{
  "markdown": "# @afferens/mcp-server\n\nMCP server for [Afferens](https://afferens.com) - real-time physical perception for AI agents.\n\nUse it from local MCP clients over stdio or remote/hosted clients over streamable HTTP. It gives any MCP-compatible AI assistant live sensor data: object detections, positions, sounds, environmental readings, chemical traces, and node health.\n\n## Tools\n\n| Tool | Auth | Description |\n|------|------|-------------|\n| `afferens_demo` | None | Live perception data across all 6 modalities. Free, no key needed. |\n| `afferens_perceive` | API key | Query live events by modality with filtering and limits. |\n| `afferens_verify` | API key | Fetch the feed twice and return a proof bundle with headers, age, and a freshness verdict. |\n\n**Modalities:** `VISION` / `SPATIAL` / `ACOUSTIC` / `ENVIRONMENTAL` / `MOLECULAR` / `INTEROCEPTION`\n\n## Quick Start\n\nFree tier: 10,000 tokens, no card required. Get your key at [afferens.com](https://afferens.com).\n\n### Local MCP Clients\n\n```bash\nclaude mcp add afferens -- npx -y @afferens/mcp-server\n```\n\nThen set your key:\n\n```bash\nclaude mcp add afferens -e AFFERENS_API_KEY=YOUR_KEY -- npx -y @afferens/mcp-server\n```\n\nThis stdio setup works for Claude Code, Claude Desktop, Cursor, and Windsurf.\n\n### Remote MCP Clients\n\nFor hosted or browser-based clients, run Afferens in HTTP mode and point the client at the `/mcp` endpoint:\n\n```bash\nAFFERENS_TRANSPORT=http AFFERENS_PORT=8790 AFFERENS_API_KEY=YOUR_KEY node dist/index.js\n```\n\nThen register the endpoint:\n\n```json\n{\n  \"afferens\": {\n    \"url\": \"http://127.0.0.1:8790/mcp\",\n    \"bearer_token_env_var\": \"AFFERENS_API_KEY\"\n  }\n}\n```\n\n### Claude Desktop / Cursor / Windsurf\n\nAdd to your MCP config file:\n\n```json\n{\n  \"mcpServers\": {\n    \"afferens\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@afferens/mcp-server\"],\n      \"env\": {\n        \"AFFERENS_API_KEY\": \"YOUR_KEY\"\n      }\n    }\n  }\n}\n```\n\nConfig file locations:\n- Claude Desktop (Mac): `~/Library/Application Support/Claude/claude_desktop_config.json`\n- Claude Desktop (Windows): `%APPDATA%\\Claude\\claude_desktop_config.json`\n- Cursor: `.cursor/mcp.json` in your project root\n- Windsurf: `~/.codeium/windsurf/mcp_config.json`\n\n### Try it without a key\n\n```json\n{\n  \"mcpServers\": {\n    \"afferens\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@afferens/mcp-server\"]\n    }\n  }\n}\n```\n\nCall `afferens_demo` - no API key needed.\n\n## Usage\n\nOnce connected, your AI agent can call:\n\n```text\nafferens_perceive({ modality: \"VISION\", limit: 5 })\n```\n\nReturns structured perception events your agent can reason over and act on.\n\nFor demo verification:\n\n```text\nafferens_verify({ modality: \"VISION\", limit: 3, wait_ms: 2000 })\n```\n\nReturns two raw snapshots plus headers, age, and a hash check so you can show whether the feed is live, stale, or unchanged.\n\n## Links\n\n- [afferens.com](https://afferens.com) - sign up, dashboard, API docs\n- [npm](https://www.npmjs.com/package/@afferens/mcp-server)\n- [Smithery](https://smithery.ai/servers/afferens/afferens-mcp)\n\n## License\n\nMIT\n",
  "bytes": 3035,
  "sha": "22883e8833dece2aa9fa63bac12f7340e722ad822d130e0b92ed1d316cd4c4bb",
  "repo_slug": "afferens/afferens-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_afferens_mcp_server_edc20efb/readme"
}