jcus链接休息
带MCP的REST API
如何跑步
选项1：使用run脚本
uv run python run_server.py选项2：直接使用uvicorn
uv run uvicorn src.main:app --host 0.0.0.0 --port 8000 --reload选项3：使用Python模块语法
uv run python -m uvicorn src.main:app --host 0.0.0.0 --port 8000 --reload使用Docker镜像运行
docker build -f Dockerfile -t jcus-rest:latest .
docker run --rm -p 8000:8000 --env-file .env.prod jcus-rest:latestMCP工具示例
FastMCP的流式HTTP传输可以在同一端点上以两种模式进行回复：
- application/json用于正常的json-RPC响应（单个响应体）。
- 用于流式响应和会话事件的文本/事件流。
服务器强制客户端明确声明它可以处理这两种情况，因为它可以根据请求或服务器状态进行选择。这就是为什么它拒绝只接受其中一个请求的原因。 因此：FastMCP流式HTTP要求客户端同时接受 application/json 和 text/event-stream，因此在中包含Accept标头 请求：
以下是您可以发送到的JSON-RPC有效载荷示例 /mcp 对于MCP工具。
开发人员说明
LLM快速建设现在生活在 src/services/resume_service.pyLLM服务 暴露 embed_text, generate_stream_text，以及 generate_text_response 用于嵌入 以及文本生成。
工具
1.1.通过提供文本获得匹配的工作经验
curl -s -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "generate_matched_resume",
"arguments": {
"input_type": "text",
"input_data": "We need a backend engineer with FastAPI and AWS.",
"top_k": 10,
"threshold": 0.5
}
}
}'1.2.通过提供url获得匹配的工作经验
curl -s http://localhost:8001/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "generate_matched_resume",
"arguments": {
"input_type": "url",
"input_data": "https://nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAExternalCareerSite/details/Senior-Software-Engineer--AI-Inference-Systems_JR2008495?q=software&locationHierarchy1=2fcb99c455831013ea529c3b93ba3236",
"top_k": 10,
"threshold": 0.5
}
}
}'1.3通过提供pdf文件获得匹配的工作经验
curl -s -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "generate_matched_resume",
"arguments": {
"input_type": "pdf",
"filename": "job_description.pdf",
"input_data": "", # web app should send like this
"input_data": "JVBERi0xLjQKJcTl8uXr......",
"top_k": 10,
"threshold": 0.5
}
}
}'1.4.通过搜索配置文件表获取相似内容
curl -s -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "search_similar_content",
"arguments": {
"input_text": "API",
"top_k": 10,
"threshold": 0.7
}
}
}'- 生成最新/更新的简历
curl -s -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "search_similar_content",
"arguments": {
"job_description": "We need a backend engineer with FastAPI and AWS.",
"top_k": 5,
"use_cache": true
}
}
}'- 下载最新简历
curl -s -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 3,
"method": "tools/call",
"params": {
"name": "download_latest_resume",
"arguments": {
"use_cache": true
}
}
}'- 使用LRU检查存储简历的缓存状态
curl -s -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 4,
"method": "tools/call",
"params": {
"name": "resume_cache_status",
"arguments": {}
}
}'资源
- 获取所有资源
curl -s -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 9,
"method": "resources/list",
"params": {}
}'- 获取服务器信息
curl -s -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 10,
"method": "resources/read",
"params": {
"uri": "resource://mcp/server-info"
}
}'- 获取提示信息
curl -s -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 11,
"method": "resources/read",
"params": {
"uri": "resource://mcp/prompts"
}
}'- 从资源中获取简历生成提示
curl -s -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 12,
"method": "resources/read",
"params": {
"uri": "resource://mcp/prompts/resume_generation_prompt"
}
}'提示
- 列出所有提示
curl -s -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 5,
"method": "prompts/list",
"params": {}
}'- 获取简历整理提示
curl -s -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 6,
"method": "prompts/get",
"params": {
"name": "resume_generation_prompt",
"arguments": {
"job_description": "We need a backend engineer with FastAPI and AWS.",
"matched_resumes": []
}
}
}'- 获取作业分析提示
curl -s -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 7,
"method": "prompts/get",
"params": {
"name": "job_analysis_prompt",
"arguments": {
"job_description": "We need a backend engineer with FastAPI and AWS."
}
}
}'- 从源提示符获取简历
curl -s -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 8,
"method": "prompts/get",
"params": {
"name": "resume_from_source_prompt",
"arguments": {
"job_description": "We need a backend engineer with FastAPI and AWS.",
"resume_source": {"skills": ["FastAPI", "AWS"]},
"match_summary": {"top_matches": ["FastAPI"]}
}
}
}'