MCP serverio.github.zhiyu-dev/chenji-affect-mcp
Affect analysis, 3D avatar params, empathy hints and somatic emotion decode.
Overview
Score?
UNRATED 0.641
of what a free look can see, on 32 looks
Looks
35
last 10 hr ago
Tools
4
More info
URL
taichusjs.cn/mcp
streamable-http
Says it is
chenji-affect 1.29.1
protocol 2025-06-18
In the record since
32 days ago
Among servers18,413 with a card
0median 0.606 · this server 0.641 · highest on record 0.8561
Toolsfrom sha256:1291514ba9…a878f5
| Tool | Schema |
|---|---|
| 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. tex |
input · output |
| 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 conv |
input · output |
| 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 |
input · output |
| 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 |
input · output |
Verify it yourself
npx teppi-check https://taichusjs.cn/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2P26XJ4BPFQ75FPQ0DD0