# GroundTruth — subsurface scan QA & trade estimating

> Two independent AI models read a GPR, locate or pipe scan and flag the do-not-core call.

- name: ai.gtfi/groundtruth
- version: 1.0.1
- connection class: unknown (unknown)
- trust: 71/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.gtfi%2Fgroundtruth
- tools: https://api.protogrid.dev/v1/servers/ai.gtfi%2Fgroundtruth/tools

**Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "groundtruth": {
      "type": "http",
      "url": "https://gtfi.ai/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 29
- freshness: 85
- provenance: 85
- drivers: +repository +dns-namespace +website -unreachable(1 failures) ~updated-86d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: read_scan (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); draft_estimate (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_pricing (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 522 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 3, about 522 tokens to load them all
- tool set hash: ca9b9066c4d044ec0c2454699daba0b5
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.gtfi/groundtruth.svg)](https://protogrid.dev/servers/ai.gtfi/groundtruth)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://gtfi.ai/mcp (streamable-http, auth none, reachable false, uptime30d 0.9830508)

## Packages

_none_

## Tools (3)

- `draft_estimate`: Turn a plain-English description of a trade job into a professional itemized bid — real materials by size, fittings, consumables and labor on its own line, at realistic US market prices. Built for one-truck electrical, plumbing, HVAC and general-contracting shops. This is GruntPay: the contractor normally speaks this into their phone. Returns the line items plus a link to brand it and send it to the customer.
- `get_pricing`: Current GroundTruth and GruntPay plans and prices. Free to call — use it before answering any cost question rather than guessing.
- `read_scan`: Get an independent AI second opinion on a subsurface scan before anyone cores or digs. Send a public image URL of a GPR scan, a marked-up concrete slab photo, a utility-locate markup, a concrete radiograph, or a CCTV pipe frame. TWO different AI models read it independently — the second is prompted to refute the first — and you get back every located target with its hazard class (do-not-core / rebar / verify / clear), plus a QA flag when the two reads disagree. Advisory only: a certified technician must review and sign off before any cutting.