Chenji Affect is a remote MCP server that gives an AI agent 4 tools, among them analyze_text, empathy_hint, generate_avatar_params. It answers at https://taichusjs.cn/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
Affect analysis, 3D avatar params, empathy hints and somatic emotion decode.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
analyze_text | 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'. Inputs: text, lang |
empathy_hint | 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; privac Inputs: text |
generate_avatar_params | 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. Inputs: text |
somatic_decode | 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 Inputs: text |
Every block below points at https://taichusjs.cn/mcp. Pick your client and copy.
claude mcp add --transport http chenji-affect https://taichusjs.cn/mcp
{
"mcpServers": {
"chenji-affect": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://taichusjs.cn/mcp"]
}
}
}{
"mcpServers": {
"chenji-affect": {
"url": "https://taichusjs.cn/mcp"
}
}
}{
"servers": {
"chenji-affect": {
"type": "http",
"url": "https://taichusjs.cn/mcp"
}
}
}{
"context_servers": {
"chenji-affect": {
"url": "https://taichusjs.cn/mcp"
}
}
}{
"mcpServers": {
"chenji-affect": {
"serverUrl": "https://taichusjs.cn/mcp"
}
}
}{
"mcpServers": {
"chenji-affect": {
"url": "https://taichusjs.cn/mcp"
}
}
}name: Chenji Affect
version: 0.0.1
schema: v1
mcpServers:
- name: Chenji Affect
type: streamable-http
url: https://taichusjs.cn/mcp{
"mcpServers": {
"chenji-affect": {
"httpUrl": "https://taichusjs.cn/mcp"
}
}
}{
"mcpServers": {
"chenji-affect": {
"type": "http",
"url": "https://taichusjs.cn/mcp"
}
}
}{
"mcpServers": {
"chenji-affect": {
"url": "https://taichusjs.cn/mcp"
}
}
}goose://extension?url=https%3A%2F%2Ftaichusjs.cn%2Fmcp&type=streamable_http&id=chenji-affect&name=Chenji%20Affect
It answered our last check on 24 October 2026 in 988 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
4, as returned by the server's own tools/list on 22 September 2026: analyze_text, empathy_hint, generate_avatar_params, somatic_decode.
It answered our last check on 24 October 2026 in 988 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://taichusjs.cn/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.zhiyu-dev. Endpoint host: taichusjs.cn. ARD identifier: urn:air:io.github.zhiyu-dev:mcp:chenji-affect-mcp.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.