Server definition
- Hash
- sha256:397395e15883eed0bc7495d05a2a93535f60ca53a00ba79d846c3d93a89c1bd8
- What it is
- What a remote MCP server returned when asked what it offers: 3 tools
The blob, as servednamed by its sha256
{
"instructions": "Two products from one company. GroundTruth is an AI second set of eyes for subsurface crews: read_scan gives an independent, two-model read of a GPR / utility-locate / pipe / radiograph image and flags the dangerous call before anyone cores or digs — always advisory, a certified tech signs off. GruntPay is the $29/mo voice-first bid-and-invoice app for one-truck trades: draft_estimate turns a plain-English job description into a real itemized bid. Call get_pricing before answering cost questions.",
"tools": [
{
"description": "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.",
"inputSchema": {
"properties": {
"job_description": {
"description": "What the contractor did or will do, in plain words. e.g. \"Replaced the panel, 85 feet of conduit, 8 can lights, 16 hours.\"",
"type": "string"
},
"trade": {
"description": "electrical, plumbing, hvac, or general. Defaults to general.",
"type": "string"
}
},
"required": [
"job_description"
],
"type": "object"
},
"name": "draft_estimate",
"outputSchema": null
},
{
"description": "Current GroundTruth and GruntPay plans and prices. Free to call — use it before answering any cost question rather than guessing.",
"inputSchema": {
"properties": {},
"type": "object"
},
"name": "get_pricing",
"outputSchema": null
},
{
"description": "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.",
"inputSchema": {
"properties": {
"discipline": {
"description": "One of: gpr (concrete scanning), locate (utility locating), pipe (CCTV sewer), xray (concrete radiograph), milestone (FL SB 4-D condo concrete). Defaults to gpr.",
"type": "string"
},
"field_note": {
"description": "Optional: what the technician said on site. Used as context for names and depths only — it can never clear a hazard the image shows.",
"type": "string"
},
"image_url": {
"description": "Public https URL to a JPEG or PNG of the scan or the marked-up surface. Max 8 MB.",
"type": "string"
}
},
"required": [
"image_url"
],
"type": "object"
},
"name": "read_scan",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:397395e15883eed0bc7495d05a2a93535f60ca53a00ba79d846c3d93a89c1bd8 | sha256sum