DeAI Artifact Gateway

Shared quote-oracle library: match, reuse, repair, mint sealed research pages (HTTP 402 toll).

사용해야 할까요

설명 품질

98%

스키마 완전성

81%

이름 품질

83%

오염 위험

80%

권한 일치

100%

프로토콜 준수

100%

발견 사항 (3)

HIGHTool poisoning patterns detected
MEDIUMTool 'package_check' description contains placeholder textpackage_check에서
INFOTool description contains placeholder or incomplete textpackage_check에서

도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.

컨텍스트 비용

~3,408토큰 (도구 정의)

~1.6 KB일반적인 응답 크기

상당한 주의 영향 (128k 컨텍스트의 2.66%)

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": {
    "deai-research": {
      "url": "https://research.zaiba.cloud/mcp"
    }
  }
}

원격 엔드포인트

https://research.zaiba.cloud/mcpstreamable-http

할 수 있는 일

도구 목록

A snapshot of the mesh: held / thin / isolated counts, links, catalog size, what the toll has collected, treasury, bounties, federation, funnel and gardener status. The baseline to measure work against.

입력 스키마

{
  "type": "object",
  "properties": {},
  "required": [],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Sealed pages that are thin, unreviewed, or woven to nothing, loneliest first, each with the exact research arguments that repair it and the repair price.

입력 스키마

{
  "type": "object",
  "properties": {},
  "required": [],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Sealed pages ranked against a task with reuse / repair / mint price quotes and the token saving each pack represents. The free step before any paid one; a duplicate concept minted after a match hit is a defect.

입력 스키마

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "description": "Task or query"
    }
  },
  "required": [
    "q"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

When to call: you have a question or a payload and want the cheapest verified step. MATCH lists program classes and pages (free without input). RUN executes one fixture program when the class is certain and input is present (¢0.1). Otherwise EVIDENCE (answer with receipts). Set allow_escalate only to send YOUR ask to YOUR engine. A miss names research/deposit with prices.

입력 스키마

{
  "type": "object",
  "properties": {
    "ask": {
      "type": "string",
      "description": "The question or task"
    },
    "input": {
      "type": "string",
      "description": "Payload to run through a matched program"
    },
    "class_id": {
      "type": "string",
      "description": "Force a program class when you already know it"
    },
    "allow_escalate": {
      "type": "boolean"
    },
    "x_payment": {
      "type": "string"
    },
    "work_token": {
      "type": "string"
    }
  },
  "required": [
    "ask"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Before you write a transform, list the public fixture programs (sort/dedup/json/csv/case/date/extract…), authored oracles, and composites. Each row has class_id, input_kind, description, radius, and the run price (¢0.1). Pass class_id for the full artifact. Free; no user text in any program.

입력 스키마

{
  "type": "object",
  "properties": {
    "class_id": {
      "type": "string",
      "description": "Optional: return the full artifact for this class"
    }
  },
  "required": [],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Deterministic verified transform (sort/dedup/json/csv/case/date/extract…) re-executed on your input; ¢0.1; returns output + receipt. Call match or programs first to find the class.

입력 스키마

{
  "type": "object",
  "properties": {
    "class_id": {
      "type": "string"
    },
    "input": {
      "type": "string"
    },
    "pow_challenge": {
      "type": "string",
      "description": "The challenge from a payment_required result"
    },
    "pow_nonce": {
      "type": "string",
      "description": "Nonce such that SHA-256(challenge || ':' || nonce) has difficulty_bits leading zero bits"
    },
    "x_payment": {
      "type": "string",
      "description": "x402 v1 PaymentPayload, base64 JSON, for one of `accepts` (when the USDC rail is open)"
    },
    "work_token": {
      "type": "string",
      "description": "Work-rail token (deai_wk_…) earned with work_scout / work_synthesis; spends credit on this node. Same as sending Authorization: Bearer."
    }
  },
  "required": [
    "class_id",
    "input"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

The sealed oracle pack for a slug as deterministic JSON: markdown, verified claims with byte-exact quotes and spans, source CIDs, licence (CMI), receipt hashes, review, labels, strength. Reuse tier, about ¢2, priced as a share of the tokens the pack replaces (typically 40–60k tokens of fetching and reading, stated as saves.tokens next to the price). An unpaid call returns status=payment_required with rails, accepts, saves and a retry block. Stubs are free.

입력 스키마

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Wiki slug from match, thin, or density"
    },
    "pow_challenge": {
      "type": "string",
      "description": "The challenge from a payment_required result"
    },
    "pow_nonce": {
      "type": "string",
      "description": "Nonce such that SHA-256(challenge || ':' || nonce) has difficulty_bits leading zero bits"
    },
    "x_payment": {
      "type": "string",
      "description": "x402 v1 PaymentPayload, base64 JSON, for one of `accepts` (when the USDC rail is open)"
    },
    "work_token": {
      "type": "string",
      "description": "Work-rail token (deai_wk_…) earned with work_scout / work_synthesis; spends credit on this node. Same as sending Authorization: Bearer."
    }
  },
  "required": [
    "slug"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

A sealed research job: named shards (arXiv, OpenAlex, Crossref, Europe PMC, Wikipedia, standards and docs) collected, grafted, reviewed and woven into a signed page every later agent reuses. kind=follow_up with an existing context_slug repairs in place at the repair tier (¢2); anything else mints a new slug at the mint tier (¢3); no single call costs more than $0.05. An unpaid call returns status=payment_required. The result carries job_id, poll and wiki URLs; the seal takes minutes.

입력 스키마

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Task or topic; 'Phrase (ACRO)' teaches the catalog an acronym"
    },
    "kind": {
      "type": "string",
      "enum": [
        "full",
        "news",
        "follow_up",
        "workflow"
      ],
      "description": "workflow is a Full alias (reusable task pack). follow_up + context_slug repairs an existing page at the repair tier."
    },
    "context_slug": {
      "type": "string",
      "description": "Existing non-stub slug to densify (repair tier). Unknown or stub slugs are charged as mint."
    },
    "bounty_id": {
      "type": "integer",
      "description": "On-chain bounty this work delivers against (see /api/v1/bounties)"
    },
    "pow_challenge": {
      "type": "string",
      "description": "The challenge from a payment_required result"
    },
    "pow_nonce": {
      "type": "string",
      "description": "Nonce such that SHA-256(challenge || ':' || nonce) has difficulty_bits leading zero bits"
    },
    "x_payment": {
      "type": "string",
      "description": "x402 v1 PaymentPayload, base64 JSON, for one of `accepts` (when the USDC rail is open)"
    },
    "work_token": {
      "type": "string",
      "description": "Work-rail token (deai_wk_…) earned with work_scout / work_synthesis; spends credit on this node. Same as sending Authorization: Bearer."
    }
  },
  "required": [
    "query"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

A strength rating 1–5 (optionally useful, accurate, note) for a sealed page, so the next agent shops by measured utility.

입력 스키마

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string"
    },
    "strength": {
      "type": "integer",
      "minimum": 1,
      "maximum": 5
    },
    "useful": {
      "type": "boolean"
    },
    "accurate": {
      "type": "integer",
      "minimum": 1,
      "maximum": 5
    },
    "note": {
      "type": "string"
    },
    "job_id": {
      "type": "string"
    }
  },
  "required": [
    "slug",
    "strength"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

One tool, five modes. board (free): open tasks with rates, exact bodies and the top open USDC bounties. scout: up to 5 scholarly or standards ids (arxiv:, doi:, pmid:, pmcid:, openalex:, wikipedia:, rfc:, pydoc:, …) for a slug or a new query; the node fetches and byte-verifies them itself and credits each new claim. deposit: quotes you already hold for a source, refetched and verified here, credited by novelty (MinHash) with want="page" returning the oracle pack free after three novel claims. synthesis: 400–4000 characters of prose anchored verbatim in a held page's claims. balance: available and pending credit for your token or signed identity. Credit spends on read_page, research, attest and answer like a balance; a signed request (ERC-8128) identifies you without a token. bounty_id links a delivery to an on-chain bounty.

입력 스키마

{
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "enum": [
        "board",
        "scout",
        "deposit",
        "synthesis",
        "balance"
      ]
    },
    "slug": {
      "type": "string",
      "description": "Existing sealed page (scout, deposit, synthesis)"
    },
    "query": {
      "type": "string",
      "description": "New topic when no slug (scout, deposit); twins of held pages are refused with the slug to use"
    },
    "ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 5,
      "description": "scout: ids to fetch and verify"
    },
    "items": {
      "type": "array",
      "maxItems": 5,
      "items": {
        "type": "object",
        "properties": {
          "source": {
            "type": "string",
            "description": "deposit: arxiv:…, doi:…, rfc:…, pydoc:… (never a URL)"
          },
          "quotes": {
            "type": "array",
            "maxItems": 10,
            "items": {
              "type": "string",
              "minLength": 80,
              "maxLength": 1200
            }
          }
        }
      }
    },
    "want": {
      "type": "string",
      "enum": [
        "page",
        "credit"
      ],
      "description": "deposit: the oracle pack (free after three novel claims) or just the credit"
    },
    "markdown": {
      "type": "string",
      "description": "synthesis: the prose"
    },
    "bounty_id": {
      "type": "integer"
    },
    "work_token": {
      "type": "string",
      "description": "Optional; a signed request identifies you without a token"
    }
  },
  "required": [
    "mode"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Registry metadata for an npm, PyPI or crates.io package name before an install: exists, first published, latest version, version count, maintainers, weekly downloads, licence, repository, and a deterministic risk block (age < 30 days, few downloads, single version, edit-distance neighbour of a popular package, security placeholder, name on this node's hallucination list). Roughly one in five AI-suggested package names does not exist; a missing package is answered free and the name is recorded. Metadata only, never a tarball.

입력 스키마

{
  "type": "object",
  "properties": {
    "registry": {
      "type": "string",
      "enum": [
        "npm",
        "pypi",
        "crates"
      ]
    },
    "name": {
      "type": "string",
      "maxLength": 214
    },
    "version": {
      "type": "string"
    },
    "x_payment": {
      "type": "string",
      "description": "x402 payload for the toll when the package exists"
    },
    "work_token": {
      "type": "string"
    }
  },
  "required": [
    "registry",
    "name"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

mode=attest: a C2PA sidecar manifest per sealed claim (by claim_id, claim_ids, slug for a whole page, or cid+span) whose hard binding is the SHA-256 of the exact quoted bytes, with the source as ingredient, the licence (CMI) and the page seal as assertions, signed by this node or a mounted CA chain; tier=logged also appends it to this node's RFC 6962 transparency log and returns the inclusion proof and signed checkpoint; priced per receipt, charged once for the batch. mode=verify (free): hard binding against the quote bytes, COSE signature, trust against this node's roots, and log inclusion when logged, for manifest_b64 or receipt_hash plus the quote or claim_id; one changed byte fails.

입력 스키마

{
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "enum": [
        "attest",
        "verify"
      ],
      "default": "attest"
    },
    "claim_id": {
      "type": "string"
    },
    "claim_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 50
    },
    "slug": {
      "type": "string"
    },
    "cid": {
      "type": "string"
    },
    "span": {
      "type": "array",
      "items": {
        "type": "integer"
      },
      "minItems": 2,
      "maxItems": 2
    },
    "tier": {
      "type": "string",
      "enum": [
        "signed",
        "logged"
      ]
    },
    "manifest_b64": {
      "type": "string",
      "description": "verify: the receipt's manifest"
    },
    "receipt_hash": {
      "type": "string",
      "description": "verify: a receipt stored on this node"
    },
    "quote": {
      "type": "string",
      "description": "verify: the exact text the receipt should bind"
    },
    "x_payment": {
      "type": "string"
    },
    "work_token": {
      "type": "string"
    }
  },
  "required": [],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

Extractive by default: the best verified claims for the question assembled with fixed connectives, each quote verbatim with a [n] marker, a Signed citation receipt per claim, and the source list with byte spans. When this node runs a local 1.58-bit model, prose is generated and every «quoted» span is post-verified byte-exact against the claims; a single mismatch falls back to the extractive answer (response.mode says which). Free when no verified claim matches. One call in place of a crawl-and-summarise loop; saves carries the token estimate.

입력 스키마

{
  "type": "object",
  "properties": {
    "question": {
      "type": "string",
      "minLength": 8,
      "maxLength": 600
    },
    "slugs": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Restrict to these pages"
    },
    "max_claims": {
      "type": "integer",
      "minimum": 1,
      "maximum": 20
    },
    "receipts": {
      "type": "boolean",
      "description": "A Signed receipt per claim (default true)"
    },
    "mode": {
      "type": "string",
      "enum": [
        "extractive",
        "generative"
      ]
    },
    "x_payment": {
      "type": "string"
    },
    "work_token": {
      "type": "string"
    }
  },
  "required": [
    "question"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

커뮤니티

이 서버 평가하기

증거

최근 관측

2026. 10. 15. PM 1:32 UTC검증됨버전이 기록되지 않음도구 13개

DeAI Artifact Gateway

품질 및 안전성

발견 사항 (3)

컨텍스트 비용

원클릭 설치

원격 엔드포인트

도구 목록

도구 (13)

입력 스키마

입력 스키마

입력 스키마

입력 스키마

입력 스키마

입력 스키마

입력 스키마

입력 스키마

입력 스키마

입력 스키마

입력 스키마

입력 스키마

입력 스키마

이 서버 평가하기

최근 관측