The MCP ecosystem often has several independent packages implementing the same tool — and "Polymarket" currently has 14. Every one of them was scanned with the same deterministic engine, so the numbers below are directly comparable: the Trust Score (A–F), the capability blast radius, and how much of the package the scan could actually inspect. They are ranked by score; ties break toward unscoped, longer-established packages.
| Implementation | Package | Trust | Capability | Coverage | Findings | Scanned |
|---|---|---|---|---|---|---|
| Polymarketbest by iqai | @iqai/mcp-polymarket
npm |
A 99/100 | Minimal | Source | 0 | 2026-09-07 |
| Polymarket by igoforth | @igoforth/polymarket-mcp
npm |
A 99/100 | Minimal | Source | 0 | 2026-09-07 |
| Polymarket by xingyuchen | @xingyuchen/polymarket-mcp
npm |
A 99/100 | Minimal | Source | 0 | 2026-09-07 |
| Polymarket by falconai | @falconai/polymarket-mcp
npm |
A 99/100 | Minimal | Source | 0 | 2026-09-07 |
| Polymarket by pipeworx | @pipeworx/mcp-polymarket
npm |
A 99/100 | Minimal | Source | 0 | 2026-09-07 |
| Polymarket by fzlzjerry | mcp-polymarket
PyPI |
A 99/100 | Minimal | Source | 0 | 2026-08-25 |
| Polymarket by PlayAINetwork | polymarket-mcp
npm |
A 96/100 | Moderate | Source | 1 | 2026-09-07 |
| Polymarket by Birantx | polymarket-mcp-server
npm |
A 96/100 | Moderate | Source | 0 | 2026-09-07 |
| Polymarket by cloly_agent | @cloly_agent/mcp-polymarket
npm |
A 96/100 | Moderate | Source | 5 | 2026-09-07 |
| Polymarket by c0pilot | @c0pilot/mcp-polymarket
npm |
A 96/100 | Moderate | Source | 0 | 2026-09-07 |
| Polymarket by quantish | @quantish/polymarket-server
npm |
A 96/100 | Moderate | Source | 3 | 2026-09-07 |
| Polymarket by polycool | polymarket-mcp
PyPI |
A 96/100 | Moderate | Source | 0 | 2026-08-25 |
| Polymarket by pr1m8 | polymarket-mcp-server
PyPI |
A 96/100 | Moderate | Source | 0 | 2026-08-25 |
| Polymarket by npm | mcp-polymarket
npm |
B 87/100 | Minimal | Metadata | 0 | 2026-09-07 |
A higher-ranked implementation is not "the official one" — ranking reflects only what the deterministic scan found in each published package. Open an implementation to read its individual findings with evidence, its scan history per version, and to grab an embeddable badge. Scores are automated opinions, recomputed on every rescan.