EDNA — On-Device Human Sensing for AI
On-device human sensing for AI: EDNA ID continuity and live human context via MCP.
사용해야 할까요
품질 및 안전성
발견 사항 (19)
- LOWedna.get_human_proof에서
- LOWedna.get_signal_vector에서
- LOWedna.id.memory에서
- LOWedna.submit_proof에서
- LOWedna.get_human_proof에서
- LOWedna.get_signal_vector에서
- LOWedna.get_human_context에서
- LOWedna.get_verification_info에서
- LOWedna.id.genesis에서
- LOWedna.id.feed에서
도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.
컨텍스트 비용
이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.
설치
원클릭 설치
`claude_desktop_config.json` 파일에 다음을 추가하세요:
{
"mcpServers": {
"edna": {
"url": "https://openos.space/mcp"
}
}
}원격 엔드포인트
https://openos.space/mcpstreamable-http할 수 있는 일
도구 목록
도구 (18)
🟡edna.submit_proof(confidence, classification, signals, hashPattern, context, ...)
Submit the current human proof (score, classification, quantized signals, hash pattern, optional context/reading/process). Consent REQUIRED: scope.mcp === true. Never raw biometrics.
입력 스키마
{
"type": "object",
"properties": {
"confidence": {
"type": "number"
},
"classification": {
"type": "string",
"enum": [
"gathering_data",
"bot",
"likely_bot",
"uncertain",
"human_verified"
]
},
"signals": {
"type": "object"
},
"hashPattern": {
"type": "string"
},
"context": {
"type": "object"
},
"reading": {
"type": "object"
},
"process": {
"type": "object"
},
"consent": {
"type": "object"
},
"timestamp": {
"type": "string"
},
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
},
"required": [
"confidence",
"classification",
"consent"
]
}⚪edna.get_human_proof(session)
Current human proof { confidence, classification } for this session.
입력 스키마
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}⚪edna.get_signal_vector(session)
Quantized 16-channel behavioral signal vector of this session.
입력 스키마
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}⚪edna.get_human_context(session)
Time-aware human context: dynamics, tempo trend, pauses, cautious indicators with limits.
입력 스키마
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}⚪edna.get_verification_info(session)
How to independently verify the engine (open protocol).
입력 스키마
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}⚪edna.id.genesis(handle, consent, session)
EDNA ID (production): device-bound EDNA ID (ECDSA-P256 keypair, signed handle, genesis from latest proof). Consent REQUIRED: scope.id === true. Continuity proof — never a real-world identity.
입력 스키마
{
"type": "object",
"properties": {
"handle": {
"type": "string"
},
"consent": {
"type": "object"
},
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
},
"required": [
"handle",
"consent"
]
}⚪edna.id.feed(session)
EDNA ID (production): feed latest proof into the chain; grows only on full human verification.
입력 스키마
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}⚪edna.id.status(session)
EDNA ID (production): chain status + measured identity-confidence curve (99%+ = research target).
입력 스키마
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}⚪edna.id.memory(layer, session)
EDNA ID (production): memory layer live | session | longterm (vs the user's OWN anchor).
입력 스키마
{
"type": "object",
"properties": {
"layer": {
"type": "string",
"enum": [
"live",
"session",
"longterm"
]
},
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}⚪edna.id.verify_resume(session)
EDNA ID (production): resume gate — reference-window match (>=0.85), never last-hash alone.
입력 스키마
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}⚪edna.id.integrity(checkpointsOnly, session)
EDNA ID (production): verify signatures + linkage over full log and checkpoint chain.
입력 스키마
{
"type": "object",
"properties": {
"checkpointsOnly": {
"type": "boolean"
},
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}⚪edna.id.export_state(session)
EDNA ID (production): local state export — no private key, no raw signals, no plaintext handle.
입력 스키마
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}⚪edna.id.revoke(session)
EDNA ID (production): real LOCAL deletion — key, vault, model, log destroyed.
입력 스키마
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}🟡edna_identity_create(session)
EDNA ID (production): seal the device-signed identity anchor — only after edna.id.genesis and ≥3 minutes of full human verification on the Chladni hash chain. The seal is a device-key signature; it can only be created on the user's device (this endpoint validates it).
입력 스키마
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}⚪edna_identity_verify(handle, signals, session)
EDNA ID (production): verify a handle against the genesis handle commitment + live Chladni pattern vs account vault. Three consecutive 100% matches authenticate the session into the EDNA ID account (behavioral login); any miss resets the streak.
입력 스키마
{
"type": "object",
"properties": {
"handle": {
"type": "string"
},
"signals": {
"type": "object"
},
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
},
"required": [
"handle"
]
}⚪edna.get_response_guidance(session)
Adaptive Response Layer (production): overridable mode (FLOW/FOCUS/EXPLORE/EXECUTE/REFLECT) from consented dynamics. The humanness score is NEVER an input.
입력 스키마
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}⚪edna.get_writing_process(session)
Writing-process channel (production): HOW the current message came to be — typing bursts, thinking pauses (the reason is never inferred), correction runs, tempo dynamics and a quantized 12-step timeline. Never content, never key identity.
입력 스키마
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}⚪edna.get_live_brief(session)
One-call live brief for continuous perception: current proof + human context + writing process + response guidance in a single pull. Call before each answer while an EDNA session is streaming.
입력 스키마
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Test session id [a-zA-Z0-9_-]{1,64} — sensor bridge and AI client must use the SAME id. Omit to use the X-EDNA-Session header or the \"default\" session."
}
}
}커뮤니티
증거