tinyzkp-mcp

TinyZKP — Verifiable Receipts for AI Agents tinyzkp.com · Try it in browser · API docs · Free signup Mint a tamper-evident proof that…

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Describe Template: Get full parameter schema and example JSON for a specific proof template. Call this before prove_template to understand what parameters are needed.
  • Get Capabilities: Get server capabilities, version, and recommended workflow. Start here if you're unsure what this server can do.
  • Get Proof: Retrieve the base64-encoded proof bytes for a completed job. Pass the result to verify_proof for independent verification.

What data it sees

Do you need an account

No: the server works without sign-in

TinyZKP — Verifiable Receipts for AI Agents

tinyzkp.com · Try it in browser · API docs · Free signup

Mint a tamper-evident proof that your agent ran the code it claims, on the inputs it claims. One MCP install. One API call. Verify in milliseconds. No cryptography degree required.

How to connect

How to connect tinyzkp-mcp to Claude

The server address to paste into Claude settings:

https://tinyzkp-mcp--logan.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect tinyzkp-mcp to ChatGPT

The server address to paste into ChatGPT settings:

https://tinyzkp-mcp--logan.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect tinyzkp-mcp to Cursor

The server address to paste into Cursor settings:

https://tinyzkp-mcp--logan.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (10)

Raw names from tools/list. Only developers need these.

describe_templateGet full parameter schema and example JSON for a specific proof template. Call this before prove_template to understand what parameters are needed.
get_capabilitiesGet server capabilities, version, and recommended workflow. Start here if you're unsure what this server can do.
get_proofRetrieve the base64-encoded proof bytes for a completed job. Pass the result to verify_proof for independent verification.
get_proof_summaryGet a human-readable summary of what a proof job attests to, including template, public inputs, and status.
list_templatesList all available proof templates with IDs, summaries, and tags. Use this to discover what kinds of proofs you can generate.
list_workloadsList all registered workload IDs. Workloads are predefined proof programs.
poll_jobCheck the status of a proof job. Returns: pending, running, succeeded, or failed.
prove_templateGenerate a zero-knowledge proof from a template ID and parameters. Returns a job_id — call poll_job to check progress. Consumes one proof from your monthly quota.
prove_workloadGenerate a proof from a registered workload ID. Returns a job_id — call poll_job to check progress. Consumes one proof from your monthly quota.
verify_proofVerify a proof independently. Pass the base64-encoded proof from get_proof. Returns {valid: true/false}. This is a pure cryptographic check — no quota consumed.