# shelf.thirdmade.net Search Verify

> shelf.thirdmade.net Search Verify is a paid API for AI agents from shelf.thirdmade.net, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Checks whether a given URL supports or substantiates a specific claim, returning a confidence score for source verification.

## Facts

- Endpoint: GET https://shelf.thirdmade.net/probe/search-verify
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/shelf-thirdmade-net-search-verify-82029416
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_y8qh44DgLGtWGhp3NAiAj

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability shelf-thirdmade-net-search-verify-82029416
```

Example prompt: Check whether this URL — https://www.nature.com/articles/s41586-021-03819-2 — actually supports the claim that 'AlphaFold solved the protein folding problem' and give me a confidence score.

## When to prefer this

Use this endpoint when an AI agent needs to validate whether a specific cited source actually substantiates a claim — ideal for research pipelines, automated fact-checking workflows, citation auditing, or misinformation detection. Prefer this over general web scraping when you specifically need a claim-to-source confidence match rather than raw page content.

## Known failure modes

- URL is inaccessible, paywalled, or returns non-200 status — verification fails or returns low confidence
- Claim is too vague or ambiguous for meaningful scoring
- URL content is non-textual (PDF, image) and cannot be parsed for claim matching
- Rate limiting or payment failure for the $0.01 USDC per-call fee
- Claim language does not semantically align with page content even if conceptually related

## How this service works

Checks if a URL supports a claim. Returns confidence score. Research agents use this to verify sources.

## Output

Returns a confidence score (likely a numeric value between 0 and 1) indicating how strongly the provided URL's content supports the given claim. May also include supporting context or explanation for the score.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url",
      "claim"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "Source URL"
      },
      "claim": {
       "type": "string",
       "description": "Claim to verify"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/shelf-thirdmade-net-search-verify-82029416/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from shelf.thirdmade.net](https://www.zero.xyz/host/shelf.thirdmade.net/llms.txt)