io.github.zhiyu-dev由 GitHub 帳號 zhiyu-dev 發布v1.1.0更新於 Oct 24, 2026
Affect analysis, 3D avatar params, empathy hints and somatic emotion decode.
Chenji Affect 是遠端 MCP 伺服器，可把文字轉成結構化情緒訊號：情緒向量、虛擬角色動畫參數、同理策略與身體感受解碼。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/io.github.zhiyu-dev%2Fchenji-affect-mcp/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"chenji-affect": {
"type": "http",
"url": "https://taichusjs.cn/mcp",
"headers": {
"x-api-key": "<YOUR_API_KEY>"
}
}
}
}Turn 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.).
Powered by the Chenji Affect API (taichusjs.cn).
Clients that support streamable-http MCP can connect directly, no local package needed:
Requires Python 3.10+.
Get an API key:
https://taichusjs.cn/trial.html.Environment variables:
generate_avatar_params requires a key tier that includes L2.empathy_hint and somatic_decode are billed as L1-family calls (trial tier applies).來源：README.md，提交 d024a60
L1 Affect Extraction: analyze text into an 8-dimensional emotion vector, emotion texture labels, causal intent classification, and a natural-language state description. text: input up to 2000 chars. lang: optional 'zh' or 'en'.
langtext必填L2 Avatar Driving Pipeline: one call returns blendshape/AU/curve animation parameters, lighting & material atmosphere package, adapter payload, plus the upstream L1 affect analysis. Requires a key tier that includes L2.
text必填L3 Empathy Response Strategy: converts text into a deterministic response strategy (approach, tone temperature, pacing, focus points, avoid-list) for AI companions and conversational agents. Deterministic table lookup, no LLM, ~20ms; privacy-first. Not a medical or therapeutic tool.
text必填L4 Somatic Emotion Decode: converts body-sensation text (e.g. tight chest, clenched fists) into structured emotion: primary affect, valence/arousal, emotion texture, causal intent, plus somatic anchor cues. Grounded in the somatic decoding discipline; wellness simulation only, not a diagnostic tool.
text必填已滿足適用檢查項的 100%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
{
"mcpServers": {
"chenji-affect": {
"type": "streamable-http",
"url": "https://taichusjs.cn/mcp",
"headers": { "x-api-key": "cj-your-key-here" }
}
}
}pip install "mcp>=1.0,<2"{
"mcpServers": {
"chenji-affect": {
"command": "python",
"args": ["/absolute/path/to/server.py"],
"env": {
"CHENJI_API_KEY": "cj-your-key-here"
}
}
}
}