Developer Productivity MCP
Developer Productivity MCP
一个 FastMCP 服务器,将 GitHub、Jira 和工程指标能力 作为 MCP 工具暴露,外加一个 OpenAI Agents SDK 客户端,将它们作为多步骤 工作流驱动。
┌──────────────────┐
│ User │
└────────┬─────────┘
│
▼
┌──────────────────┐
│ OpenAI Agent │
│ Agents SDK │
└────────┬─────────┘
│
MCP Protocol
│
▼
┌─────────────────────────┐
│ FastMCP Server │
│ │
│ search_github_code │
│ get_jira_sprint_status │
│ analyze_pull_request │
│ query_project_metrics │
└──────┬──────┬──────┬────┘
│ │ │
GitHub API Jira PostgreSQL模型从不直接与 GitHub、Jira 或 PostgreSQL 通信。MCP 服务器 负责凭据、分页、错误处理和响应整形,并 返回事实;代理贡献推理和解释。因此,说明性文本 不是工具——解释工具会把判断推入 服务器,而服务器无法看到其他工具的结果。
四个工具
工具 | 后端 | 除了包装 API 之外的功能 |
| GitHub REST | 将搜索结果规范化为 |
| Jira Agile | 完成百分比、故事点进度、阻塞/高优先级/逾期/未分配/有风险工单、冲刺风险等级 |
| GitHub REST | 对 diff 进行静态分析:安全、数据库、API 契约、依赖和测试检测;删除代码分析;评分风险等级;破坏性变更和审查建议 |
| PostgreSQL | 由允许列表保护的六个指标——模型选择指标名称,绝不编写 SQL |
Related MCP server: GitHub Dev Copilot
布局
.
├── main.py # agent-side CLI entry point
├── .env.example
├── agent/
│ ├── developer_agent.py # agent definitions + instructions
│ └── workflows.py # multi-step agentic workflows
├── src/
│ ├── config.py # MCP server environment
│ ├── pr_analysis.py # PR static-analysis helpers
│ └── server.py # FastMCP server + the four tools
└── sql/
└── schema.sql # tables backing query_project_metrics设置
uv sync
cp .env.example .env # then fill in your credentials
psql "$DATABASE_URL" -f sql/schema.sql运行
终端 1 — MCP 服务器(Streamable HTTP,位于 http://localhost:8000/mcp):
uv run python -m src.server终端 2 — 一个代理工作流:
# GitHub code search
uv run python main.py search --repository my-org/payments-api --query retry
# pull-request risk analysis
uv run python main.py pr --repository my-org/payments-api --number 142
# the full multi-tool sprint investigation
uv run python main.py sprint --project PAY --sprint 42MCP_TRANSPORT=stdio 改为通过 stdio 运行服务器,适用于客户端
将其作为子进程启动。
代理工作流
main.py sprint 提出一个自然语言问题,代理决定调用哪些
工具以及调用顺序:
1. get_jira_sprint_status()
↓
2. Agent selects the tickets worth investigating
↓
3. search_github_code()
↓
4. analyze_pull_request()
↓
5. query_project_metrics()
↓
6. Agent generates explanation第 2 步不需要工具调用。get_jira_sprint_status 已经掌握了所有问题,
因此阻塞/高优先级/逾期的分类在那里完成,代理
根据返回的 blocked_tickets 和 high_priority_tickets 进行推理,
以决定下一步查看什么。将其拆分为第二次往返会多消耗
一次请求,且毫无收益。
设计说明
analyze_pull_request根据文件名、diff 补丁和模式匹配来评估风险, 而不是由 LLM 阅读代码。它廉价、确定性高且可复现; 对最高风险补丁进行 LLM 审查阶段是 计划中的扩展。Jira 故事点自定义字段 ID 和看板 ID 因安装而异,因此
JIRA_BOARD_ID和JIRA_STORY_POINTS_FIELD是配置项而非 常量。query_project_metrics读取sql/schema.sql中的表,这些表期望有 一个摄取作业加载 GitHub/Jira/CD 历史。
This server cannot be deployed
Maintenance
Related MCP Connectors
Search GitHub, npm, PyPI, StackOverflow, ArXiv from one MCP — built for coding agents.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
AI-native git hosting — repos, PRs, issues, CI gates, and AI code review over MCP (60 tools).
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Related MCP Servers
- AlicenseBqualityCmaintenanceMCP server that exposes GitHub operations as tools for AI agents, enabling code search, issue management, and PR review.12MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to interact with GitHub via MCP, managing repositories, issues, PRs, and analyzing repository health through tools like list_repositories, read_issues, create_issue, comment_on_pr, and analyze_repo_health.-
- FlicenseNot gradedqualityCmaintenanceEnables natural-language analysis of GitHub repositories by exposing repository metadata, source code retrieval, search, and file reading as MCP tools, with answers grounded in the actual repository content.-
- AlicenseNot gradedqualityCmaintenanceProvides MCP tools for fetching GitHub PR diffs, searching codebases, running unit tests, and linting code, enabling automated code review and CI/CD workflows.MIT