Chenji Affect MCP server
io.github.zhiyu-dev/chenji-affect-mcpzhiyu-devstreamable-httpv1.1.0Scanned
Affect analysis, 3D avatar params, empathy hints and somatic emotion decode.
4 tools: 3 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Chenji Affect MCP server can do
The Chenji Affect MCP server is published by the GitHub account zhiyu-dev. It has 4 tools. It can create or change data (3 tools: generate_avatar_params, empathy_hint and somatic_decode), but cannot delete data. 1 tool only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 2026, version 1.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
4 tools
Changes things 3Claude Code: ask
empathy_hintL3 Empathy Response Strategy: converts text into a deterministic response strategy (approach, tone temperature, pacing, focus points, avoid-list) for AI companions and conversation…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
generate_avatar_paramsL2 Avatar Driving Pipeline: one call returns blendshape/AU/curve animation parameters, lighting & material atmosphere package, adapter payload, plus the upstream L1 affect analysis…No findings
Why it is in this group
- The name "generate_avatar_params" says "generate": a word for a change.
Description, as the server wrote it 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.
somatic_decodeL4 Somatic Emotion Decode: converts body-sensation text (e.g.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
Only reads 1Show 1 read-only tool
analyze_textL1 Affect Extraction: analyze text into an 8-dimensional emotion vector, emotion texture labels, causal intent classification, and a natural-language state description.No findings
Why it is in this group
- The name "analyze_text" says "analyze": a word for reading.
Description, as the server wrote 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 is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:13 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://taichusjs.cn/mcp: tools/list returned 4 tools to an anonymous client, including generate_avatar_params (write), empathy_hint (write), somatic_decode (write)
Posture changes
- Nov 13, 2026
- Reachable: no to yes
- HTTP status of an anonymous initialize: none to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 3
- Protocol version: none to 2025-06-18
- Nov 6, 2026
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 3 to 0
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Reachable: no -> yes; HTTP status of an anonymous initialize: none -> 200; tools/list served without credentials: no -> yes (and 2 more).View diff
- Reachable: no to yes
- HTTP status of an anonymous initialize: none to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 3
- Protocol version: none to 2025-06-18
PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 2 more).View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 3 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http chenji-affect https://taichusjs.cn/mcp --header 'x-api-key: <your-x-api-key>'claude mcp add --transport http chenji-affect https://taichusjs.cn/mcp --header 'x-api-key: <your-x-api-key>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__chenji-affect__analyze_text"
],
"ask": [
"mcp__chenji-affect__generate_avatar_params",
"mcp__chenji-affect__empathy_hint",
"mcp__chenji-affect__somatic_decode"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as chenji-affect. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.zhiyu-dev/chenji-affect-mcp/verify?hash=c4f99ba5237cb6ee676e648df79dcffa8554d0dfb988c31cc3f9b0e024261895" | jq -e '.changed == false'Pinned hash c4f99ba5237c, from Nov 20, 2026, 19:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.zhiyu-dev/chenji-affect-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.zhiyu-dev/chenji-affect-mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:52 UTC.
Chenji Affect MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Chenji Affect MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Chenji Affect MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Chenji Affect MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Chenji Affect MCP server have?
- 4 tools: 3 write, 1 read. generate_avatar_params, empathy_hint, somatic_decode and analyze_text.
Does the Chenji Affect MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Chenji Affect MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Chenji Affect MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.