Crinkl Commerce MCP

Verified commerce data and proof-backed shopper activation tools for agents.

我該用這個嗎

品質與安全性

A
說明品質
100%
結構描述完整度
75%
命名品質
67%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

發現項目(22)

  • LOWTool 'get-protocol-summary' doesn't follow camelCase/snake_case在 get-protocol-summary 中
  • LOWTool 'get-cumulative-gmv' doesn't follow camelCase/snake_case在 get-cumulative-gmv 中
  • LOWTool 'get-daily-gmv' doesn't follow camelCase/snake_case在 get-daily-gmv 中
  • LOWTool 'get-trailing-gmv' doesn't follow camelCase/snake_case在 get-trailing-gmv 中
  • LOWTool 'get-spend-signals' doesn't follow camelCase/snake_case在 get-spend-signals 中
  • LOWTool 'resolve-cbsa' doesn't follow camelCase/snake_case在 resolve-cbsa 中
  • LOWTool 'get-merchant-summary' doesn't follow camelCase/snake_case在 get-merchant-summary 中
  • LOWTool 'get-spend-distribution' doesn't follow camelCase/snake_case在 get-spend-distribution 中
  • LOWTool 'get-settlement-summary' doesn't follow camelCase/snake_case在 get-settlement-summary 中
  • LOWTool 'get-gmv-inclusion-proof' doesn't follow camelCase/snake_case在 get-gmv-inclusion-proof 中

根據工具定義與協定合規性的自動化分析。

上下文成本

~3,019Token(工具定義)
~681 B典型回應大小
顯著的注意力影響(128k 上下文的 2.36%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "crinkl-commerce": {
      "url": "https://mcp.crinkl.xyz/mcp"
    }
  }
}

遠端端點

https://mcp.crinkl.xyz/mcpstreamable-http

它能做什麼

工具清單

工具(22)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢get-protocol-summary

Get a concise explanation of what Crinkl is and how the protocol works. Use this first if you have no prior context about Crinkl. Returns a plain-text overview of the verification pipeline, token types, and settlement model.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-cumulative-gmv(startDate, asOfDate)

Get cumulative Gross Merchandise Value (GMV) from the public cumulative feed. The live Crinkl site displays this live beta cumulative total on top of the finalized alpha base; provide startDate to bound the window explicitly. Returns a cryptographically signed token containing total USD cents, spend count, and computation timestamp.

輸入結構描述

{
  "type": "object",
  "properties": {
    "startDate": {
      "type": "string",
      "description": "Optional ISO date (YYYY-MM-DD) to start counting from. The live beta cumulative feed uses 2026-01-27."
    },
    "asOfDate": {
      "type": "string",
      "description": "Optional ISO date to compute GMV as of (defaults to now)"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-daily-gmv(date)

Get the signed GMV summary for a specific calendar date (UTC). Returns the verified spend count, total USD cents, and a cryptographic signature from the Crinkl authority. Each daily GMV token is independently verifiable using the issuer's Ed25519 public key.

輸入結構描述

{
  "type": "object",
  "properties": {
    "date": {
      "type": "string",
      "description": "UTC date in YYYY-MM-DD format"
    }
  },
  "required": [
    "date"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-trailing-gmv(days)

Get a rolling N-day GMV trend summary. Returns daily verified GMV figures for the trailing window, enabling trend analysis of verified commerce volume. Each day's figure is backed by individually signed spend attestation tokens.

輸入結構描述

{
  "type": "object",
  "properties": {
    "days": {
      "type": "number",
      "description": "Number of trailing days (default 7, max 90)"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-spend-signals(limit)

Get recent verified spend activity signals from the Crinkl network. Each signal represents a cryptographically attested receipt that has passed OCR extraction, store resolution, and hard verification. Signals include store name, category (e.g. Grocery & Supermarkets, Gas & Convenience), CBSA metro code, and spend amount — but no personally identifiable information. Use resolve-cbsa to convert CBSA codes to metro area names.

輸入結構描述

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "description": "Number of recent signals to return (default 20, max 50)"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪resolve-cbsa(code)

Resolve a CBSA (Core Based Statistical Area) code to its metro area name. CBSA codes appear in spend signals and distribution data as 5-digit codes (e.g. '35620'). This tool converts them to human-readable names (e.g. '35620' → 'New York-Newark-Jersey City, NY-NJ'). Also handles non-metro codes like 'non-metro:US-TN'.

輸入結構描述

{
  "type": "object",
  "properties": {
    "code": {
      "type": "string",
      "description": "The CBSA code to resolve (e.g. '35620' or 'non-metro:US-TX')"
    }
  },
  "required": [
    "code"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-merchant-summary

Get aggregated merchant and category distribution across all verified spends. Shows top store brands, category breakdown (grocery, restaurant, gas, etc.), and spend concentration metrics. All data is derived from cryptographically verified receipt attestations.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-spend-distribution(days)

Get the geographic and category distribution of verified spends over a trailing window. Returns a breakdown by store category and CBSA (Core Based Statistical Area) metro code, enabling analysis of where and how verified commerce is distributed across the United States.

輸入結構描述

{
  "type": "object",
  "properties": {
    "days": {
      "type": "number",
      "description": "Number of trailing days (default 7, max 90)"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-settlement-summary

Get reward settlement statistics for supported reward rails. Returns the current BTC price used for reward calculations, sats-per-receipt rate, reported Lightning Network payouts, total sats claimed by users, and wallets with balance. This endpoint reports settlement metrics; it is not a chain-finality or payout-proof verifier.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-gmv-inclusion-proof(spendId)

Get a Merkle inclusion proof that a specific spend is included in a daily GMV total. Returns the spend leaf hash, sibling hashes for the Merkle path, and the GMV root hash. This cryptographic proof allows anyone to independently verify that a spend was counted in the reported GMV without trusting the server.

輸入結構描述

{
  "type": "object",
  "properties": {
    "spendId": {
      "type": "string",
      "description": "The spend ID (UUID) to get an inclusion proof for"
    }
  },
  "required": [
    "spendId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪verify-reward-commitment(token)

Verify a reward commitment token's cryptographic integrity. Checks that the reward Merkle tree is valid, the batch signature is authentic, and the reward amounts match the committed values. Reward commitments bind point/sat allocations to specific spends before payout, preventing retroactive manipulation.

輸入結構描述

{
  "type": "object",
  "properties": {
    "token": {
      "type": "object",
      "additionalProperties": {},
      "description": "The full reward commitment token JSON object to verify"
    }
  },
  "required": [
    "token"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪verify-issued-gmv(spendToken, gmvToken, gmvInclusionProof, rewardCommitmentToken, batchAnchor)

Verify a supplied spend/GMV artifact bundle. Accepts a spend attestation token, GMV token, GMV inclusion proof, and reward commitment token, then verifies: (1) spend token signature is valid, (2) GMV token signature is valid, (3) spend is in the GMV Merkle tree, (4) reward commitment is valid, (5) all spend IDs match across artifacts. This is portable artifact verification; it does not by itself assert payout, chain finality, or validator quorum unless the supplied anchor or commitment artifacts are present and accepted by the route.

輸入結構描述

{
  "type": "object",
  "properties": {
    "spendToken": {
      "type": "object",
      "additionalProperties": {},
      "description": "The spend attestation token"
    },
    "gmvToken": {
      "type": "object",
      "additionalProperties": {},
      "description": "The observed GMV token for the spend's date"
    },
    "gmvInclusionProof": {
      "type": "object",
      "additionalProperties": {},
      "description": "The Merkle inclusion proof"
    },
    "rewardCommitmentToken": {
      "type": "object",
      "additionalProperties": {},
      "description": "The reward commitment token"
    },
    "batchAnchor": {
      "type": "object",
      "additionalProperties": {},
      "description": "Optional batch anchor artifact. When omitted, verification is portable artifact verification only."
    }
  },
  "required": [
    "spendToken",
    "gmvToken",
    "gmvInclusionProof",
    "rewardCommitmentToken"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-recent-issued-proofs(limit)

Get recent gateway-issued artifact bundles for portable spend/GMV verification. Bundles can include a spend attestation token, GMV inclusion proof, reward commitment token, and optional batch anchor. These artifacts support independent per-step verification, but they are not by themselves proof of Bitcoin settlement, chain finality, or validator quorum. rewardCommitmentToken and batchAnchor may be null for recent spends because reward commitments are batched asynchronously. Check the 'steps' array and 'ok' field for per-step verification results.

輸入結構描述

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "description": "Number of recent proofs to return (default 10, max 50)"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-issuer-keys

Get the Crinkl authority's Ed25519 public key used to sign all attestation tokens. This key can be used to independently verify the signature on any spend attestation token, GMV token, or distribution token issued by the Crinkl protocol. The key is returned in base64 format.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-reward-policy

Get the current Crinkl reward policy. Returns the active policy version, SHA-256 policy hash, reward parameters (referral bonuses, base points), category multipliers (grocery 1.5×, dining 1.5×, etc.), $CRINKL token holding tier multipliers, and the latest reserve checkpoint (BTC price, sats/receipt, coverage ratio). All values are deterministic — the policy hash covers the full parameter set. Updated daily.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-agent-capabilities

Get Crinkl's canonical external agent capability catalog. Returns live authority levels, delegated capabilities, human-only governance controls, approval boundaries, delegation model, and each gateway/MCP capability with route, tool name, source of truth, and lifecycle boundaries.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-vendors

Get the currently approved DKIM vendor domains exposed by the public agent endpoint. Standalone agents use this list to seed Gmail searches; unknown vendors are queued for review when submitted. No authentication required.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪pair-agent(deviceToken)

Start the human-authorized agent pairing flow. Generates a 4-character code that a human approves in the Crinkl PWA to authorize the agent. Returns the code and expiration time (10 minutes). No authentication required.

輸入結構描述

{
  "type": "object",
  "properties": {
    "deviceToken": {
      "type": "string",
      "description": "A random 64-character hex string. Store this — needed to claim the API key."
    }
  },
  "required": [
    "deviceToken"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪claim-api-key(deviceToken, code)

Poll for the API key after the human approves the pairing code in the Crinkl PWA. Returns 202 while pending, 200 with the API key once approved, 410 if expired. Poll every 5 seconds. No authentication required.

輸入結構描述

{
  "type": "object",
  "properties": {
    "deviceToken": {
      "type": "string",
      "description": "The same deviceToken used in pair-agent."
    },
    "code": {
      "type": "string",
      "description": "The 4-character pairing code returned by pair-agent."
    }
  },
  "required": [
    "deviceToken",
    "code"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪verify-receipt(apiKey, eml)

Preview DKIM verification of a billing email without creating a spend or earning sats. Returns extracted invoice data (vendor, amount, date, DKIM status). The full email is required because DKIM signatures are computed over the original RFC 2822 message bytes — the signature cannot be verified without them. The email is discarded after verification.

輸入結構描述

{
  "type": "object",
  "properties": {
    "apiKey": {
      "type": "string",
      "description": "Your Crinkl agent API key (crk_...)."
    },
    "eml": {
      "type": "string",
      "description": "The raw billing email, base64-encoded. Required for DKIM signature verification."
    }
  },
  "required": [
    "apiKey",
    "eml"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡submit-receipt(apiKey, eml)

Submit a DKIM-verified billing email to mint a spend token and earn sats. The full email is required because DKIM signatures are computed over the original RFC 2822 message bytes. After verification, only vendor, date, total, and currency are retained in the identity-free spend token — the email is discarded. Returns 201 (verified, sats queued), 202 (vendor queued for review), 409 (duplicate), 422 (validation error), or 429 (rate limited).

輸入結構描述

{
  "type": "object",
  "properties": {
    "apiKey": {
      "type": "string",
      "description": "Your Crinkl agent API key (crk_...)."
    },
    "eml": {
      "type": "string",
      "description": "The raw billing email, base64-encoded. Required for DKIM signature verification."
    }
  },
  "required": [
    "apiKey",
    "eml"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get-agent-me(apiKey)

Get your agent's submission count, earned sats, and wallet-level stats. Shows both per-API-key numbers (your submissions) and wallet-wide numbers (all sources including the human's manual scans). Returns satsPerReceipt (current rate).

輸入結構描述

{
  "type": "object",
  "properties": {
    "apiKey": {
      "type": "string",
      "description": "Your Crinkl agent API key (crk_...)."
    }
  },
  "required": [
    "apiKey"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本22 個工具
已驗證未記錄版本22 個工具
已驗證未記錄版本22 個工具