# io.github.FieldmodeLLC/scrapecheck (remote · scrapecheck-mcp.fly.dev)

Verify scraped data against the live source page. Signed verdicts, $0.01 via x402.

- Trust score: 62/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `scrapecheck-mcp.fly.dev`: 62/100 (this document), [markdown](https://verifymcp.io/servers/fieldmodellc-scrapecheck/scrapecheck-mcp.md), [page](https://verifymcp.io/servers/fieldmodellc-scrapecheck/scrapecheck-mcp)

## Channel facts

- Endpoint: `https://scrapecheck-mcp.fly.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 3 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 580 tokens (~193/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (67% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http fieldmodellc-scrapecheck https://scrapecheck-mcp.fly.dev/mcp
```

### Codex

```toml
[mcp_servers.fieldmodellc-scrapecheck]
url = "https://scrapecheck-mcp.fly.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fieldmodellc-scrapecheck": {
      "type": "remote",
      "url": "https://scrapecheck-mcp.fly.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add fieldmodellc-scrapecheck --url https://scrapecheck-mcp.fly.dev/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  fieldmodellc-scrapecheck:
    url: "https://scrapecheck-mcp.fly.dev/mcp"
```

### Other

```json
{
  "mcpServers": {
    "fieldmodellc-scrapecheck": {
      "type": "http",
      "url": "https://scrapecheck-mcp.fly.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 62, +10)

- [security regression] HSTS header: unverified → fail
- [security improvement] Transport: fail → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 3 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

### 2026-08-02 (score 52, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-08-01 (score 51)

First indexed and scored.

## MCP tools (3)

### `verify_web_field` (~291 tokens)

Verify scraped claim (full)

Verify a scraped claim against the live source page and get back an ed25519-signed verdict: "pass", "fail", or "unverifiable". ScrapeCheck independently re-fetches the URL itself, confirms the claimed value is actually present and served live (not a stale cache), and an independent LLM judge confirms the value answers what was asked. The guarantee is structural, not statistical: a claim is never certified unless the re-fetched page contains it, AND a judge's vote is mechanically voided if its restatement of the claim doesn't match what was actually claimed — absence cannot pass, substitution cannot pass, and anything unconfirmed returns "unverifiable", never "pass". Every verdict carries a stable verdict_id, the engine digest that produced it, and a signature verifiable offline against the public key (see get_verifier_info). Scope: server-rendered pages; client-rendered (JS-only) content returns "unverifiable". $0.01 per call via x402.

Input parameters:

- `asked` (string, required): What the scraper was asked to extract, e.g. "get the current price and stock status"
- `claim` (object, required): The scraped field(s) to verify against the live page, e.g. {"price": "£51.77", "in_stock": true}
- `url` (string, required): URL of the source page the claim was scraped from

Output parameters:

- `check_type` (string)
- `confidence` (number)
- `engine` (string)
- `evidence` (object)
- `reasons` (array)
- `signature` (string)
- `verdict` (string)
- `verdict_id` (string)

### `verify_presence` (~212 tokens)

Presence check (not an answer check)

Presence check only — this does NOT confirm the value is the right answer to what was asked, and its positive verdict is "present", never "pass". It confirms the claimed value appears on the live source page: ScrapeCheck independently re-fetches the URL and checks the value is present and served live, with no LLM judge. Published accuracy numbers apply to full verification (verify_web_field) only. Returns a signed verdict ("present", "fail", or "unverifiable") with check_type "web_field_presence_v1". Scope: server-rendered pages. $0.002 per call via x402.

Input parameters:

- `asked` (string, required): What the scraper was asked to extract, e.g. "get the current price and stock status"
- `claim` (object, required): The scraped field(s) to verify against the live page, e.g. {"price": "£51.77", "in_stock": true}
- `url` (string, required): URL of the source page the claim was scraped from

Output parameters:

- `check_type` (string)
- `confidence` (number)
- `engine` (string)
- `evidence` (object)
- `reasons` (array)
- `signature` (string)
- `verdict` (string)
- `verdict_id` (string)

### `get_verifier_info` (~77 tokens)

Verifier trust info (free)

Free trust artifact: the evidence for deciding whether to trust ScrapeCheck's verdicts, in-band. Returns the ed25519 public key every verdict signature verifies against, the benchmark summary with honest small-N labels, the scope statement, and service endpoints. Verdicts are signed over canonical sorted-key JSON of all fields except "signature".

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/fieldmodellc-scrapecheck/scrapecheck-mcp#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 52
- 2026-08-01: 51

## Links

- Remote endpoint: https://scrapecheck-mcp.fly.dev/mcp
- Repository: https://github.com/FieldmodeLLC/scrapecheck-mcp
- Changelog RSS feed: https://verifymcp.io/servers/fieldmodellc-scrapecheck/scrapecheck-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/fieldmodellc-scrapecheck/scrapecheck-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/fieldmodellc-scrapecheck/scrapecheck-mcp