GroundTruth Field Evidence is an MCP server published by io.github.unspecifiedcoder, hosted at groundtruth-oracle.vercel.app. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 4 tools, including ground_truth_info, human_do, task_status, review_task.
Verified location-bound retail evidence for AI agents, delivered by human field workers.
107 connections through 5 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Get info about the GroundTruth ASP — what it does, pricing, and how to call it
No parameters.
{
"name": "ground_truth_info",
"title": "GroundTruth Info",
"description": "Get info about the GroundTruth ASP — what it does, pricing, and how to call it",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
}
}Create a task for a human oracle to complete in the real world. Requires x402 payment. Returns a task_id to poll with task_status.
| Parameter | Type | Description |
|---|---|---|
| intent * | string | What you want the human to do |
| proof_type * | string | Type of proof |
| instructions * | string | Detailed instructions for the human |
| service_tier | string | one of ["integration_test","evaluation_test","quick_check","photo_visit","urgent_visit","complex_visit"] |
| target_location | object | Optional target location and allowed capture radius |
| timeout_seconds | integer |
{
"name": "human_do",
"title": "Human Do",
"description": "Create a task for a human oracle to complete in the real world. Requires x402 payment. Returns a task_id to poll with task_status.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"intent",
"proof_type",
"instructions"
],
"properties": {
"intent": {
"type": "string",
"maxLength": 500,
"minLength": 1,
"description": "What you want the human to do"
},
"proof_type": {
"enum": [
"photo",
"form"
],
"type": "string",
"description": "Type of proof"
},
"instructions": {
"type": "string",
"maxLength": 1000,
"minLength": 1,
"description": "Detailed instructions for the human"
},
"service_tier": {
"enum": [
"integration_test",
"evaluation_test",
"quick_check",
"photo_visit",
"urgent_visit",
"complex_visit"
],
"type": "string",
"default": "integration_test"
},
"target_location": {
"type": "object",
"required": [
"label",
"latitude",
"longitude"
],
"properties": {
"label": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "Human-readable store or site name"
},
"latitude": {
"type": "number",
"maximum": 90,
"minimum": -90
},
"longitude": {
"type": "number",
"maximum": 180,
"minimum": -180
},
"radius_meters": {
"type": "integer",
"default": 150,
"maximum": 5000,
"minimum": 25
}
},
"description": "Optional target location and allowed capture radius"
},
"timeout_seconds": {
"type": "integer",
"default": 3600,
"maximum": 86400,
"minimum": 60
}
}
}
}Check the status and result of a GroundTruth task by its task_id
| Parameter | Type | Description |
|---|---|---|
| task_id * | string | The task ID returned by human_do |
{
"name": "task_status",
"title": "Task Status",
"description": "Check the status and result of a GroundTruth task by its task_id",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"task_id"
],
"properties": {
"task_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "The task ID returned by human_do"
}
}
}
}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.
| Parameter | Type | Description |
|---|---|---|
| reason | string | Optional note explaining the decision |
| task_id * | string | The task ID to review |
| decision * | string | accept = pay the oracle; reject = no payout |
{
"name": "review_task",
"title": "Review Task",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"task_id",
"decision"
],
"properties": {
"reason": {
"type": "string",
"maxLength": 300,
"description": "Optional note explaining the decision"
},
"task_id": {
"type": "string",
"format": "uuid",
"pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
"description": "The task ID to review"
},
"decision": {
"enum": [
"accept",
"reject"
],
"type": "string",
"description": "accept = pay the oracle; reject = no payout"
}
}
}
}Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.