。
服务器
start_serve.sh 启动前会执行 uv sync --frozen(可用 MCP_SKIP_UV_SYNC=1 跳过)。
./start_serve.sh
./start_serve.sh sirna
./start_serve.sh -f enzyme
默认端口(见 pipelines.yaml):affinity 8101、sirna 8102、enzyme 8103。
远程客户端(Streamable HTTP)
服务端强制 Authorization: Bearer <token>,token 来自 auth.yaml(示例见 auth.yaml.example)。将下列片段写入 Cursor 的 mcp.json(~/.cursor/mcp.json 或项目 .cursor/mcp.json),按实际主机改 url。
{
"mcpServers": {
"argo-affinity": {
"url": "http://127.0.0.1:8101/mcp",
"headers": {
"Authorization": "Bearer change-me-affinity-alice"
}
},
"argo-sirna": {
"url": "http://127.0.0.1:8102/mcp",
"headers": {
"Authorization": "Bearer change-me-sirna-carol"
}
},
"argo-enzyme": {
"url": "http://127.0.0.1:8103/mcp",
"headers": {
"Authorization": "Bearer change-me-enzyme-dave"
}
}
}
}
对应示例身份:alice(结构生物学组)、carol(核酸药物组)、dave(酶工程组)。上线请改掉 change-me-*,勿把真实 token 提交仓库;也可用 "Authorization": "Bearer ${env:ARGO_SIRNA_TOKEN}" 从环境变量注入。
pipelines.yaml
pipelines:
sirna:
server_name: argo-sirna
kubeconfig: "~/.kube/config"
port: 8102
instructions: |
...
templates:
- sirna-predict
环境变量
| 变量 | 含义 |
|---|---|
MCP_PIPELINE |
当前 pipeline(必填) |
MCP_PIPELINES_CONFIG |
pipelines.yaml 路径 |
MCP_AUTH_CONFIG |
auth.yaml 路径 |
MCP_TRANSPORT |
stdio / streamable-http |
MCP_SKIP_STARTUP_CHECKS |
1 跳过启动校验 |
MCP_SKIP_UV_SYNC |
1 跳过 uv sync |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.