Koskamo

GroundTruth Field Evidence MCP

Dispatches paid real-world retail field checks and returns verified photographic evidence, structured observations, and settlement receipts via human field workers. Supports creating funded asynchronous field missions, polling mission status for proof and payment finalization, and reviewing task submissions.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

GroundTruth Field Evidence MCP logo, by unspecifiedcoderCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by unspecifiedcoder
MCP endpoint (Streamable HTTP)
https://groundtruth-oracle.vercel.app/api/mcp
Vendor documentation

What its tools do

4 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (4)

4 of 4 have a description · 0 of 4 declare behavior hints · 2 of 3 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Create a funded asynchronous field mission to verify retail store status
  • Poll a mission until its proof and payment are final
  • Approve or reject a held submission when authorized
  • Inspect service capabilities and payment requirements

Source and maintenance

Community listingRegistry 1.0.0
mcp-registry: io.github.unspecifiedcoder/groundtruth@1.0.0Source repository
Maintenance checked

Protocol and capabilities

Server
groundtruth 1.0.0-beta
MCP protocol negotiated in check
2025-11-25
Tools
4 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Tools

4 advertised

ground_truth_info — GroundTruth Info
Advertised by the server during the last successful anonymous check.

Get info about the GroundTruth ASP — what it does, pricing, and how to call it

ground_truth_info input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {}
}
human_do — Human Do
Advertised by the server during the last successful anonymous check.

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.

human_do input schema
{
  "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
    }
  }
}
task_status — Task Status
Advertised by the server during the last successful anonymous check.

Check the status and result of a GroundTruth task by its task_id

task_status input schema
{
  "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_task — Review Task
Advertised by the server during the last successful anonymous check.

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.

review_task input schema
{
  "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"
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
487 ms
95th percentile latency
487 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 487 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http groundtruth-field-evidence-mcp https://groundtruth-oracle.vercel.app/api/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add groundtruth-field-evidence-mcp --url https://groundtruth-oracle.vercel.app/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable groundtruth-field-evidence-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "groundtruth-field-evidence-mcp": {
      "url": "https://groundtruth-oracle.vercel.app/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "groundtruth-field-evidence-mcp": {
      "type": "streamableHttp",
      "url": "https://groundtruth-oracle.vercel.app/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start groundtruth-field-evidence-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "groundtruth-field-evidence-mcp": {
      "type": "http",
      "url": "https://groundtruth-oracle.vercel.app/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http groundtruth-field-evidence-mcp https://groundtruth-oracle.vercel.app/api/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://groundtruth-oracle.vercel.app/api/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "groundtruth-field-evidence-mcp": {
      "serverUrl": "https://groundtruth-oracle.vercel.app/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like GroundTruth Field Evidence MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 5,557