propline_get_book_accuracy
shallowio.github.proplineapi/propline-mcp · Verify this server
Free-tier endpoint. How well each sportsbook prices player props: each book's closing prop prices are de-vigged and scored (Brier) against the real result and against the other books on the same line. Per book: props scored, brier, consensus_brier, skill_bp (> 0 = closer to the result than the market average) with a 95% interval, verdict (beats_market / trails_market / in_line) and margin_pct (average overround), plus by_sport and by_market breakdowns. Useful for: 'which book prices props most accurately', 'which book has the lowest margin'. A pricing report, never a profit claim or betting edge.
1 trials · measured 15 days ago
propline_get_book_accuracy scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against io.github.proplineapi/propline-mcp, measured 6 Oct 2026 under methodology v0.2.0. Every measured component scored 100.
Component breakdown
| Component | Weight | Value |
|---|---|---|
| Reliability | 35% | not applicable |
| Schema integrity | 25% | 100.0 |
| Failure behaviour | 15% | not applicable |
| Latency | 15% | not applicable |
| Concurrency | 10% | not applicable |
Tool details
- Transport
- remote + stdio
- Credential class
- self-provisionable
- Input schema
- not declared
- Output schema
- not declared
- Side-effect classification
- unclassified
Score history
| Day | Score | Tier | Methodology |
|---|---|---|---|
| 2026-10-06 | 100.0 | shallow | v0.2.0 |
Probe evidence
| Probe | Outcomes |
|---|---|
| schema_integrity | pass: 1 |
Raw request/response logs are not archived yet — the outcome counts above are drawn directly from every recorded trial.
Embed this score
Available for every tool, scored or not — not a verification perk. Always links back to this page.
[](https://vouch.tools/tools/a72d593c-a5ad-4f0c-aa41-535cc1d75008)