coverage-orchestrator-mcp
Drives test coverage toward target thresholds by coordinating workspace test execution with code-tree-mcp uncovered-symbol analysis.
README
coverage-orchestrator-mcp
A TypeScript MCP server that drives test coverage toward target thresholds by coordinating workspace test execution with code-tree-mcp uncovered-symbol analysis.
What It Does
- ensures workspace coverage tooling exists
- runs tests with coverage and collects failures
- imports LCOV into
code-tree-mcp - fetches uncovered symbols from
code-tree-mcp - ranks the next highest-impact coverage actions
- iterates until thresholds are met or a stop condition is reached
Requirements
- Node.js 20+
- a reachable
code-tree-mcpbinary, typically vianpx code-tree-mcp - a target workspace with a Node-based test runner
Install
npm install
npm run build
Run
One-command server startup after build:
npx coverage-orchestrator-mcp
Run the fixture workflow and call the orchestrator from npx:
npx coverage-orchestrator-mcp implementTestCoverage
Optional target percentage:
npx coverage-orchestrator-mcp implementTestCoverage 90
If the percentage is omitted, this command targets 100% (highest possible target).
During local development:
npm run dev
Setup
Print VS Code MCP configuration:
npx coverage-orchestrator-mcp setup --print-config
Write .vscode/mcp.json in the current working directory:
npx coverage-orchestrator-mcp setup --client vscode
If the current directory is not the workspace you want to update, pass --project-root.
Workspace
This repository tree includes a multi-root workspace file at ../new mc.code-workspace that opens both:
code-tree-mcpcoverage-orchestrator-mcp
Tool Workflow Example
- Call
ensure_coverage_setupfor the target workspace. - Call
run_tests_with_coverage. - Call
fetch_uncovered_code. - Call
verify_coverage_target. - Call
improve_test_coverage_orchestratorfor iterative orchestration.
Troubleshooting
- If
setupcannot write.vscode/mcp.json, rerun with--print-configand copy the JSON manually. - If
code-tree-mcpis not on your path, configure the orchestrator process withCODE_TREE_MCP_COMMANDandCODE_TREE_MCP_ARGS. - If coverage artifacts are missing, confirm the target workspace can run
npm run test:coverageand produces bothcoverage/coverage-summary.jsonandcoverage/lcov.info.
Validation
npm testruns unit coverage helpers, CLI, server routing, and orchestrator-loop tests.npm run test:integrationrebuilds the siblingcode-tree-mcppackage, launches it over stdio, and verifies uncovered-symbol fetching against a real MCP server.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。