I want to build my own MCP server or skill
Skills that write and test custom MCP servers and skills, plus servers to inspect them. Start from code templates rather than empty directories.
MCP servers for this
- MCP server
- Official
Oh My Posh Validator
Oh-my-posh
Validate oh-my-posh configurations and segment snippets against the official schema.
24kActive- Remote
- No auth
- MCP server
Repomix
Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
29kActive- Runs locally
- No auth
- Free
Setup documented for Claude Code, VS Code (GitHub Copilot), Claude Desktop, Cline- MCP server
PraisonAI
PraisonAI
AI Agents Framework with Self Reflection and MCP support
9.3kActive- Runs locally
- API key
- MCP server
Ouroboros
Pins an acceptance spec; the verify command and expected output never enter the success contract.
6.3kActive- Runs locally
- No auth
Setup documented for Claude Code, GitHub Copilot CLI, Codex, Google Antigravity and 3 more- MCP server
- Official
Template MCP Server
Microsoft
Template MCP server example.
3.8kActive- Runs locally
- MCP server
- Official
Compiler Explorer
Compiler Explorer
Compile code with thousands of compilers, inspect the assembly, and share godbolt.org links
19kActive- Remote
- No auth
- MCP server
- Official
Harness
Autonomous
Start Claude Code and Codex agents the person can watch, wait for them and read their answers.
1.4kActive- Runs locally
- No auth
Setup documented for Claude Code, GitHub Copilot CLI, Codex, Cursor and 1 more- MCP server
pm-claude-skills
1310 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.
1.5kActive- Runs locally
- No auth
- Free
Setup documented for Claude Code, Cursor, Windsurf, Cline and 1 more- MCP server
nx-console
Nx
A Model Context Protocol server implementation for Nx
1.4kActive- Runs locally
- No auth
Setup documented for VS Code (GitHub Copilot), Cursor, JetBrains AI and Junie- MCP server
- Official
mockserver
MockServer
Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.
5kActive- Runs locally
- No auth
- MCP server
bernstein
The open-source governance layer for AI agents. Byte-identical run receipts, 40+ adapters, air-gap.
1.3kActive- Runs locally
- No auth
- Free
- MCP server
rsdoctor
Rstack
An MCP server that provides build analysis and optimization recommendations for Rspack projects.
1.2kActive- Runs locally
- No auth
- MCP server
LLM Sandbox
Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
1.1kActive- Runs locally
- No auth
Setup documented for Claude Desktop- MCP server
Agent Skills Search Server
Anthropic
Search and discover Agent Skills from the skills.sh registry. Powered by HAPI MCP server.
27kActive- Remote
- No auth
- MCP server
treg.to
Treg
OpenRouter for tools and data. Compare catalog providers and call them from one hosted MCP endpoint.
6.4kActive- Remote
- API key
- OAuth
- Freemium
Setup documented for Claude Code- MCP server
Claude Code Explorer MCP
Explore the Claude Code CLI source — browse tools, commands, search code, and more.
3.4kActive- Runs locally
- API key
Setup documented for VS Code (GitHub Copilot), Cursor, Claude Desktop- MCP server
- Official
jscpd
Documentation: https://jscpd.dev
6.5kActive- Runs locally
- No auth
- Free
- MCP server
Codeman
Start, prompt and read AI coding agent sessions (Claude Code, Codex, Gemini CLI and more) in Codeman
820Active- Runs locally
- API key
Setup documented for Claude Code, Codex- MCP server
pyscn
Python code analysis for AI agents: complexity, dead code, clones, coupling, and a health score.
1.1kActive- Runs locally
Setup documented for Claude Code- MCP server
SandBase Harness
Stdio MCP bridge for SandBase Harness agents, sessions, turns, artifacts, and cancellation.
636Active- Runs locally
- API key
Setup documented for Cline- MCP server
storybook
Storybook
Storybook addon for MCP-powered UI development workflows.
91kActive- Runs locally
- No auth
Setup documented for Claude Code- MCP server
Concord MCP
Cross-harness communication and shared work-state for AI coding agents.
735Active- Runs locally
Setup documented for Claude Code, Codex, Cursor, Google Antigravity and 2 more- MCP server
token-optimizer-mcp
Context-window optimization: caching, compression & smart file tools that cut tokens 60-90%.
563Active- Runs locally
Setup documented for Claude Code, GitHub Copilot CLI, Codex, Claude Desktop and 2 more- MCP server
- Official
GoModel
EnterPilot
Self-hosted gateway aggregating upstream MCP servers behind one authenticated HTTP endpoint.
1.3kActive- Runs locally
- API key
Skills for this
- Skill
reverse-engineer-anything
Reverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture. Use shipped-artifact or requested runtime evidence to explain features, compare versions…
398kActive- No scripts
- Works offline
Setup documented for Claude Code, Codex- Skill
superpowers (skills)
An agentic skills framework & software development methodology that works.
307kActive- Skill
using-superpowers
This skill establishes a mandatory protocol for agents to identify and invoke relevant skills before performing any action, including responding to questions or exploring code.
307kActive- No scripts
- Works offline
Setup documented for Claude Code, Codex, Google Antigravity- Skill
mattpocock/skills
My agent skills that I use every day to do real engineering - not vibe coding.
305kActive- Bundles scripts
- Needs network
Setup documented for Claude Code, VS Code (GitHub Copilot), GitHub Copilot CLI, Codex and 4 more- Skill
- Official
dummy-dataset
Pawel Huryn
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
27kActive- No scripts
- Works offline
- Skill
- Official
- Featured
mcp-builder
Anthropic
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
184kActive- Plugin
- Needs network
- Skill
- Official
gemini-agents-api
Google Cloud
Manages custom Agent resources on Gemini Enterprise Agent Platform. Use when the user wants to programmatically create, configure, list, update, or delete stateful, server-managed Agent resources (including mounting files, skills, and tools) before executing conversations.
22kActive- No scripts
- Needs network
Setup documented for Google Antigravity- Skill
- Official
gemini-interactions-api
Google
Guides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform. Use when the user wants to use the stateful, server-managed Interactions API for multi-turn conversations, background execution, streaming, structured output, and function calling on the Agent Platform.
22kActive- No scripts
- Needs network
Setup documented for Google Antigravity- Skill
- Official
skill-authoring-workflow
Dean Peters
Turn raw PM content into a compliant, publish-ready skill. Use when creating or updating a repo skill without breaking standards.
7.7kActive- No scripts
- Works offline
- Skill
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
78kActive- Bundles scripts
- Needs network
- Skill
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
78kActive- Bundles scripts
- Works offline
- Skill
- Official
NVIDIA skills
NVIDIA
This folder contains the NVIDIA skills mirrored from product repositories. Each product folder contains one or more skill directories, and each skill directory has a SKILL.md file at its root.
3.8kActive- No scripts
- Needs network
- Skill
tool-design
This skill provides a framework for designing the tool-interface layer of an agent system, focusing on writing unambiguous tool descriptions, schemas, and error recovery messages to improve agent tool selection and performance.
18kActive- Bundles scripts
- Works offline
- Skill
evaluation
This skill provides a framework for building agent evaluation systems, including deterministic checks, regression suites, multi-dimensional rubrics, and production monitoring to measure agent performance and outcomes.
18kActive- Bundles scripts
- Skill
ui-skills
UI Skills
Browse and fetch skills from your terminal.
10kActive- Bundles scripts
- Needs network
- Skill
Vibe-Skills
Vibe Code Orchestrator (VCO) is a governed runtime entry that freezes requirements, bounds execution, and enforces verification and phase cleanup.
3.8kActive- Bundles scripts
- Works offline
Setup documented for Claude Code- Skill
vibe-coding-prompt-template
Copy a prompt, answer its questions, save the result, and move to the next step. You can use a fresh chat for every prompt; attach the saved documents listed below.
3.2kActive- Bundles scripts
- Works offline
Setup documented for Claude Code, Cursor- Skill
markstream-install
Install and wire markstream-vue, markstream-react, markstream-vue2, markstream-angular, or markstream-svelte into an existing repository. Use when Codex needs to choose the right package, install the smallest framework-specific peer-dependency set, fix CSS/reset order, choose Vue 3 renderer mode…
3kActive- No scripts
- Works offline
Setup documented for Codex- Skill
opc-skills
Skills are folders of instructions, scripts, and resources that AI agents load dynamically to improve performance on specialized tasks. Each skill is self-contained with a SKILL.md file containing instructions and metadata.
1.9kActive- Bundles scripts
- Needs network
Setup documented for Claude Code, VS Code (GitHub Copilot), GitHub Copilot CLI, Codex and 4 more- Skill
agmsg
Cross-agent messaging via SQLite. Send messages between Claude Code, Codex, Gemini CLI, and other agents. No network, no dependencies beyond bash and sqlite3, and no daemon required (the optional agmsgd is a local resident service).
1.6kActive- Bundles scripts
- Works offline
Setup documented for Claude Code, Codex, Gemini CLI- Skill
Aegis
Make your AI coding agent trustworthy: fewer reworks, safer changes, proof before "done".
1.4kActive- Bundles scripts
- Needs network
Setup documented for Claude Code, VS Code (GitHub Copilot), GitHub Copilot CLI, Codex and 2 more- Skill
ios-simulator-skill
Production-ready skill for building, testing, and automating iOS apps. 30 scripts optimized for both human developers and AI agents.
1.3kActive- No scripts
- Works offline
Setup documented for Claude Code, Codex- Skill
task-observer
Monitors task execution for skill improvement opportunities: logs patterns, user corrections and methodology worth preserving to the workspace, turns them into skill updates in a weekly review, and flags repeating work as new skills. Use during ANY multi-step task, agentic workflow, or work…
3.6kActive- Bundles scripts
- Works offline
Setup documented for Claude Code- Skill
- Official
vitest-skill
TestMu AI
Generates Vitest tests in JavaScript/TypeScript with Vite-native speed. Jest-compatible API with ESM support and HMR. Use when user mentions "Vitest", "vi.mock", "vitest.config". Triggers on: "Vitest", "vi.mock", "vi.fn", "Vite test", "vitest config".
381Active- No scripts