{
  "markdown": "# Veragent MCP Server\n\n<!-- mcp-name: io.github.lixiaowww/veragent -->\n\nThe trust layer for MCP — as an MCP tool. Let Claude (or any MCP client/agent) check\nwhether an MCP tool is **safe before installing it**, look up the most trusted tools,\nor score an entire MCP stack — all backed by the [Veragent](https://veragent.store)\ntrust registry.\n\n> ⭐ **Star this repo** &nbsp;·&nbsp; `uvx veragent-mcp` — check any tool's trust before you install &nbsp;·&nbsp; **[Get your tool SGC Certified →](https://veragent.store)** &nbsp;·&nbsp; [How we audit (open methodology) →](https://github.com/lixiaowww/veragent-audit)\n\n## Tools\n\n| Tool | What it does |\n|------|--------------|\n| `check_tool_trust(name)` | Veragent trust score + audit state for a tool/server/agent. Use **before** installing. |\n| `list_trusted_tools(query, limit)` | The most trusted MCP tools, optionally filtered. |\n| `scan_mcp_stack(mcp_config)` | Score a whole `mcp_settings.json` — per-server risk + summary. |\n\n## Install (Claude Desktop)\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"veragent\": {\n      \"command\": \"uvx\",\n      \"args\": [\"veragent-mcp\"]\n    }\n  }\n}\n```\n\nThen ask Claude: *\"Is the playwright-mcp server safe? Check Veragent.\"*\n\n## Run locally\n\n```bash\nuvx veragent-mcp\n# or\npip install veragent-mcp && veragent-mcp\n```\n\n## Configuration\n\n- `VERAGENT_API_BASE` — override the API base (default `https://veragent.store/api/v1`).\n\n## Honesty\n\nVeragent labels static-analysis results as **Heuristic** and reserves **SGC Certified**\nfor behavioral-sandbox passes. Scores are reported with this distinction.\n",
  "bytes": 1616,
  "sha": "23a830f709295a9d5ee79435e0bfbbb74cf5fb558ef5efbcffa5b01e49e12ee0",
  "repo_slug": "lixiaowww/veragent-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_lixiaowww_veragent_bd352704/readme"
}