{
  "markdown": "# Chenji Affect MCP Server\r\n\r\n<!-- mcp-name: io.github.zhiyu-dev/chenji-affect-mcp -->\r\n\r\nTurn raw text into structured affect signals — an **8-dimensional emotion vector**, **emotion texture labels**, **causal intent**, **3D avatar driving parameters**, **empathy response strategies**, and **somatic-sensation emotion decoding** — inside any MCP-capable client (Claude Desktop, Cursor, Qoder, etc.).\r\n\r\nPowered by the [Chenji Affect API](https://rapidapi.com/zhiyudev/api/chenji-affect-api) (`taichusjs.cn`).\r\n\r\n## Tools\r\n\r\n| Tool | Level | Description |\r\n| --- | --- | --- |\r\n| `analyze_text` | L1 | Text → 8-dim affect vector + emotion texture + intent + state description |\r\n| `generate_avatar_params` | L2 | Text → blendshape/AU/curve animation package + lighting/atmosphere package + upstream L1 |\r\n| `empathy_hint` | L3 | Text → deterministic empathy response strategy (approach, tone, pacing, focus, avoid-list), ~20ms, no LLM |\r\n| `somatic_decode` | L4 | Body-sensation text → structured emotion (primary affect, valence/arousal, texture, intent) + somatic anchors |\r\n\r\n## Remote mode (no install)\r\n\r\nClients that support streamable-http MCP can connect directly, no local package needed:\r\n\r\n```json\r\n{\r\n  \"mcpServers\": {\r\n    \"chenji-affect\": {\r\n      \"type\": \"streamable-http\",\r\n      \"url\": \"https://taichusjs.cn/mcp\",\r\n      \"headers\": { \"x-api-key\": \"cj-your-key-here\" }\r\n    }\r\n  }\r\n}\r\n```\r\n\r\n## Install\r\n\r\nRequires Python 3.10+.\r\n\r\n```bash\r\npip install \"mcp>=1.0,<2\"\r\n```\r\n\r\nGet an API key:\r\n- Free BASIC plan (100 req/day, 3,000/month): subscribe on [RapidAPI](https://rapidapi.com/zhiyudev/api/chenji-affect-api), or request a trial key at `https://taichusjs.cn/trial.html`.\r\n\r\n## Configure (Claude Desktop example)\r\n\r\n```json\r\n{\r\n  \"mcpServers\": {\r\n    \"chenji-affect\": {\r\n      \"command\": \"python\",\r\n      \"args\": [\"/absolute/path/to/server.py\"],\r\n      \"env\": {\r\n        \"CHENJI_API_KEY\": \"cj-your-key-here\"\r\n      }\r\n    }\r\n  }\r\n}\r\n```\r\n\r\nEnvironment variables:\r\n\r\n| Variable | Required | Description |\r\n| --- | --- | --- |\r\n| `CHENJI_API_KEY` | Yes | Your Chenji API key |\r\n| `CHENJI_API_BASE` | No | Defaults to `https://taichusjs.cn` |\r\n\r\n## Notes\r\n\r\n- L1 input is limited to 2000 characters (every 200 chars = 1 billing unit).\r\n- `generate_avatar_params` requires a key tier that includes L2.\r\n- `empathy_hint` and `somatic_decode` are billed as L1-family calls (trial tier applies).\r\n- Privacy: raw text is never persisted by the API; only key hashes and telemetry are retained.\r\n- Wellness and affect-state simulation only — not a medical or diagnostic tool.\r\n\r\n## Links\r\n\r\n- Website: https://taichusjs.cn\r\n- RapidAPI listing: https://rapidapi.com/zhiyudev/api/chenji-affect-api\r\n- Machine-readable capability card: https://taichusjs.cn/.well-known/capability.jsonld\r\n",
  "bytes": 2797,
  "sha": "a89635fa8f08de4e88171771903418b9ae807473b96cd90499924cebcca639ec",
  "repo_slug": "zhiyu-dev/chenji-affect-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_zhiyu_dev_chenji_affect_mcp_0ba6b908/readme"
}