开发工具 MCP 服务器

Monitors agent context health: token utilization, context quality degradation and session fatigue, with 0-100 health scores and recovery…

Performance testing with Locust.

iOS code quality and test automation: Xcode test execution, SwiftLint integration and failure analysis. Also runs as a CLI.

Search, install and manage agent skills (SKILL.md files) from GitHub repositories, with workspace analysis for personalized recommendations.

Zero-configuration Go library that exposes existing Echo web framework APIs as MCP tools.

Generate and visualize unified diffs as HTML or PNG, with side-by-side and line-by-line views for filesystem dry runs.

Access CSV files via RestCSV.

Convert any Git repository into a text digest of its codebase using gitingest.

Local code search for agents: symbols, usages, call graph, AST patterns, grep and semantic search

Search, inspect and install Ballmac UI React and Tailwind components, blocks and templates.

Read, write, analyze, test and diff the VBA in Office files, and the document around it

Engineering decisions, change impact, documentation audits, and CI evidence for coding assistants.

Buildable development platform: manage tasks, track progress, get project context and collaborate with humans on software projects.

Conan C/C++ package manager: create projects, manage dependencies, check licenses and scan for security vulnerabilities.

Code-quality gate for Bazel monorepos: runs lint, coverage and architecture checks from the build graph and returns a pass/fail verdict.

GitLab and Jira: manage projects, merge requests, files, releases and tickets.

LynxMCP: 100% local MCP server for the code questions grep can't answer: call graph, hybrid search

MCP server for .NET memory profiling — in-process heap snapshots via EventPipe with leak heuristics

Up-to-date documentation for npm packages, fetched from the latest README in the package's GitHub repository.

Offline Garmin Connect IQ SDK documentation with search and API examples.

Dynamic SOC security threat analysis for a Text2SQL AI agent.

Deployment tracking and monitoring with live status badges.

Offline access to TwitterAPI.io docs for AI assistants. 67 endpoints, 32 pages, 24 blog posts.

iOS development tools: build, run, screenshot and interact with the iOS Simulator.

One list every AI tool you use can write to — scoped per project, local-first, self-hostable.

Godot's own view of your GDScript project: code, scenes, and the running game

A MCP server for TestDino

Explore OpenAPI specs, search endpoints and generate TypeScript types.

Codebeamer ALM: read and write work items, trackers, projects, associations, references, comments and risk management data via the REST API.

Android and iOS runtime inspection and control via Frida: method hooks, state inspection, temporary overrides, UI actions and screenshots.

Trainable non-fiction writing voice, presets, and an anti-AI-tells audit for Claude, via MCP.

Audit public webpages and supplied markup for HTML, CSS, SEO, JSON-LD, and link issues.

The canonical Python stdlib oracle for AI coding agents — always free, always MIT, token-frugal.

Contract-first language and MCP server for capability-aware code and patch review.

Deterministic tech stack recommendations, audits, and project estimates. No hallucinations.

Exposes a catalog of coding assistant system prompts as tools, with model-aware suggestions and persona activation to emulate agents like…

Analyze GitHub repositories' tech stack, dependencies, architecture, health metrics and security indicators with deterministic JSON output.

Prose linter + AI-slop detector: weasel words, passive voice, hedging, and research-cited AI tells

Cryptocurrency tipping using the x402 payment protocol and CDP Wallet.

Create, retrieve and delete webhooks on webhook-test.com.

Validate AI-built front-ends against Figma by tokens and geometry, not pixels.

Call graph for coding agents: callers up to HTTP routes, callees, usages for TS/JS, Go, Python, Java

EN Diagram — structural verification for concurrent systems. Pure math, no AI.

Analyze, audit, fix and diff HTML, MJML, Maizzle and React Email across 21 email clients.

Tracks open-source AI projects across GitHub, PyPI, npm, Hugging Face, Docker Hub and Hacker News for discovery, comparison and trend…

TNL (Typed Natural Language): per-feature English contracts that coding agents can look up, propose edits to and verify implementations…

Auto-download & launch https://github.com/LinuxSuRen/atest-mcp-server

Observability for AI coding: tracks token usage and time, and turns AI deviations into persistent project rules.

Read-only access to Swarmia metrics for quick reporting.

AI coding usage analytics: track spend, model usage and costs across Cursor and Claude Code sessions.

Markdown MCP — search, extract sections, list headings, find code blocks.

Self-hosted webhook relay and tunnel with Noise NK encryption: inspect requests, replay webhooks, trace AI pipelines, manage tunnels and…

Find unused files and APIs in Next.js projects, with project analysis tools exposed over MCP.

Serves task-specific instructions to agents instead of static Markdown files.

Turns repetitive AI interactions into persistent, executable Bash, Python, Node.js or TypeScript scripts.

MCP server for dotnet new: discover, inspect, preview and create .NET projects from templates.

Converts any OpenAPI/Swagger specification into MCP tools automatically.

Let your coding agent see the squiggles — LSP diagnostics, navigation, refactoring, and extras

Git content governance, 23 deterministic MCP tools. Hosted: docs.contentrain.io/developer/mcp-cloud

Keyless local MCP server for QA: standards retrieval, effort estimation, doc review, test analysis.