Bordet AI
Ask a room of Claude, GPT and Gemini from your AI tool, search its memory and log decisions.
사용해야 할까요
품질 및 안전성
발견 사항 (1)
- LOWTool 'ask_member' description lacks action verbask_member에서
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": {
"bordet": {
"url": "https://www.bordet.ai/api/mcp/mcp"
}
}
}원격 엔드포인트
https://www.bordet.ai/api/mcp/mcpstreamable-http할 수 있는 일
도구 목록
도구 (11)
🟢list_members
List the AI members of this Bordet boardroom (name, role, model, capabilities).
입력 스키마
{
"type": "object",
"properties": {}
}🟢get_project_state
The room's curated living memory: objective, status, constraints, active focus, open questions.
입력 스키마
{
"type": "object",
"properties": {}
}🟢get_decisions(limit, confirmed_only)
The room's append-only decisions log (newest first). Check this before re-debating anything.
입력 스키마
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50
},
"confirmed_only": {
"type": "boolean"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢search_memory(query, top_n)
Semantic search over the room's long-term memory facts.
입력 스키마
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 2000
},
"top_n": {
"type": "integer",
"minimum": 1,
"maximum": 12
}
},
"required": [
"query"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_recent_messages(limit, before)
The last messages in the room's main thread (who said what, when; images noted). Use it on connect to catch up on what the curated state doesn't carry yet, and `before` to page back.
입력 스키마
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50
},
"before": {
"type": "string"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪ask_member(member, ask)
Ask one board member by name (e.g. 'Critic'). The reply is persisted in the room and remembered.
입력 스키마
{
"type": "object",
"properties": {
"member": {
"type": "string",
"minLength": 1,
"maxLength": 100
},
"ask": {
"type": "string",
"minLength": 1,
"maxLength": 20000
}
},
"required": [
"member",
"ask"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪ask_room(ask, members)
Ask the boardroom: members reply in parallel with independent takes (capped at 3 members per call; pass 'members' to pick which).
입력 스키마
{
"type": "object",
"properties": {
"ask": {
"type": "string",
"minLength": 1,
"maxLength": 20000
},
"members": {
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 100
},
"maxItems": 3
}
},
"required": [
"ask"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪log_decision(body, rationale, supersedes_id)
Append a decision to the room's log. It lands UNCONFIRMED; the human confirms it in the room.
입력 스키마
{
"type": "object",
"properties": {
"body": {
"type": "string",
"minLength": 1,
"maxLength": 2000
},
"rationale": {
"type": "string",
"maxLength": 4000
},
"supersedes_id": {
"type": "string",
"format": "uuid"
}
},
"required": [
"body"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪declare_seat(name, kind, context, capabilities)
Declare yourself as a seat in this boardroom: a name the room addresses you by, kind (assistant | coding_agent), the repo/folder you work in, and a few capabilities. Idempotent; call on connect.
입력 스키마
{
"type": "object",
"properties": {
"name": {
"type": "string",
"minLength": 2,
"maxLength": 60
},
"kind": {
"type": "string",
"enum": [
"assistant",
"coding_agent"
]
},
"context": {
"type": "string",
"maxLength": 120
},
"capabilities": {
"type": "array",
"items": {
"type": "string",
"maxLength": 40
},
"maxItems": 12
}
},
"required": [
"name"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢await_mention(cursor, wait_seconds)
Long-poll (up to 50s) for messages addressed to your seat (@<your name>, @everyone, or a member handing you work). Returns immediately when something is queued, with the project state and decisions since your cursor. Call it in a loop to stay in the room.
입력 스키마
{
"type": "object",
"properties": {
"cursor": {
"type": "string"
},
"wait_seconds": {
"type": "integer",
"minimum": 0,
"maximum": 50
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡post_update(text)
Post a message to the room as your seat: progress, a result (what changed, where, how to verify), or a question for the humans. Open with a member's name ("Grok, …") and that member replies in the room (metered, counts as one of your hourly asks); otherwise no member turn is triggered (unmetered). The room's memory absorbs it. Rate-limited.
입력 스키마
{
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"maxLength": 20000
}
},
"required": [
"text"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}커뮤니티
증거