Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

GroundTruth Field Evidence

REMOTE · GROUNDTRUTH-ORACLE.VERCEL.APP

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

0 this week 79 Trust /100

Last scanned (18 hours ago)

Scores higher than 74% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Maps and Location

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 261 tokens (~65/item across 4 items; 4 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage93
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 80% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (12)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 11 Nov 26 0
    • Stability: 0.97 → pass security
  • 10 Nov 26 0
    • Stability: pass → 0.97 functional
  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 26 Oct 26 0
    • Stability: 0.97 → pass security
  • 25 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Sept 26 0
    • Stability: unverified → 0.03 ▲ functional
    • “human_do” added an optional parameter “service_tier” cosmetic
    • “human_do” dropped the optional parameter “budget_usdt” cosmetic
  • 26 Sept 26 0

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://groundtruth-oracle.vercel.app/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.vercel.app CN=WR1,O=Google Trust Services,C=US 31 Oct 2026 29 Jan 2027 RSA 2048 SHA256-RSA 9c5f0e6a35c955e113044c86848e4cd5
SANs: *.vercel.app
CN=WR1,O=Google Trust Services,C=US (CA) CN=GTS Root R1,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 RSA 2048 SHA256-RSA 7fd9e2c2d2048a0474b627a26d0868a7
CN=GTS Root R1,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 19 Jun 2020 28 Jan 2028 RSA 4096 SHA256-RSA 77bd0d6cdb36f91aea210fc4f058d30d

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of groundtruth-oracle.vercel.app. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
app. DS published 23684 8 Verified
vercel.app. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000; includeSubDomains; preload
content-security-policy default-src 'self'; base-uri 'self'; form-action 'self'; frame-ancestors 'none'; object-src 'none'; img-src 'self' data: blob: https://*.supabase.co; font-src 'self' data:; style-src 'self' 'unsafe-inline'; script-src 'self' 'unsafe-inline'; connect-src 'self' https://*.supabase.co wss://*.supabase.co https://www.okx.com https://*.xlayer.tech; upgrade-insecure-requests
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(self), geolocation=(self), microphone=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://groundtruth-oracle.vercel.app/api/mcp Verified 200
http (plaintext) http://groundtruth-oracle.vercel.app/api/mcp HTTPS enforced 308 https://groundtruth-oracle.vercel.app/api/mcp
MCP tools · 4 exposed · ~261 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ground_truth_info ~29

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

human_do ~106

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.

NameTypeReqDescription
instructionsstringyesDetailed instructions for the human
intentstringyesWhat you want the human to do
proof_typestringyesType of proof
service_tierstring––
target_locationobject–Optional target location and allowed capture radius
timeout_secondsinteger––

No output schema declared.

No examples provided.

review_task ~88

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.

NameTypeReqDescription
decisionstringyesaccept = pay the oracle; reject = no payout
reasonstring–Optional note explaining the decision
task_idstringyesThe task ID to review

No output schema declared.

No examples provided.

task_status ~38

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

NameTypeReqDescription
task_idstringyesThe task ID returned by human_do

No output schema declared.

No examples provided.

Install

How do I install the GroundTruth Field Evidence MCP server?

GroundTruth Field Evidence is a hosted endpoint at https://groundtruth-oracle.vercel.app/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · groundtruth-oracle.vercel.app

# add to Claude Code
claude mcp add --transport http unspecifiedcoder-groundtruth 'https://groundtruth-oracle.vercel.app/api/mcp'
Common questions

What is the GroundTruth Field Evidence MCP server?

GroundTruth Field Evidence is an MCP server listed in the public MCP registry as io.github.unspecifiedcoder/groundtruth. Verified location-bound retail evidence for AI agents, delivered by human field workers. This page covers its hosted endpoint (https://groundtruth-oracle.vercel.app/api/mcp).

Is the GroundTruth Field Evidence MCP server safe to use?

GroundTruth Field Evidence scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the GroundTruth Field Evidence MCP server expose?

GroundTruth Field Evidence exposes 4 tools: ground_truth_info, human_do, task_status, review_task. Their descriptions and schemas cost roughly 261 tokens of context every time the server is loaded.

Does the GroundTruth Field Evidence MCP server require authentication?

No. We connected to GroundTruth Field Evidence without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the GroundTruth Field Evidence MCP server still maintained?

GroundTruth Field Evidence is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the GroundTruth Field Evidence MCP server?

VerifyMCP ran 12 checks on GroundTruth Field Evidence, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about GroundTruth Field Evidence: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.