{
  "markdown": "<p align=\"center\">\n  <img src=\"https://raw.githubusercontent.com/BeBraveBeKind/mcpskills-server/main/assets/og.png\" alt=\"MCP Skills — the pre-install trust layer for MCP servers and AI skills\" width=\"820\">\n</p>\n\n# @mcpskillsio/server\n\nUse the MCPSkills pre-install trust layer from inside Claude Code, Cursor, or any MCP client.\n\n13 standard signals (15 in Skills Mode) across 4 dimensions with safety scanning for prompt injection, credential theft, and supply chain attacks. Check install risk before an MCP server or AI skill reaches your agent.\n\n[![npm version](https://img.shields.io/npm/v/@mcpskillsio/server?logo=npm&color=cb3837)](https://www.npmjs.com/package/@mcpskillsio/server)\n[![MCP Registry](https://img.shields.io/badge/MCP_Registry-io.mcpskills%2Fserver-6E56CF)](https://registry.modelcontextprotocol.io/v0/servers?search=mcpskills)\n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)\n\n[![Add to Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/en/install-mcp?name=mcpskills&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBtY3Bza2lsbHNpby9zZXJ2ZXIiXX0%3D)\n[![Install in VS Code](https://img.shields.io/badge/VS_Code-Install_Server-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=mcpskills&config=%7B%22type%22%3A%22stdio%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40mcpskillsio%2Fserver%22%5D%7D)\n\n## Install\n\n### Claude Code\n\n```bash\nclaude mcp add mcpskills -- npx @mcpskillsio/server\n```\n\n### Cursor\n\nAdd to your `.cursor/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"mcpskills\": {\n      \"command\": \"npx\",\n      \"args\": [\"@mcpskillsio/server\"]\n    }\n  }\n}\n```\n\n### Claude Desktop\n\nAdd to `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"mcpskills\": {\n      \"command\": \"npx\",\n      \"args\": [\"@mcpskillsio/server\"]\n    }\n  }\n}\n```\n\n## Tools\n\n### `check_trust_score`\n\nScore any GitHub repo, npm package, or registry URL. Returns trust tier, composite score, and 4 dimension scores.\n\n```\n\"Score anthropics/anthropic-sdk-typescript\"\n```\n\n### `scan_safety`\n\nFocused safety scan for AI skills. Checks for prompt injection, shell execution, network exfiltration, credential theft, and obfuscated payloads.\n\n```\n\"Is this MCP server safe? modelcontextprotocol/servers\"\n```\n\n### `list_packages`\n\nBrowse curated, pre-scored skill packages organized by use case.\n\n```\n\"Show me safe AI skill packages for full-stack development\"\n```\n\n### `get_badge`\n\nGenerate an SVG trust badge URL for your README.\n\n```\n\"Get a trust badge for my repo anthropics/anthropic-sdk-typescript\"\n```\n\n### `watch_repo`\n\nStart monitoring a repo for trust score changes (requires API key).\n\n```\n\"Watch modelcontextprotocol/servers for score changes\"\n```\n\n### `check_watched`\n\nRe-scan all watched repos for score or tier changes (requires API key).\n\n```\n\"Check my watched repos\"\n```\n\n### `batch_check`\n\nScore up to 5 repos in a single call (Developer Pro or Team).\n\n```\n\"Batch check these repos: anthropics/anthropic-sdk-typescript, langchain-ai/langchainjs\"\n```\n\n### `auto_gate`\n\nGet a boolean go/no-go decision with reasoning.\n\n```\n\"Should I install this MCP server? 21st-dev/magic-mcp\"\n```\n\n### `build_stack`\n\nRecommend a vetted, pre-scored stack from MCP Skills' curated packages.\n\n```\n\"Build me a stack: auth + payments + email\"\n```\n\n## Full Reports\n\nFree tier returns trust tier + dimension scores (same as mcpskills.io free scans, 10/day).\n\nFor full reports (13 standard / 15 Skills Mode signals + safety findings) inside your IDE, set your API key:\n\n```bash\nexport MCPSKILLS_API_KEY=your_key_here\n```\n\nGet your API key at [mcpskills.io/api](https://mcpskills.io/api). Developer Pro is $19/mo or $149/yr. Team is $99/mo for org/security workflows.\n\n## How It Works\n\nThe server calls the mcpskills.io trust scoring API, which:\n\n1. Fetches repo data from GitHub API and OpenSSF Scorecard\n2. Scores 13 standard signals across 4 dimensions (Alive, Legit, Solid, Usable)\n3. Detects AI skills/MCP servers and activates Skills Mode (+2 bonus signals — 15 total)\n4. Runs 5 safety scans based on ClawHavoc and ToxicSkills attack patterns\n5. Assigns a trust tier: Verified (>=7.0), Established (>=4.5), New, or Blocked\n\n## License\n\nMIT — Built by [Michael Browne](https://linkedin.com/in/michaelbrowne03/) at [Rise Above Partners](https://rise-above.net).\n",
  "bytes": 4396,
  "sha": "91dfcc95b866ec32fddbdb57a8db76ac037551ad9cb75f78001109fe66a1f3e1",
  "repo_slug": "bebravebekind/mcpskills-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_mcpskills_server_b7a943d3/readme"
}