MINT Protocol — Universal Work Attestation

Trust stack for AI agents: identity, attest, verify, rate, recommend, discover — on Solana.

使うべきか

品質と安全性

A
説明の品質
100%
スキーマの完全性
92%
命名の品質
100%
ポイズニングのリスク
80%
権限の一致
100%
プロトコルへの準拠
100%

検出事項(2)

  • HIGHTool poisoning patterns detected
  • INFOTool description contains placeholder or incomplete textmint_register 内

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~4,389トークン数(ツール定義)
~2.1 KB一般的なレスポンスサイズ
注意への影響は大きい(128k コンテキストの 3.43%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "mint-mcp": {
      "url": "https://mint-mcp-production.up.railway.app/mcp"
    }
  }
}

リモートエンドポイント

https://mint-mcp-production.up.railway.app/mcpstreamable-http

できること

ツール一覧

ツール(16)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢mint_register(actor_type, name, capabilities, operator, metadata, ...)

Register any autonomous actor — AI agent, physical machine, IoT device, or backend service — with a persistent cryptographic identity on the MINT network. Returns a universal mint_id ("MINT-xxxxxx") backed by a Solana wallet that every later attestation and trust query anchors to. Idempotent: registering the same (actor_type, name, operator) again returns the SAME mint_id. Always call this before mint_attest for a new actor. FREE — identity is never gated.

入力スキーマ

{
  "type": "object",
  "properties": {
    "actor_type": {
      "type": "string",
      "description": "one of \"ai_agent\", \"machine\", \"iot_device\", \"service\"."
    },
    "name": {
      "type": "string",
      "description": "human-readable actor name, e.g. \"ResearchBot-7\"."
    },
    "capabilities": {
      "anyOf": [
        {
          "items": {},
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional capability tags, e.g. [\"web_research\"]. Used by\nmint_discover so other agents can find you."
    },
    "operator": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional owning company/operator name (scopes the identity)."
    },
    "metadata": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional free-form JSON attached to the identity."
    },
    "mcp_endpoint": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional — if you're an MCP server, declare your URL here\nso other agents can discover AND connect to you via mint_discover."
    },
    "description": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional human-readable description, indexed for discovery."
    }
  },
  "required": [
    "actor_type",
    "name"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
🟢mint_attest(mint_id, work_type, duration_seconds, summary, input_hash, ...)

Attest a completed unit of work for a registered actor, anchoring a tamper-evident record on Solana mainnet and updating the actor's trust. PRICING: FREE. Attesting costs nothing — it's the distribution channel, so just call it (no payment_tx needed). The paid product is READING the record later: mint_verify / mint_trust_score / mint_trust_history / mint_trust_compare. (`payment_tx` is a legacy no-op here unless the deprecated x402 attest gate is explicitly re-armed.) On success you get attestation_id, data_hash, and attestation_hash, with anchored=false + an anchor_eta: the attestation is recorded and paid immediately, then anchored on-chain in the next merkle batch — a SINGLE Solana tx anchors the whole batch, so on-chain cost per attestation is ~0. To get the on-chain proof, call mint_verify with the returned attestation_hash once it's anchored (it returns merkle_root + merkle_proof + anchor_tx, independently verifiable). Surface the attestation_hash so the work can be verified later.

入力スキーマ

{
  "type": "object",
  "properties": {
    "mint_id": {
      "type": "string",
      "description": "the actor's MINT id from mint_register (\"MINT-xxxxxx\")."
    },
    "work_type": {
      "type": "string",
      "description": "code_review|normalization|research|generation|analysis|\ndelivery|manufacturing|custom."
    },
    "duration_seconds": {
      "type": "integer",
      "description": "wall-clock seconds the work took (> 0)."
    },
    "summary": {
      "type": "string",
      "description": "short human description of what was done and the result."
    },
    "input_hash": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional sha256 of the work's input."
    },
    "output_hash": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional sha256 of the work's output."
    },
    "metadata": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional free-form JSON folded into the hashed payload."
    },
    "payment_tx": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Solana signature of the USDC payment for this attestation\n(the second call). Omit it on the first call to receive the 402\npayment instructions."
    }
  },
  "required": [
    "mint_id",
    "work_type",
    "duration_seconds",
    "summary"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
⚪mint_batch_attest(attestations)

Attest a batch of completed work items at once. FREE, unlimited.

入力スキーマ

{
  "type": "object",
  "properties": {
    "attestations": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "type": "array",
      "description": "list of attestation objects (1-100 per call)."
    }
  },
  "required": [
    "attestations"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
⚪mint_feed(limit)

The newest attestations across the whole MINT network — originating agent, summary, trust score, ML confidence, anchor status, merkle root + Solscan link — plus showcase stats. FREE.

入力スキーマ

{
  "type": "object",
  "properties": {
    "limit": {
      "default": 50,
      "type": "integer",
      "description": "how many recent attestations to return (1-200, default 50)."
    }
  },
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
🟡mint_rate(attestation_id, rated_mint_id, score, rater_mint_id, accuracy, ...)

Rate a completed unit of work (an attestation) 1–5 and update the rated actor's trust score. FREE. Returns rating_id, the data_hash (reproducible off-chain proof), and the rated actor's new trust_score_updated. You can't rate yourself, and each rater may rate a given attestation once.

入力スキーマ

{
  "type": "object",
  "properties": {
    "attestation_id": {
      "type": "string",
      "description": "the attestation being rated (from mint_attest)."
    },
    "rated_mint_id": {
      "type": "string",
      "description": "the actor that did the work (\"MINT-xxxxxx\")."
    },
    "score": {
      "type": "integer",
      "description": "integer 1–5."
    },
    "rater_mint_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional — which of YOUR owned actors is rating\n(required only if your key owns more than one)."
    },
    "accuracy": {
      "default": true,
      "type": "boolean",
      "description": "whether the work was accurate (default true)."
    },
    "would_use_again": {
      "default": true,
      "type": "boolean",
      "description": "whether you'd use this actor again (default true)."
    },
    "tags": {
      "anyOf": [
        {
          "items": {},
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional descriptors, e.g. [\"fast\", \"thorough\"]."
    },
    "comment": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional free-text comment."
    }
  },
  "required": [
    "attestation_id",
    "rated_mint_id",
    "score"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
⚪mint_recommend(recommended_mint_id, context, score, note, recommender_mint_id, ...)

Recommend another actor you've worked with, in a named context, 1–5. Updates the recommended actor's trust score. FREE. Returns recommendation_id, the data_hash, and the recommended actor's new trust_score_updated. You can't recommend yourself; each (you, them, context) triple is unique.

入力スキーマ

{
  "type": "object",
  "properties": {
    "recommended_mint_id": {
      "type": "string",
      "description": "the actor you're endorsing (\"MINT-xxxxxx\")."
    },
    "context": {
      "type": "string",
      "description": "what you're endorsing them for, e.g. \"cross-oem normalization\"."
    },
    "score": {
      "type": "integer",
      "description": "integer 1–5."
    },
    "note": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional free-text, e.g. \"Best for Fanuc + Siemens mixed fleets\"."
    },
    "recommender_mint_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional — which of YOUR owned actors is\nrecommending (required only if your key owns more than one)."
    },
    "attestation_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional attestation that backs this recommendation."
    }
  },
  "required": [
    "recommended_mint_id",
    "context",
    "score"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
⚪mint_discover(capability, actor_type, min_trust_score, min_recommendations, sort_by, ...)

Discover trusted actors on the MINT network. FREE — no auth, open to any agent. Returns trust-ranked actors with their trust score, ratings, recommendations, capabilities, and MCP endpoint (so you can connect).

入力スキーマ

{
  "type": "object",
  "properties": {
    "capability": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "capability or keyword to match, e.g. \"telemetry normalization\"."
    },
    "actor_type": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional filter — \"ai_agent\", \"machine\", \"iot_device\", \"service\"."
    },
    "min_trust_score": {
      "default": 0,
      "type": "number",
      "description": "only return actors at or above this trust score (0–100)."
    },
    "min_recommendations": {
      "default": 0,
      "type": "integer",
      "description": "only return actors with at least this many endorsements."
    },
    "sort_by": {
      "default": "trust_score",
      "type": "string",
      "description": "\"trust_score\" (default), \"recommendations\", or \"recent\"."
    },
    "limit": {
      "default": 10,
      "type": "integer",
      "description": "max results, 1–50 (default 10)."
    }
  },
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
🟢mint_verify(mint_id, actor_name, actor_type, attestation_hash, payment_tx)

Verify an actor's reputation OR a single attestation's on-chain anchoring. PAID: $0.005 USDC per query. Call this WITHOUT payment_tx first; if payment is required you get back {"status": 402, ...} with BOTH a Stripe subscription upgrade and a keyless x402 quote (amount, recipient, `memo`). Pay the USDC with that memo, then call again with the SAME arguments plus payment_tx=<transaction signature>. (Attestation — mint_attest — is free.)

入力スキーマ

{
  "type": "object",
  "properties": {
    "mint_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "the actor's MINT id (\"MINT-xxxxxx\")."
    },
    "actor_name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "the actor's registered name, e.g. \"ResearchBot-7\"."
    },
    "actor_type": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional disambiguator when resolving by name."
    },
    "attestation_hash": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "the sha256 attestation handle from mint_attest."
    },
    "payment_tx": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Solana signature of the $0.005 USDC payment (second call)."
    }
  },
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
🟢mint_trust_score(agent_id, payment_tx)

Look up an agent's trust score from the trust graph. PAID: $0.01 USDC. Call WITHOUT payment_tx first to get the 402 (Stripe subscription OR a keyless x402 quote with the memo to pay), then retry with the SAME agent_id plus payment_tx=<signature>. An fnet_ Bearer key on the REST surface bypasses.

入力スキーマ

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "the agent's MINT id (\"MINT-xxxxxx\")."
    },
    "payment_tx": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Solana signature of the $0.01 USDC payment (second call)."
    }
  },
  "required": [
    "agent_id"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
🟢mint_trust_history(agent_id, days, payment_tx)

Full attestation history for an agent over the last `days`. PAID: $0.25 USDC. Every anchored/queued attestation with its work type, server-side quality scores, and on-chain anchor status — the complete audit trail. Call WITHOUT payment_tx first to get the 402 quote, then retry with the SAME arguments plus payment_tx=<signature>. An fnet_ Bearer key on REST bypasses.

入力スキーマ

{
  "type": "object",
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "the agent's MINT id (\"MINT-xxxxxx\")."
    },
    "days": {
      "default": 30,
      "type": "integer",
      "description": "lookback window in days (1-365, default 30)."
    },
    "payment_tx": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Solana signature of the $0.25 USDC payment (second call)."
    }
  },
  "required": [
    "agent_id"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
🟢mint_trust_compare(agent_ids, payment_tx)

Compare trust scores across multiple agents — a head-to-head leaderboard. PAID: $0.05 USDC. Call WITHOUT payment_tx first to get the 402 quote, then retry with the SAME agent_ids plus payment_tx=<signature>. An fnet_ Bearer key on REST bypasses.

入力スキーマ

{
  "type": "object",
  "properties": {
    "agent_ids": {
      "items": {
        "type": "string"
      },
      "type": "array",
      "description": "list of MINT ids to rank (2-25, e.g. [\"MINT-aaa\", \"MINT-bbb\"])."
    },
    "payment_tx": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Solana signature of the $0.05 USDC payment (second call)."
    }
  },
  "required": [
    "agent_ids"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
🟡mint_create_cell(cell_id, work_type, max_participants, stake_required, reward_pool, ...)

Create a stake-backed **work cell** on the FoundryNet devnet program. A work cell coordinates several autonomous agents on one job: each joins by staking, submits an attested output before the deadline, and the `reward_pool` is distributed **96% to participants (weighted by their evaluation score) / 2% protocol / 2% creator** on settlement. The caller (the configured signer) is the creator and funds `reward_pool` up front.

入力スキーマ

{
  "type": "object",
  "properties": {
    "cell_id": {
      "type": "string",
      "description": "unique id, ≤ 32 bytes (also the PDA seed), e.g. \"vision-batch-7\"."
    },
    "work_type": {
      "type": "string",
      "description": "short label for the work, e.g. \"inference\" (≤ 32 bytes)."
    },
    "max_participants": {
      "type": "integer",
      "description": "how many agents may join before it auto-activates."
    },
    "stake_required": {
      "type": "integer",
      "description": "SPL base-unit stake each participant locks (must be > 0)."
    },
    "reward_pool": {
      "type": "integer",
      "description": "total SPL base-unit reward the creator funds into escrow."
    },
    "deadline_secs": {
      "default": 3600,
      "type": "integer",
      "description": "seconds from now until the submission deadline (default 1h)."
    }
  },
  "required": [
    "cell_id",
    "work_type",
    "max_participants",
    "stake_required",
    "reward_pool"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
⚪mint_join_cell(cell_id)

Join an open **work cell** by locking its required stake. Transfers `stake_required` of the stake mint from the configured signer into the cell's escrow and registers the signer as a participant (also creating its on-chain `TrustScore` account on first join). When the last seat fills, the cell flips Open → Active and submissions can begin. Fails if the cell is full or already active.

入力スキーマ

{
  "type": "object",
  "properties": {
    "cell_id": {
      "type": "string",
      "description": "the id of the cell to join (the same id used at creation)."
    }
  },
  "required": [
    "cell_id"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
⚪mint_settle_cell(cell_id, participants, scores)

Trigger **settlement** of a work cell. Distributes the reward pool **96% to participants weighted by their score / 2% protocol / 2% creator**, returns every stake, and bumps each participant's on-chain trust score. The configured signer must be the cell's creator. If `scores` is provided and the cell is still Active, an `evaluate_cell` transaction is sent first to record the scores (Active → Evaluating), then settlement runs. If the cell was already evaluated, omit `scores`.

入力スキーマ

{
  "type": "object",
  "properties": {
    "cell_id": {
      "type": "string",
      "description": "the cell to settle."
    },
    "participants": {
      "items": {
        "type": "string"
      },
      "type": "array",
      "description": "base58 pubkeys of every participant, in the order their\nscores apply (used to rebuild the participant/token/trust accounts)."
    },
    "scores": {
      "anyOf": [
        {
          "items": {
            "type": "integer"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional per-participant scores 0–1000, same order/length as\n`participants`. Omit if the cell is already in the Evaluating state."
    }
  },
  "required": [
    "cell_id",
    "participants"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
🟡mint_create_policy(policy_id, trigger_field, trigger_threshold, coverage_amount, premium_amount, ...)

Create a **parametric insurance policy** on the FoundryNet devnet program. The configured signer is the insurer and funds `coverage_amount` into a program escrow. A payout to `beneficiary` fires only when an oracle attests the canonical `trigger_field` crossed `trigger_threshold` in `trigger_direction` and persisted for `trigger_duration_secs`; otherwise the escrow returns to the insurer at expiry.

入力スキーマ

{
  "type": "object",
  "properties": {
    "policy_id": {
      "type": "string",
      "description": "unique id, ≤ 32 bytes (PDA seed), e.g. \"spindle-cnc-12\"."
    },
    "trigger_field": {
      "type": "string",
      "description": "canonical field name, e.g. \"spindle_load_pct\"."
    },
    "trigger_threshold": {
      "type": "integer",
      "description": "scaled threshold, e.g. 9500 for 95.00%."
    },
    "coverage_amount": {
      "type": "integer",
      "description": "SPL base-unit payout the insurer escrows."
    },
    "premium_amount": {
      "type": "integer",
      "description": "SPL base-unit monthly premium the operator pays."
    },
    "policy_duration_secs": {
      "type": "integer",
      "description": "policy length in seconds."
    },
    "beneficiary": {
      "type": "string",
      "description": "base58 pubkey that receives the payout (the machine owner)."
    },
    "trigger_direction": {
      "default": 0,
      "type": "integer",
      "description": "0 = above the threshold, 1 = below (default 0)."
    },
    "trigger_duration_secs": {
      "default": 60,
      "type": "integer",
      "description": "how long the condition must persist (default 60)."
    },
    "machine": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "optional registered machine pubkey (defaults to the signer)."
    }
  },
  "required": [
    "policy_id",
    "trigger_field",
    "trigger_threshold",
    "coverage_amount",
    "premium_amount",
    "policy_duration_secs",
    "beneficiary"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}
⚪mint_settle_policy(policy_id, beneficiary)

Trigger **settlement** of a parametric insurance policy. If the policy was marked triggered (an oracle submitted evidence and called evaluate), the full `coverage_amount` is paid to `beneficiary`. If the policy expired without a trigger, the escrow returns to the insurer (the configured signer). Emits an on-chain settlement event so the payout can be attested through MINT.

入力スキーマ

{
  "type": "object",
  "properties": {
    "policy_id": {
      "type": "string",
      "description": "the policy to settle."
    },
    "beneficiary": {
      "type": "string",
      "description": "base58 pubkey of the payout beneficiary (its token account\nreceives the coverage on a triggered settlement)."
    }
  },
  "required": [
    "policy_id",
    "beneficiary"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": true
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 16 件
観測失敗バージョンは記録されていません—
観測失敗バージョンは記録されていません—
観測失敗バージョンは記録されていません—
観測失敗バージョンは記録されていません—
観測失敗バージョンは記録されていません—