AI 에이전트를 위한 TON 블록체인 기반 Zero-Auth 암호화 공증 및 증거 레이어.
🌐 프로토콜 웹사이트 • 📖 OpenAPI 명세 • 📱 텔레그램 봇
이것은 ProofCore Protocol을 위한 공식 Model Context Protocol (MCP) 서버입니다.
AI 어시스턴트(Claude, Cursor, Windsurf 등)가 감사 결과, 법적 계약, 서버 로그 등의 출력물을 능동적으로 암호화 방식으로 봉인하여 The Open Network (TON) 블록체인에 직접 기록할 수 있게 해줍니다.
이 서버를 사용하면 AI 에이전트가 자신의 출력물이 특정 타임스탬프에 존재했으며 이후에 변조되거나 허위로 생성된 것이 아님을 수학적으로 증명할 수 있습니다.
Related MCP server: DocImprint
seal_content(content: str, title: str)
제공된 텍스트를 SHA-256으로 해시한 후, TON 블록체인의 Merkle Tree 일괄 처리(batching) 대기열에 추가합니다. 변경할 수 없는 인용 배지와 Ed25519 서명을 반환합니다.
get_proof_status(deal_id: str)
이전에 봉인된 딜에 대한 암호화 매니페스트, Merkle 경로 및 TON 트랜잭션 해시를 조회합니다.
verify_content(deal_id: str, content: str)
에이전트 간 검증: 봉인된 딜을 프로그래밍 방식으로 검증합니다. 콘텐츠 해시를 다시 계산하고, Ed25519 공증인 서명을 확인하며, TON 앵커 상태를 확인합니다.
get_public_key()
오프라인 서명 검증을 위한 ProofCore 서버의 Ed25519 공개 키를 반환합니다.
ProofCore를 사용하기 위해 API 키가 필요하지 않습니다. 엄격한 Zero-Auth 메커니즘을 기반으로 작동합니다.
claude_desktop_config.json에 다음을 추가하세요:
{
"mcpServers": {
"proofcore": {
"command": "uvx",
"args": ["proofcore-mcp"]
}
}
}Cursor Settings -> Features -> MCP를 엽니다.
+ Add new MCP Server를 클릭합니다.
유형 command를 선택합니다.
이름: proofcore
명령어: uvx proofcore-mcp
AI에게 그냥 물어보세요:
"이 Solidity 컨트랙트를 감사하고, 최종 판정을 온체인에 암호화 방식으로 봉인하세요."
"Alice와 Bob 사이의 NDA를 작성한 다음 ProofCore를 통해 공증하세요."
"딜 UUID의 블록체인 상태는 무엇인가요?"
(신규) M2M 검증: "여기 보고서와 딜 ID UUID가 있습니다. ProofCore를 사용하여 진위와 서명을 검증하세요."
AI가 도구를 자동으로 호출하여 문서를 앵커링/검증하고 검증 링크를 제공할 것입니다!
ProofCore는 *"공증인을 믿지 말고, 증명을 직접 검증하라."*라는 철학을 바탕으로 구축되었습니다.
모든 봉인된 문서는 인용 링크(예: https://proofcore.org/app/<UUID>)를 반환합니다.
누구나 이 링크를 방문하여 암호화 3중 일치를 독립적으로 검증할 수 있습니다:
Local SHA-256 Hash == Manifest Merkle Path == TON Blockchain Transaction Payload
게다가, 증명은 100% 자율적입니다. 사용자는 원본 자산, JSON 매니페스트, 독립형 Python/HTML 검증 스크립트가 포함된 **오프라인 증거 패키지(ZIP)**를 다운로드할 수 있습니다. ProofCore 서버가 오프라인이 되더라도 사용자의 암호화 증명은 TON 블록체인에 대해 직접 수학적으로 검증 가능합니다.
"ProofCore를 믿지 말고, 증명을 직접 검증하라."
MIT 라이선스에 따라 배포됩니다.
Fetches cryptographic manifest and TON transaction status.
| Name | Required | Description | Default |
|---|---|---|---|
| deal_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions 'fetches', implying a read operation, but offers no details on side effects, permissions, idempotency, or error behavior. It does not disclose whether the operation is safe or what it might affect. The presence of an output schema partially mitigates return-format expectations but not behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no redundant wording. It front-loads the action and resource. However, it is so minimal that it misses critical context; nevertheless, its structure is concise and free of filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter tool with an output schema, the description is still incomplete. It lacks any explanation of the parameter, does not characterize the expected output semantically, and provides no usage context. The agent is left without essential information to invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must explain the parameter. It fails to mention deal_id, its purpose, format, or how it relates to the cryptographic manifest and TON transaction status. An agent cannot infer what value to supply without external knowledge.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it fetches cryptographic manifest and TON transaction status, using a specific verb and resource. It does not explicitly distinguish from siblings, though the operations are inherently different (seal, verify, get public key vs. status). Thus it meets the 'specific verb+resource' but falls short of explicit sibling differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like seal_content or verify_content. There is no mention of prerequisites, intended context, or conditions for use. The description only states the act, leaving usage entirely to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns the ProofCore server's Ed25519 public key.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It states the action but does not disclose side effects, authentication needs, or error behaviors. For a simple public key retrieval, this is minimal but not misleading.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence with no redundant wording. Perfectly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the existence of an output schema and the absence of parameters, the description fully covers what an agent needs to call the tool correctly. No missing contextual information.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool accepts zero parameters, so the schema fully documents the input. Per the rubric, a baseline of 4 applies for parameterless tools, and the description adds no unnecessary detail.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Returns') and the specific resource ('ProofCore server's Ed25519 public key'). It distinguishes itself from siblings which handle sealing, status, and verification.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use guidance or mention of alternatives is provided. The usage is implied by the tool's name and nature, but the description does not tell the agent under what circumstances it should be invoked versus the siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Cryptographically seals text/code/audits onto the TON Blockchain.
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | AI Audit Report | |
| content | Yes | ||
| agent_id | No | mcp-agent |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It implies a permanent, cryptographic action but does not mention prerequisites (e.g., private key, network availability), potential side effects, reversibility, or failure modes. This is a significant gap for a blockchain-mutating tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that front-loads the core action with no fluff. It is well-structured for readability, though it sacrifices necessary detail for brevity, making it slightly under-specified.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool that seals content onto a blockchain, this description is notably incomplete. It lacks explanation of expected inputs beyond a vague hint, does not describe what happens after sealing (e.g., proof generation), and omits operational context. The presence of an output schema mitigates the need to describe return values, but the description still fails to cover essential behavioral and parameter context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It hints at 'text/code/audits' which maps to the content parameter, but it does not clarify the purpose or meaning of title and agent_id, nor their defaults. This leaves agents without sufficient understanding of all inputs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action (seals) on a specific resource (text/code/audits onto the TON Blockchain). It clearly differentiates from siblings like get_proof_status, verify_content, and get_public_key by indicating a write operation. However, 'seals' is somewhat metaphorical and could be more precise about the exact operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool instead of its siblings or when not to use it. The description merely states what it does without any context for selection, leaving the agent to infer usage solely from the purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Programmatically verify a sealed deal (Agent-to-Agent). Checks hash match and Ed25519 signature.
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | ||
| deal_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It transparently discloses the core behavioral mechanism: hash match and Ed25519 signature verification. It does not cover failure behavior or side effects, but the output schema likely handles return details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short, front-loaded sentences with no filler. The first sentence states the action, and the second provides the key verification details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter tool with an output schema, the description covers the core purpose and mechanism. However, it lacks explicit parameter meanings and usage context, leaving noticeable gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explain deal_id or content beyond their self-evident names. The description does not compensate for the missing parameter documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('verify'), identifies the resource ('a sealed deal'), and states the exact mechanism ('Checks hash match and Ed25519 signature'). This clearly distinguishes it from sibling tools such as seal_content and get_proof_status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'verify a sealed deal' implies the use case, and 'Agent-to-Agent' adds context. However, it does not explicitly state when to use this tool versus alternatives or mention any exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
get_public_keyverify_contentv0.1.1get_proof_statusseal_contentEach tool has a clearly distinct purpose: sealing, status checking, verification, and key retrieval. No two tools overlap in functionality, making tool selection unambiguous.
All tools follow a consistent verb_noun pattern (seal_content, get_proof_status, verify_content, get_public_key). The naming is predictable and uniform across the set.
With only 4 tools, the server is tightly focused on its core purpose of sealing and verifying content. Each tool is essential and contributes to a complete workflow without redundancy.
The tool surface covers the full lifecycle: sealing content, checking its status, verifying, and obtaining the public key for verification. No obvious gaps exist for the stated domain.
Privacy-first document verification anchored to the public ledger.
Prove your AI work existed first: timestamped, Bitcoin-anchored. Free, no account.
AI document intelligence: extract, summarize, claim-check, notarize, and signed action receipts.
Timestamp & verify evidence on-chain, free. Proofpack: a portable BEEF+BUMP proof bundle per txid.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ProofCore-Protocol/proofcore-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
