MCP Tools DirectoryAbout this integration
Benchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models.
- Transport
- stdio
- Authentication
- api-key
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.6.1
- Package
- llmtest-mcp
- Last compatibility test
- Not independently tested
Connect your agent
llmtest-mcpPublisher README and npm manifest were reviewed from pinned captures. Qualification is documentation-only: the package, API, benchmarks, account, paid credits, changes, safety gates, and rollback behavior were not executed or independently verified. Autopilot must first be enabled and has publisher-documented account and flow prerequisites.
Capabilities: Inspect proxy activity and AI flows, Benchmark model alternatives, Manage optimization suggestions, Control weekly optimization autopilot
Connected profiles
Additional details
io.github.tjacquesson/llmtest-mcp
Source ↗ · Checked 2026-09-170.6.1
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17npm
Source ↗ · Checked 2026-09-17LLMTEST_API_KEY
Source ↗ · Checked 2026-09-17llmtest-mcp
Source ↗ · Checked 2026-09-200.6.1
Source ↗ · Checked 2026-09-20The publisher documents an opt-in autopilot that runs weekly, applies only changes that pass its stated gates, offers a 24-hour revert window, and continues drift checks.
Source ↗ · Checked 2026-09-20The connection requires an LLMTest API key supplied through the LLMTEST_API_KEY environment variable.
Source ↗ · Checked 2026-09-20The reviewed catalog identity remains a local stdio npm server launched with npx and the API key in its environment.
Source ↗ · Checked 2026-09-20Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-20