Affect analysis, 3D avatar params, empathy hints and somatic emotion decode.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Chenji API key (free BASIC tier on RapidAPI or taichusjs.cn)
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
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'.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
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'.
| Argument | Type | Description |
|---|---|---|
| lang | string | |
| text* | string |
{
"type": "object",
"title": "analyze_textArguments",
"required": [
"text"
],
"properties": {
"lang": {
"type": "string",
"title": "Lang",
"default": ""
},
"text": {
"type": "string",
"title": "Text"
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| text* | string |
{
"type": "object",
"title": "empathy_hintArguments",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"title": "Text"
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| text* | string |
{
"type": "object",
"title": "generate_avatar_paramsArguments",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"title": "Text"
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| text* | string |
{
"type": "object",
"title": "somatic_decodeArguments",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"title": "Text"
}
}
}