Skip to content

GroundTruth Field Evidence

by unspecifiedcoder · remote · no sign-in to list tools · v1.0.0 · published by GitHub user unspecifiedcoder

Verified location-bound retail evidence for AI agents, delivered by human field workers.

Changes · 2

4 tools: 2 change things and 2 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 groundtruth https://groundtruth-oracle.vercel.app/api/mcp

Tools

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

4 tools

Changes things 2Claude Code: ask
  • human_doCreate a task for a human oracle to complete in the real world.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create a task for a human oracle to complete in the real world. Requires x402 payment. Returns a task_id to poll with task_status.
  • review_taskReview a submitted proof and accept or reject it.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.
    Description, as the server wrote it
    Review a submitted proof and accept or reject it. Accept releases the on-chain payout to the human oracle; reject fails the task with no payout. Call this after task_status shows the proof.
Only reads 2Claude Code: allow
  • ground_truth_infoGet info about the GroundTruth ASP — what it does, pricing, and how to call itNo findings

    Why it is in this group

    • The description's first verb is "get": a word for reading.
    Description, as the server wrote it
    Get info about the GroundTruth ASP — what it does, pricing, and how to call it
  • task_statusCheck the status and result of a GroundTruth task by its task_idNo findings

    Why it is in this group

    • The name "task_status" says "status": a word for reading.
    Description, as the server wrote it
    Check the status and result of a GroundTruth task by its task_id

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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http groundtruth https://groundtruth-oracle.vercel.app/api/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__groundtruth__ground_truth_info",
      "mcp__groundtruth__task_status"
    ],
    "ask": [
      "mcp__groundtruth__human_do",
      "mcp__groundtruth__review_task"
    ],
    "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 groundtruth. Review it before you use it.