Each MCP server is run through the gauntlet: a live LLM agent attempts generated tasks using only the server's tools, alongside schema, description, security, reliability, and robustness checks. Grade is the weighted overall; a critical security finding caps it.
| # | Server | Grade | Score | Task success | Security | Tools |
|---|---|---|---|---|---|---|
| 1 | sequential-thinking | A | 100.0 | — | ✓ | 1 |
| 2 | good-fixture | A | 99.4 | 100 | ✓ | 3 |
| 3 | everything | B | 82.8 | 50 | ✓ | 13 |
| 4 | memory | B | 81.9 | 42 | ✓ | 9 |
| 5 | filesystem | C | 79.2 | 35 | ✓ | 14 |
| 6 | bad-fixture | C | 75.0 | 50 | ⚠ | 4 |
Agent model: gemini:gemini-flash-latest · generated 2026-07-23T23:27+00:00 · scores from a live agent are stochastic (repeated and averaged); the ⚠ flag marks tool-poisoning / injection findings.