Skip to content

rta — zero-knowledge proof of a threshold

by rta.lat · remote · no sign-in to list tools · v0.1.0 · published by lat.rta

Prove a hidden value reached a threshold without revealing the value.

Changes · 1
CompareRegistry entry

2 tools: 1 change things and 1 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http rta https://rta.lat/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

2 tools

Changes things 1Claude Code: ask
  • verify_proofVerify a Groth16 zero-knowledge proof that a hidden value reached a threshold — for example 'the account balance is at least 1000'.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Verify a Groth16 zero-knowledge proof that a hidden value reached a threshold — for example 'the account balance is at least 1000'. The verifier learns that the threshold is met and never learns the value: the public signals are empty by construction. Returns whether the proof is valid, the predicate, and what the proof does NOT disclose. Use when a counterparty must show a threshold was met without revealing the number. A one-time nonce is required so the same proof cannot be replayed.

    Annotations the server declares

    • title: Verify a zero-knowledge proof of a threshold
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 1Claude Code: allow
  • list_predicatesList the thresholds ṚTA can prove: for each predicate, the name, the threshold value, the circuit size and a plain-language label.No findings

    Why it is in this group

    • The name "list_predicates" says "list": a word for reading.
    Description, as the server wrote it
    List the thresholds ṚTA can prove: for each predicate, the name, the threshold value, the circuit size and a plain-language label. Use before generating a proof, so the agent knows which statement it can prove without revealing the underlying value.

    Annotations the server declares

    • title: List provable thresholds
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http rta https://rta.lat/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__rta__list_predicates"
    ],
    "ask": [
      "mcp__rta__verify_proof"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as rta. Review it before you use it.