Production-ready MCP servers for Claude Code — give Claude the tools to browse, read, write, and reason beyond its defaults.
MCP servers extend what Claude can do — not just what it knows. Install a service and Claude gains new capabilities it can use autonomously: controlling a real browser, reading and writing files, structuring its reasoning step by step.
Each service is an MCP (Model Context Protocol) server that Claude Code connects to as an external process. Once installed, Claude picks up the new tools automatically — no extra prompting required.
npx (node)claude)macOS (Homebrew):
brew install node
Nix:
nix profile install nixpkgs#nodejs
Install claude separately: Claude Code installation guide
1. Register the marketplace in ~/.claude/settings.json:
{
"extraKnownMarketplaces": {
"claude-services": {
"source": {
"source": "github",
"repo": "claude-contrib/claude-services"
}
}
}
}
2. Install a service inside Claude Code:
/plugin install playwright@claude-services
Claude now has browser automation tools available in every session.
| Service | Description | Tools unlocked |
|---|---|---|
thinking | Sequential thinking for structured problem analysis | Break down complex problems step by step before acting |
filesystem | Filesystem access beyond the working directory | Read, write, and navigate files across your system |
playwright | Full browser automation via Playwright | Navigate pages, click, fill forms, take screenshots |
Have an MCP server your team relies on? Package it for one-command install:
plugins/your-service/
├── .claude-plugin/plugin.json # name, version, description
├── .mcp.json # server command + args
└── README.md # what it unlocks + install instructions
plugins/.claude-plugin/marketplace.json→ Read the full authoring guide
| Repo | What it provides |
|---|---|
| claude-extensions | Hooks, context rules, session automation |
| claude-features | Devcontainer features for Claude Code and Anthropic tools |
| claude-languages | LSP language servers — completions, diagnostics, hover |
| claude-sandbox | Sandboxed Docker environment for Claude Code |
| claude-services ← you are here | MCP servers — browser, filesystem, sequential thinking |
| claude-skills | Slash commands for Claude Code |
| claude-status | Live status line — context, cost, model, branch, worktree |
MIT — use it, fork it, extend it.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub claude-contrib/claude-services --plugin playwrightFilesystem MCP server for file operations
Sequential thinking MCP server for structured problem analysis
Official Terraform language server
Official Go language server
Rust language server
Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses