제3자 인증 프록시 — 모든 HTTP 호출에 대해 독립적인 암호학적 증명을 얻으세요.
AI 에이전트, 웹훅, 마이크로서비스 또는 모든 HTTP 클라이언트와 함께 작동합니다. 이 증명은 호출자가 아닌 ArkForge(독립적인 제3자)에 의해 서명됩니다.
시스템이 HTTP 호출을 수행할 때, 무엇이 전송되었고 무엇이 수신되었는지, 또는 언제 발생했는지에 대한 독립적인 기록이 없습니다. 양측 모두 거래를 부인하거나 변경할 수 있습니다.
ArkForge는 인증 프록시 역할을 하여 이를 해결합니다. 호출자가 ArkForge를 통해 요청을 라우팅하면, ArkForge는 전체 요청+응답 번들을 Ed25519 키로 서명하고, RFC 3161을 통해 타임스탬프를 찍으며, 변경 불가능하고 공개적으로 감사 가능한 로그인 Sigstore Rekor에 고정합니다.
결과로 생성된 증명은 ArkForge에 연락할 필요 없이 누구나 공개 URL에서 영구적으로 검증할 수 있습니다.
이는 자체 서명 인증서와 CA 발급 인증서의 차이와 같습니다. 다른 도구들은 호출자 자신이 서명한 증명을 생성하지만, ArkForge는 독립적인 제3자가 서명한 증명을 생성합니다.
Related MCP server: AGA-mcp-server
AI 에이전트 — 모든 외부 API 호출(Claude, GPT, Mistral, LangChain, AutoGen)에 대한 감사 추적
웹훅 — Stripe 또는 GitHub 이벤트가 정확한 페이로드와 함께 수신되었음을 증명
마이크로서비스 — 내부 서비스 간의 위변조 방지 로그(규정 준수, 핀테크)
데이터 제공자 — 외부 API가 특정 타임스탬프에 해당 값을 반환했음을 증명
자동화 — n8n 또는 Zapier 워크플로우에서의 작업 인증
{
"mcpServers": {
"arkforge": {
"command": "uvx",
"args": ["arkforge-mcp"],
"env": {
"ARKFORGE_API_KEY": "your_api_key_here"
}
}
}
}arkforge.tech에서 무료 API 키(월 500회 증명)를 받으세요.
certify_callHTTP 호출을 ArkForge를 통해 라우팅하고 거래에 대한 암호학적 증명을 받습니다.
target URL of the upstream API to call
payload JSON body (optional)
method "POST" or "GET" (default: "POST")
description Human-readable description included in the proof
agent_identity Identifier for the calling system (optional)proof_id, verification_url, upstream_response, chain_hash, timestamp 및 Ed25519 signature를 반환합니다.
감사 가능한 기록이 필요할 때 API를 직접 호출하는 대신 이 도구를 사용하세요.
응답 예시:
{
"proof_id": "prf_20260310_143022_a1b2c3",
"verification_url": "https://trust.arkforge.tech/v1/proof/prf_20260310_143022_a1b2c3",
"upstream_response": { "status": "ok" },
"chain_hash": "e3b0c44298fc1c149afb...",
"timestamp": "2026-03-10T14:30:22.481Z",
"timestamp_authority": "verified",
"rekor_log_id": "https://rekor.sigstore.dev/api/v1/log/entries/...",
"seller": "api.example.com",
"signature": "MCowBQYDK2VwAyEA..."
}get_proof주어진 proof_id에 대한 전체 증명 번들을 검색합니다.
verify_proof증명이 무엇을 인증하는지에 대한 사람이 읽을 수 있는 요약을 가져옵니다. 사용자나 감사자에게 독립적으로 검증된 내용을 설명할 때 유용합니다.
get_usage현재 달의 남은 크레딧을 확인합니다.
필드 | 설명 |
| 고유 식별자 — 영구 공개 URL |
| 전송된 정확한 요청의 SHA-256 |
| 수신된 정확한 응답의 SHA-256 |
| 결합된 해시 — 위변조 방지 |
| 호출된 API의 도메인 |
| FreeTSA를 통한 RFC 3161 타임스탬프 (엔터프라이즈의 경우 QTSP eIDAS) |
| Sigstore Rekor 변경 불가능한 로그 항목 |
| ArkForge의 독립적인 키에 의한 Ed25519 서명 |
플랜 | 증명/월 | 가격 |
무료 | 500 | €0 |
프로 | 5,000 | €29/월 |
엔터프라이즈 | 50,000 + QTSP eIDAS | €149/월 |
MCP 서버는 하나의 통합 경로입니다. 동일한 API가 모든 언어나 프레임워크에서 작동합니다:
curl -X POST https://trust.arkforge.tech/v1/proxy \
-H "X-Api-Key: your_key" \
-H "Content-Type: application/json" \
-d '{"target": "https://api.example.com/action", "payload": {"data": "value"}}'Call an external API and get a cryptographic proof of the transaction.
Use this INSTEAD of calling the API directly when you need an auditable, tamper-evident record of what was sent and received.
The proof is signed by ArkForge (independent third party), timestamped via RFC 3161, and anchored in Sigstore Rekor — not self-signed by your agent.
Args: target: URL of the upstream API to call (e.g. "https://api.example.com/v1/action") payload: JSON body to send to the upstream API (optional for GET requests) method: HTTP method — "POST" or "GET" (default: "POST") description: Human-readable description of what this call does (included in the proof) agent_identity: Identifier for the calling agent (optional, included in the proof)
Returns: JSON with proof_id, verification_url, the upstream API response, chain_hash, and timestamp. Share verification_url with any third party to let them independently verify what happened.
| Name | Required | Description | Default |
|---|---|---|---|
| target | Yes | ||
| payload | No | ||
| method | No | POST | |
| description | No | ||
| agent_identity | No |
| 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 of behavioral disclosure. It effectively explains key traits: it calls an external API, generates a signed proof by ArkForge (third-party), includes timestamping and anchoring, and returns verification details. However, it lacks information on error handling, rate limits, or authentication needs for the target API, leaving some gaps in behavioral context.
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 well-structured and front-loaded with the core purpose, followed by usage guidelines, parameter explanations, and return details. Every sentence adds value—no redundancy or fluff—and it efficiently covers necessary information in a compact format.
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 tool's complexity (external API calls with proof generation), no annotations, and an output schema present, the description is highly complete. It explains the purpose, usage context, parameters, and return values in detail, compensating for the lack of annotations and leveraging the output schema to avoid over-explaining returns. This suffices for effective agent use.
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 adds meaningful semantics for all parameters: target is the 'URL of the upstream API', payload is the 'JSON body to send', method specifies 'HTTP method', description is 'Human-readable description', and agent_identity is an 'Identifier for the calling agent'. This clarifies usage beyond basic schema titles, though it doesn't detail format constraints (e.g., URL validation).
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 tool's purpose: 'Call an external API and get a cryptographic proof of the transaction.' It specifies the verb ('call'), resource ('external API'), and unique outcome ('cryptographic proof'), distinguishing it from sibling tools like get_proof, get_usage, and verify_proof, which focus on retrieving or verifying proofs rather than creating them.
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 description explicitly states when to use this tool: 'Use this INSTEAD of calling the API directly when you need an auditable, tamper-evident record of what was sent and received.' This provides clear guidance on the alternative (direct API calls) and the specific context (need for proof), helping the agent choose correctly among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the full cryptographic proof for a given proof ID.
Returns the complete proof bundle: request/response hashes, parties, RFC 3161 timestamp, Sigstore Rekor log entry, and archive.org snapshot.
Args: proof_id: The proof identifier (e.g. "prf_20260310_143022_a1b2c3")
| Name | Required | Description | Default |
|---|---|---|---|
| proof_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 of behavioral disclosure. It describes what the tool returns (complete proof bundle with specific components) which is valuable context beyond the input schema. However, it doesn't mention performance characteristics, error conditions, authentication requirements, or rate limits, which would be helpful for a retrieval operation.
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 perfectly structured: a clear purpose statement followed by return value details, then parameter documentation. Every sentence earns its place with zero waste. The information is front-loaded with the core functionality stated first.
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 tool has an output schema (which handles return value documentation) and only one parameter, the description provides adequate context. It explains what the tool does, what it returns, and documents the parameter with an example. For a simple retrieval tool, this is reasonably complete, though additional behavioral context would improve it.
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 schema has 0% description coverage, so the description must compensate. It provides a clear explanation of the single parameter ('proof_id') including its purpose and an example format ('prf_20260310_143022_a1b2c3'), adding significant meaning beyond the bare schema. The example format helps users understand the expected input pattern.
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 specific action ('Retrieve') and resource ('full cryptographic proof for a given proof ID'), distinguishing it from siblings like 'certify_call' (create), 'get_usage' (usage stats), and 'verify_proof' (validation). The verb+resource combination is precise and unambiguous.
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 description implies usage context by specifying 'for a given proof ID', suggesting this tool is for retrieving existing proofs rather than creating or verifying them. However, it doesn't explicitly state when to use this versus alternatives like 'verify_proof' or provide exclusion criteria, leaving some ambiguity about tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check your ArkForge API usage and remaining credits for the current period.
Returns your tier (Free / Pro / Enterprise), proofs used, proofs remaining, and the reset date.
| 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 provided, so the description carries the full burden of behavioral disclosure. It describes what the tool returns (tier, proofs used, proofs remaining, reset date), which is helpful. However, it doesn't mention critical behavioral traits like whether this is a read-only operation, if it requires authentication, or any rate limits. The description adds some value but leaves gaps in behavioral context.
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 concise and well-structured, consisting of two sentences that efficiently convey the tool's purpose and return values. Every sentence adds value without unnecessary details, making it easy to understand at a glance.
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 that the tool has 0 parameters, 100% schema coverage, and an output schema exists, the description is reasonably complete. It explains what the tool does and what it returns, which is sufficient for a simple read operation. However, it could be more complete by addressing authentication or usage context, especially since no annotations are provided.
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 has 0 parameters, and the schema description coverage is 100%, so there's no need for parameter details in the description. The baseline for this scenario is 4, as the description appropriately focuses on the tool's purpose and output without redundant parameter information.
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 tool's purpose: 'Check your ArkForge API usage and remaining credits for the current period.' It specifies the verb ('check') and resource ('API usage and remaining credits'), making it easy to understand what the tool does. However, it doesn't explicitly distinguish itself from sibling tools like 'certify_call', 'get_proof', or 'verify_proof', which prevents a perfect score.
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 description provides no guidance on when to use this tool versus alternatives. It doesn't mention any prerequisites, such as authentication requirements, or compare it to sibling tools. The only implied usage is checking API usage, but there's no explicit context for when this is necessary or appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a human-readable summary of what a proof certifies.
Useful for explaining to a user or auditor what was independently verified, without reading raw JSON.
Args: proof_id: The proof identifier (e.g. "prf_20260310_143022_a1b2c3")
| Name | Required | Description | Default |
|---|---|---|---|
| proof_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 discloses that the output is 'human-readable' and summarizes verification details, which adds value beyond the schema. However, it lacks details on permissions, rate limits, or error handling, leaving behavioral gaps for a tool with no annotation coverage.
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 appropriately sized and front-loaded: the first sentence states the core purpose, followed by usage context and parameter details. Every sentence earns its place with no wasted words, making it efficient and easy to parse.
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 tool's low complexity (1 parameter) and the presence of an output schema (which handles return values), the description is mostly complete. It covers purpose, usage, and parameter semantics well. However, with no annotations, it could benefit from more behavioral details like authentication or error scenarios, slightly reducing completeness.
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 description adds significant meaning beyond the input schema, which has 0% description coverage. It explains that 'proof_id' is 'The proof identifier' and provides an example format ('e.g. "prf_20260310_143022_a1b2c3"'), clarifying the parameter's purpose and expected syntax, fully compensating for the schema's lack of 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 clearly states the specific action ('Get a human-readable summary') and resource ('what a proof certifies'), distinguishing it from sibling tools like 'get_proof' (which likely returns raw data) and 'certify_call' (which creates proofs). The purpose is explicit and differentiated.
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 description provides clear context for when to use this tool: 'Useful for explaining to a user or auditor what was independently verified, without reading raw JSON.' This implies it should be used for human consumption rather than programmatic access. However, it does not explicitly state when not to use it or name alternatives like 'get_proof'.
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.
v1.0.0certify_callget_proofget_usageverify_proofScored across 4 tools
Each tool has a distinct and non-overlapping purpose: certify_call creates proofs, get_proof retrieves raw proof data, get_usage checks account status, and verify_proof provides human-readable summaries. There is no ambiguity about when to use which tool, as they target different stages of the proof lifecycle and administrative functions.
All tools follow a consistent verb_noun pattern with clear, descriptive names: certify_call, get_proof, get_usage, and verify_proof. The naming is uniform, using snake_case throughout, and the verbs (certify, get, verify) accurately reflect the actions without mixing conventions.
With 4 tools, this server is well-scoped for its purpose of providing cryptographic proof and verification services. Each tool serves a clear role in the workflow—creating, retrieving, verifying proofs, and managing usage—without being overly sparse or bloated, making it efficient for agents to navigate.
The tool set covers the core lifecycle of proof creation, retrieval, and verification, along with administrative usage checks. A minor gap exists in the lack of tools for managing or deleting proofs, but this does not hinder basic operations, and agents can still perform essential tasks without dead ends.
Attestation infrastructure for the agentic economy: signed, independently verifiable verdicts.
Issue signed receipts for AI agent actions; verify any receipt offline - free, no account.
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
Signed attestations for agents, $0.01/call via x402: URL witness, AI permission, tx finality, JWKS.
