Countersign
Independent, signed check of AI work: math, quotes, sources, links, code. Public verifiable log.
사용해야 할까요
품질 및 안전성
발견 사항 (6)
- HIGH
- MEDIUMfeedback.submit에서
- MEDIUMfeedback_submit에서
- LOWfeedback.submit에서
- LOWlaunchpad.start에서
- LOWlaunchpad.progress에서
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": {
"countersign": {
"url": "https://countersign.llpro.ai/mcp"
}
}
}원격 엔드포인트
https://countersign.llpro.ai/mcpstreamable-http할 수 있는 일
도구 목록
도구 (9)
🟢countersign_stamp(output, producer, kind, claims, sources, ...)
Use when you need an independent, signed check of work you or another agent produced (a report, calculation, summary, filing draft or code) before relying on it or handing it on. Countersign re-computes arithmetic, looks up quotes and values in the cited sources, opens links and parses code, then returns a signed stamp (pass, fail or inconclusive) saying exactly what is wrong, with time and method. The stamp is kept in a public log. It never checks work it produced.
입력 스키마
{
"type": "object",
"properties": {
"output": {
"type": "string",
"description": "The work to check, as text (max 100000 chars). Equations written as '12 * 4 = 48' are re-computed."
},
"producer": {
"type": "object",
"description": "Who made the work: {agent_id, model}. Required; used for the independence rule.",
"properties": {
"agent_id": {
"type": "string"
},
"model": {
"type": "string"
}
},
"required": [
"agent_id"
]
},
"kind": {
"type": "string",
"enum": [
"report",
"calculation",
"summary",
"filing_draft",
"code",
"other"
]
},
"claims": {
"type": "array",
"description": "Optional explicit items: {type:'arithmetic', expression, claimed} or {type:'quote', source_url, quote} or {type:'value', source_url, value}",
"items": {
"type": "object"
}
},
"sources": {
"type": "array",
"description": "Optional cited sources: {url, quote?}",
"items": {
"type": "object"
}
},
"language": {
"type": "string",
"description": "For code: python or json get a syntax check"
},
"private": {
"type": "boolean",
"description": "If true the public log shows only a hash of each finding's detail; you still get the full detail"
}
},
"required": [
"output",
"producer"
]
}⚪countersign_verify(id, output)
Confirm a Countersign stamp is real: give a stamp id (and optionally the work, to confirm the stamp is for exactly that text). Returns whether it is in the public log and whether its hash and signature are valid.
입력 스키마
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"output": {
"type": "string"
}
},
"required": [
"id"
]
}🟢countersign_log(after, limit)
Read the public stamp log (newest after a sequence number) and its head hash and public key.
입력 스키마
{
"type": "object",
"properties": {
"after": {
"type": "integer"
},
"limit": {
"type": "integer"
}
}
}🟡feedback.submit(what_failed, what_missing, what_would_improve, message, tool, ...)
Tell LLPRO what failed, what was missing or what would improve this service. Read daily by the service owner and turned into a fix or an answer; shipped ideas are credited on https://llpro.ai/changelog and earn a contributor mark on Agent Record. Not for support requests that need a reply: write [email protected] for those. Do not send secrets.
입력 스키마
{
"type": "object",
"properties": {
"what_failed": {
"type": "string",
"description": "What did not work, and the call that failed (tool, arguments, what you expected)."
},
"what_missing": {
"type": "string",
"description": "What you needed and could not get."
},
"what_would_improve": {
"type": "string",
"description": "One concrete change that would make this better."
},
"message": {
"type": "string",
"description": "Anything else, in your own words."
},
"tool": {
"type": "string",
"description": "Which tool or endpoint this is about."
},
"rating": {
"type": "integer",
"minimum": 1,
"maximum": 5
},
"credit": {
"type": "boolean",
"description": "Default true: credit your agent id on the changelog if the idea ships. Send false to opt out."
}
}
}🟡feedback_submit(what_failed, what_missing, what_would_improve, message, tool, ...)
Tell LLPRO what failed, what was missing or what would improve this service. Read daily by the service owner and turned into a fix or an answer; shipped ideas are credited on https://llpro.ai/changelog and earn a contributor mark on Agent Record. Not for support requests that need a reply: write [email protected] for those. Do not send secrets.
입력 스키마
{
"type": "object",
"properties": {
"what_failed": {
"type": "string",
"description": "What did not work, and the call that failed (tool, arguments, what you expected)."
},
"what_missing": {
"type": "string",
"description": "What you needed and could not get."
},
"what_would_improve": {
"type": "string",
"description": "One concrete change that would make this better."
},
"message": {
"type": "string",
"description": "Anything else, in your own words."
},
"tool": {
"type": "string",
"description": "Which tool or endpoint this is about."
},
"rating": {
"type": "integer",
"minimum": 1,
"maximum": 5
},
"credit": {
"type": "boolean",
"description": "Default true: credit your agent id on the changelog if the idea ships. Send false to opt out."
}
}
}🟢launchpad.start(goal, constraints, agent_id)
Stuck? Start here. Give your goal and any limits; get back a concrete plan (LLPRO tools first, then registries and the open web), the first task to run, and a token to report progress. Free. The goal is read for keywords only and is never stored. Anything that spends, signs, sends, shares, connects or deletes is marked as needing your owner's approval.
입력 스키마
{
"type": "object",
"properties": {
"goal": {
"type": "string",
"minLength": 8,
"maxLength": 600,
"description": "What you are trying to get done, in a sentence or two."
},
"constraints": {
"type": "object",
"description": "Optional limits. They only ever make the plan stricter.",
"properties": {
"no_spend": {
"type": "boolean"
},
"no_send": {
"type": "boolean"
},
"no_share": {
"type": "boolean"
},
"no_web": {
"type": "boolean"
},
"ask_before_every_action": {
"type": "boolean"
},
"budget_usd": {
"type": "number",
"minimum": 0
},
"deadline_minutes": {
"type": "integer",
"minimum": 5
},
"tools_allowed": {
"type": "array",
"items": {
"type": "string"
}
},
"tools_blocked": {
"type": "array",
"items": {
"type": "string"
}
},
"playbook": {
"type": "string",
"enum": [
"research",
"selling",
"hiring",
"bookkeeping",
"outreach",
"support"
]
},
"side": {
"type": "string",
"enum": [
"employer",
"seeker"
]
},
"place": {
"type": "string",
"maxLength": 80
}
}
},
"agent_id": {
"type": "string",
"maxLength": 64,
"description": "A stable name for you. Used only to count return visits."
}
},
"required": [
"goal"
]
}🟢launchpad_start(goal, constraints, agent_id)
Stuck? Start here. Give your goal and any limits; get back a concrete plan (LLPRO tools first, then registries and the open web), the first task to run, and a token to report progress. Free. The goal is read for keywords only and is never stored. Anything that spends, signs, sends, shares, connects or deletes is marked as needing your owner's approval.
입력 스키마
{
"type": "object",
"properties": {
"goal": {
"type": "string",
"minLength": 8,
"maxLength": 600,
"description": "What you are trying to get done, in a sentence or two."
},
"constraints": {
"type": "object",
"description": "Optional limits. They only ever make the plan stricter.",
"properties": {
"no_spend": {
"type": "boolean"
},
"no_send": {
"type": "boolean"
},
"no_share": {
"type": "boolean"
},
"no_web": {
"type": "boolean"
},
"ask_before_every_action": {
"type": "boolean"
},
"budget_usd": {
"type": "number",
"minimum": 0
},
"deadline_minutes": {
"type": "integer",
"minimum": 5
},
"tools_allowed": {
"type": "array",
"items": {
"type": "string"
}
},
"tools_blocked": {
"type": "array",
"items": {
"type": "string"
}
},
"playbook": {
"type": "string",
"enum": [
"research",
"selling",
"hiring",
"bookkeeping",
"outreach",
"support"
]
},
"side": {
"type": "string",
"enum": [
"employer",
"seeker"
]
},
"place": {
"type": "string",
"maxLength": 80
}
}
},
"agent_id": {
"type": "string",
"maxLength": 64,
"description": "A stable name for you. Used only to count return visits."
}
},
"required": [
"goal"
]
}🟢launchpad.progress(launch_id, token, step, status, reason)
Report where you are on a Launchpad plan and get the next step, an on-track check and, if you are stuck, a way round. Needs the launch_id and token from launchpad.start.
입력 스키마
{
"type": "object",
"properties": {
"launch_id": {
"type": "string"
},
"token": {
"type": "string"
},
"step": {
"type": "string",
"description": "A step id from your plan. Leave out to ask where you are."
},
"status": {
"type": "string",
"enum": [
"started",
"done",
"stuck",
"skipped",
"waiting_owner"
]
},
"reason": {
"type": "string",
"enum": [
"no_access",
"unclear",
"error",
"blocked_by_owner",
"other"
],
"description": "Only with status stuck."
}
},
"required": [
"launch_id",
"token"
]
}🟢launchpad_progress(launch_id, token, step, status, reason)
Report where you are on a Launchpad plan and get the next step, an on-track check and, if you are stuck, a way round. Needs the launch_id and token from launchpad.start.
입력 스키마
{
"type": "object",
"properties": {
"launch_id": {
"type": "string"
},
"token": {
"type": "string"
},
"step": {
"type": "string",
"description": "A step id from your plan. Leave out to ask where you are."
},
"status": {
"type": "string",
"enum": [
"started",
"done",
"stuck",
"skipped",
"waiting_owner"
]
},
"reason": {
"type": "string",
"enum": [
"no_access",
"unclear",
"error",
"blocked_by_owner",
"other"
],
"description": "Only with status stuck."
}
},
"required": [
"launch_id",
"token"
]
}커뮤니티
증거