GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Descripción del creador (original en inglés)
AI agent discovers MCP servers from GitHub npm - analyzes APIs configs
Estos tres nunca se combinan en una sola puntuación: las opiniones, las mediciones y la popularidad son cosas distintas.
Todavía no escribimos un resumen sencillo para este. Abajo están los datos que leímos del registro.
Elige la app de IA que usas y copia la configuración.
El creador no incluyó detalles de instalación en el registro. Consulta el README del creador más abajo.
Se ejecuta en tu computadora; la lista de herramientas aparece en tu app de IA después de instalarlo.
Revisamos información que cualquiera puede ver; no hemos leído el código. Las revisiones que no aplican no se cuentan. · Revisado el 7 nov 2026
El nombre en el registro se verificó con la cuenta de GitHub nirholas, dueña del repo
Todavía no hemos leído este repo en GitHub
Todavía no hemos leído este repo en GitHub
Este se ejecuta en tu computadora; no hay endpoint en internet
Se ejecuta en tu computadora y usa ajustes locales en su lugar
Se ejecuta en tu computadora; solo podemos leer listas de herramientas de endpoints en internet
Comparado con todos los servidores activos de esta categoría en el registro. Las estrellas solo cuentan cuando quien lo publica es dueño del repo.
Superó 1 de 1 revisiones básicas aplicables. No hemos leído el código. Antes de agregar una clave o un token, revisa qué acceso pide el servidor y usa una clave que tenga solo los permisos que necesitas.
El registro no indica ninguna clave obligatoria, aunque algunos servidores te piden iniciar sesión la primera vez que los usas.
Se ejecuta en tu computadora. Tu app de IA lo inicia cuando hace falta, y los datos no pasan por los servidores del creador (a menos que el propio servidor llame a un servicio en línea).
El repo de GitHub cambió por última vez –, y la última versión (1.0.0) llegó al registro hace 10 meses.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code.
En la misma categoría: GitHub, Desktop Commander, Cloudflare MCP
Servidores de la misma categoría hechos por otros creadores, ordenados por estrellas.
Cómo leer una tarjeta:★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
Copiado tal cual del repo del creador. PopNx MCP no lo ha revisado ni lo respalda. Se quitaron HTML, imágenes y scripts. Los enlaces llevan fuera de este sitio.
AI-powered tool discovery for the MCP ecosystem
Documentation · CLI Reference · Examples · Contributing
Lyra Tool Discovery is an AI-powered automation tool designed specifically for the crypto, DeFi, blockchain, and web3 ecosystem. It solves the painful problem of manually discovering, evaluating, and integrating MCP (Model Context Protocol) servers into your crypto-focused applications. Instead of spending hours searching GitHub, reading READMEs, and figuring out the right integration approach, Lyra does it for you in seconds.
The tool crawls multiple sources—GitHub and npm—to find crypto-related MCP servers, APIs, and plugins. It filters results to focus exclusively on blockchain, DeFi, web3, and cryptocurrency tooling (including Ethereum, Solana, Bitcoin, wallets, tokens, NFTs, DEXs, staking, bridges, and more). Lyra then leverages state-of-the-art AI (OpenAI GPT-4o or Anthropic Claude) to analyze each discovered tool and automatically generates ready-to-use plugin configurations.
Lyra is optimized for discovering tools related to:
Lyra is built for crypto MCP ecosystem developers who need to rapidly onboard new tools, plugin marketplace operators like plugin.delivery who curate crypto plugins, and automation engineers building CI/CD pipelines for DeFi tool discovery and deployment.
This tool is a critical piece of the discovery-to-deployment pipeline: lyra-tool-discovery → github-to-mcp → plugin.delivery → SperaxOS users. By automating the discovery and classification phase, Lyra enables fully automated plugin onboarding with minimal human intervention.
mcp-http — Remote MCP servers (HTTP/SSE)mcp-stdio — Local MCP servers (stdio)openapi — REST API integrationsstandalone — Full React applicationsmarkdown — Rich text/documentationdefault — Configurable pluginssettings — User preference pluginsbasic — Simple function plugins--dry-run mode for safe testingLyra automatically filters discovery results to focus on crypto/DeFi/blockchain/web3 tools. The following keywords are used for both search queries and result validation:
View all supported keywords
| Category | Keywords |
|---|---|
| General | crypto, cryptocurrency, defi, blockchain, web3 |
| Networks | ethereum, eth, solana, sol, bitcoin, btc, chain |
| Tokens | token, erc20, erc721, nft |
| DeFi | dex, swap, staking, yield, lending, liquidity, vault, bridge |
| Infrastructure | wallet, protocol, onchain, on-chain, smart contract |
| Libraries | web3.js, ethers, viem, wagmi, rainbowkit |
| Protocols | uniswap, aave, compound |
Tools that don't match any of these keywords are automatically filtered out, ensuring you only discover crypto-relevant MCP servers.
By default, Lyra only discovers tools that have been updated within the last 12 months. This ensures you're finding actively maintained projects. Use --max-age to adjust:
# Only tools updated in the last 6 months
lyra-discover discover --max-age 6
lyra-discover discover --max-age 3
lyra-discover discover --max-age 24
# Global install (recommended for CLI usage)
pnpm add -g @nirholas/lyra-tool-discovery
npm install -g @nirholas/lyra-tool-discovery
pnpm add @nirholas/lyra-tool-discovery
npx @nirholas/lyra-tool-discovery discover --help
# Using OpenAI (default when both keys present)
export OPENAI_API_KEY="sk-..."
export ANTHROPIC_API_KEY="sk-ant-..."
export AI_PROVIDER="anthropic" # or "openai"
export AI_MODEL="claude-sonnet-4-20250514"
export GITHUB_TOKEN="ghp_..."
# Discover MCP servers from GitHub and npm
lyra-discover discover --sources github,npm --limit 10
lyra-discover discover --dry-run --limit 20
lyra-discover analyze-repo anthropics claude-mcp
lyra-discover analyze-npm @modelcontextprotocol/server-github
lyra-discover providers
lyra-discover templates
| Flag | Alias | Description | Default |
|---|---|---|---|
--provider | -p | AI provider (openai or anthropic) | Auto-detect from env |
--model | -m | AI model to use | Provider default |
--version | -V | Show version number | — |
--help | -h | Show help | — |
discoverSearch for MCP tools and APIs across configured sources.
lyra-discover discover [options]
| Option | Alias | Description | Default |
|---|---|---|---|
--sources | -s | Comma-separated sources: github, npm, awesome-list | github,npm |
--limit | -l | Maximum tools to discover per source | 5 |
--max-age | -a | Maximum age in months for discovered repos | 12 |
--dry-run | -d | List tools without AI analysis | false |
--provider | -p | AI provider to use | Auto-detect |
--model | -m | AI model to use | Provider default |
Examples:
# Discover crypto MCP tools from GitHub only, limit 10 results
lyra-discover discover --sources github --limit 10
lyra-discover discover --max-age 6 --limit 20
lyra-discover discover --dry-run --sources npm --limit 20
lyra-discover discover --provider anthropic --model claude-sonnet-4-20250514
lyra-discover discover --provider openai --model gpt-4o
Example Output:
🔍 Discovering crypto/DeFi/web3 tools from: github, npm
📅 Max age: 12 months Found 5 from github Found 3 from npm
📊 Total discovered: 8 tools 🪙 Crypto-related: 6 tools 🔌 MCP-compatible: 5 tools
🤖 Analyzing: mcp-server-ethereum... Template: mcp-stdio Reasoning: Has MCP SDK dependency and bin entry for local execution
✅ Analyzed 5 tools
📦 Generated Configs:
--- mcp-server-ethereum --- Template: mcp-stdio Config: { "identifier": "mcp-server-ethereum", "customParams": { "mcp": { "type": "stdio", "command": "npx", "args": ["-y", "mcp-server-ethereum"] } } }
analyze-repoAnalyze a specific GitHub repository.
lyra-discover analyze-repo <owner> <repo> [options]
| Argument | Description |
|---|---|
owner | GitHub repository owner/organization |
repo | Repository name |
| Option | Alias | Description |
|---|---|---|
--provider | -p | AI provider to use |
--model | -m | AI model to use |
Examples:
# Analyze the official MCP GitHub server
lyra-discover analyze-repo modelcontextprotocol servers
lyra-discover analyze-repo anthropics claude-mcp --model gpt-4o
lyra-discover analyze-repo punkpeye mcp-server-obsidian
Example Output:
🔍 Fetching modelcontextprotocol/servers...
🤖 Analyzing...
✅ Analysis complete: Template: mcp-stdio Reasoning: Repository contains multiple MCP servers with bin entries, using @modelcontextprotocol/sdk
📋 Quick Import JSON: { "mcpServers": { "github": { "command": "npx", "args": ["-y", "@modelcontextprotocol/server-github"] } } }
analyze-npmAnalyze a specific npm package.
lyra-discover analyze-npm <package> [options]
| Argument | Description |
|---|---|
package | npm package name (with or without scope) |
| Option | Alias | Description |
|---|---|---|
--provider | -p | AI provider to use |
--model | -m | AI model to use |
Examples:
# Analyze official MCP server packages
lyra-discover analyze-npm @modelcontextprotocol/server-github lyra-discover analyze-npm @modelcontextprotocol/server-filesystem lyra-discover analyze-npm @modelcontextprotocol/server-slack
lyra-discover analyze-npm mcp-server-sqlite
providersShow available AI providers based on configured environment variables.
lyra-discover providers
Example Output (with keys configured):
🤖 AI Provider Configuration
Available providers (based on env vars): ✅ openai ✅ anthropic
Override with env vars or CLI flags: AI_PROVIDER=openai|anthropic AI_MODEL=gpt-4o|claude-sonnet-4-20250514|etc. --provider openai --model gpt-4o
Example Output (no keys):
🤖 AI Provider Configuration
Available providers (based on env vars): ⚠️ No API keys found!
Set one of these environment variables:
Solo se muestra el principio; lee el resto en el repo