mcp-workflow -js
一键使用,基于js使用✅ 多协议支持: StreamableHttp MCP协议 ✅ 智能检索: 70%效率提升的代码分析 ✅ 规范完整: 涵盖PRD分析、代码生成、流程图
claude mcp add --transport stdio shaun888-mcp-workflow-mcp-server-js npx -y --registry=http://registry.m.jd.com @jd/fop-workflow-mcp-server
How to use
This MCP server provides an automated, AI-assisted workflow for JD FOP-related projects. It implements a five-stage process: PRD analysis, code generation, flowchart/diagram output, code review, and final verification. The server can perform PRD分析, generate code guided by enhanced workflows, produce business and technical diagrams (including Mermaid sequence diagrams), perform AI-based code reviews for quality, security, and performance, and verify that all required outputs are generated correctly. You can interact with it through natural language prompts like “fop-workflow-mcp-server分析这个PRD” or “fop-workflow-mcp-server生成代码”, and the server will orchestrate the appropriate stages and produce the corresponding artifacts. Core configuration utilities include load_config, get_workflow_config, and show_config_summary to manage and inspect the current workflow settings, while get_smart_retrieval_config and get_file_naming_rules help tailor the analysis and naming conventions to FOP standards. The enhanced code workflow (get_enhanced_code_workflow) analyzes existing code, identifies modification points, proposes and applies changes, and then generates the updated code artifacts. If you need visual representations, the flowchart features can generate business process diagrams, technical architecture diagrams, sequence diagrams, API call graphs, and data flow diagrams.
How to install
Prerequisites\n- Node.js v16 or newer (recommended)\n- npm (comes with Node.js)\n- Access to JD registry: http://registry.m.jd.com\n\nInstallation steps:\n1) Verify Node.js version\nnode -v npm -v\n2) Install the MCP server using the JD internal registry (one-line install):\nnpx -y --registry=http://registry.m.jd.com @jd/fop-work-flow-mcp-server\n3) Configure MCP client to use this server (example):\n { "mcpServers": { "fop-workflow-mcp-server": { "command": "npx", "args": ["-y", "--registry=http://registry.m.jd.com", "@jd/fop-workflow-mcp-server"], "disabled": false, "autoApprove": [] } } } ``\n4) Start or test locally (optional):\n
npm start
\n5) Verify configuration and available steps:\n``` npm run config npm run stage -- --stage stage1_prd_analysis
Additional notes
Tips and notes:\n- This server uses the standard MCP protocol based on the @modelcontextprotocol/sdk. Ensure you have network access to the JD registry for the install.\n- The MCP client configuration supports enabling/disabling servers and auto-approval behavior. Use the autoApprove array to specify automatic approvals for certain outputs if needed.\n- Available stages include PRD analysis, code generation, flowchart/diagram generation, code review, and final verification. Use the provided npm scripts (config, stage, workflow, verify) to inspect settings, run stages, and validate outputs.\n- For diagram outputs, Mermaid-compatible diagrams are supported (sequence diagrams).\n- If you run into registry access issues, ensure the registry URL is reachable from your environment and your network has the necessary permissions.\n- Environment variables can be added under env in mcp_config if you need to customize runtime behavior or credentials.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.