Skip to content
Crinkl logo

Crinkl MCP server

Which MCP servers are Crinkl's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-26

← Back to Crinkl

Whose server it is
  • Registry namexyz.crinkl.mcp/crinkl-commerceverified in the MCP registry

The registry name sits under crinkl.xyz. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-26
  • Stateanswerschecked 2026-10-26
  • Tools22
  • Server calls itselfcrinkl-commerce
  • Server version1.1.0
  • Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 102 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 1 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-27
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer98 ms
  • Space in an agent's context≈ 3,341 tokensthe definitions of all its tools (22), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 22 toolsdeclared outputSchema: results come typed, read once
  • Not saying whether it only reads or can destroy: 22 of 22

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers22 tools · read 2026-10-26
  • 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.

  • get-cumulative-gmv

    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…

  • get-daily-gmv

    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…

  • get-trailing-gmv

    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.

  • get-spend-signals

    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…

  • resolve-cbsa

    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…

  • 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…

  • get-spend-distribution

    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…

  • 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…

  • get-gmv-inclusion-proof

    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…

  • verify-reward-commitment

    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…

  • verify-issued-gmv

    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…

  • get-recent-issued-proofs

    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…

  • 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…

  • 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…

  • 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…

  • 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.

  • pair-agent

    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.

  • claim-api-key

    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.

  • verify-receipt

    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…

  • submit-receipt

    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…

  • get-agent-me

    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).

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

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

Add it

Claude Code, in a terminal

claude mcp add --transport http crinkl https://mcp.crinkl.xyz/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.crinkl.xyz/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.