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.
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.
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.
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.
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.