{
  "markdown": "# HVTracker MCP\n\n[![Smithery](https://img.shields.io/badge/Smithery-hvtracker--mcp-blue)](https://smithery.ai/servers/hvtracker/hvtracker-mcp)\n[![npm](https://img.shields.io/npm/v/hvtracker-mcp)](https://www.npmjs.com/package/hvtracker-mcp) [![PyPI](https://img.shields.io/pypi/v/hvtracker-mcp)](https://pypi.org/project/hvtracker-mcp/) [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n\nMCP server for checking supply-chain trust before connecting to AI agents,\nframeworks, or MCP servers.\n\nThe hosted remote server is:\n\n```json\n{\n  \"mcpServers\": {\n    \"hvtracker\": {\n      \"url\": \"https://hvtracker.net/mcp\"\n    }\n  }\n}\n```\n\nThis repository also provides a local stdio package for clients that prefer\npackage-based installation.\n\n<!-- mcp-name: io.github.YugantM/hvtracker-mcp -->\n\n## Tools\n\n- `verify_mcp_server`: pre-connect trust verdict for an MCP server, package, GitHub repo, or agent name.\n- `check_agent_trust`: trust profile for a tracked AI agent or framework — incl. runtime capabilities (MCP status, providers, plugin surface, provenance drift) and the URL of its Ed25519-signed trust credential.\n- `compare_agents`: two agents side by side with an evidence-based verdict and the published compare-page link.\n- `search_agents`: search the HVTracker registry by name, repo, description, or category.\n- `scan_stack`: bulk pre-connect trust check for a whole dependency set — paste a requirements.txt, package.json, MCP client config, or a plain list and get a trust verdict per item plus a stack summary.\n- `list_categories`: list the HVTracker categories with agent counts, so you can then pull a category's leaderboard.\n- `get_leaderboard`: top tracked AI agents and MCP servers ranked by HVTrust score, optionally filtered to one category.\n- `get_agent_history`: 90-day trust-score, grade, and rank history for one tracked agent — is it improving or declining?\n\n## Local Install\n\nWith npm:\n\n```bash\nnpm install -g hvtracker-mcp\n```\n\nWith PyPI:\n\n```bash\npython3 -m pip install hvtracker-mcp\n```\n\nExample MCP client config:\n\n```json\n{\n  \"mcpServers\": {\n    \"hvtracker\": {\n      \"command\": \"hvtracker-mcp\"\n    }\n  }\n}\n```\n\n## Development\n\n```bash\npython3 -m pip install -e \".[dev]\"\npython3 -m pytest\nhvtracker-mcp\n```\n\nUse a different HVTracker base URL while testing:\n\n```bash\nHVTRACKER_BASE_URL=http://localhost:8080 hvtracker-mcp\n```\n\n## Registry Publishing\n\nThe official MCP Registry manifest is `server.json`.\n\n```bash\nmcp-publisher login github\nmcp-publisher publish\n```\n\nIn GitHub Actions, run the \"Publish MCP Registry\" workflow after the npm,\nPyPI, and GHCR packages for the same version are live.\n\nThe server name is:\n\n```text\nio.github.YugantM/hvtracker-mcp\n```\n\n## Claude Desktop Extension\n\nTagged releases build an `.mcpb` bundle for Claude Desktop from `manifest.json`.\nTo build it locally:\n\n```bash\nnpm ci --omit=dev\nnpx @anthropic-ai/mcpb@2.1.2 pack\n```\n\n## Privacy\n\nHVTracker MCP sends the user-supplied search string or server identifier to\n`https://hvtracker.net` to fetch public trust data. It does not require an API\nkey and does not write to user systems. See the HVTracker site for current data\nand methodology, and see `PRIVACY.md` for the repository privacy note.\n",
  "bytes": 3229,
  "sha": "1a9c0280a133a764685e34b2dccde830bd1a7fc67efe56eccb650f05ff9308ab",
  "repo_slug": "yugantm/hvtracker-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_yugantm_hvtracker_mcp_7b725fc9/readme"
}