A
licenseA
qualityB
maintenanceAn MCP server that lets any AI agent evaluate RAG outputs -- faithfulness scoring, hallucination detection, and retrieval quality metrics -- with zero API keys, using MCP sampling.
6
MIT
Eval Engine API
Server Details
Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Last Tested
- Transport
- Streamable HTTP
- URL
TDQS
A4.4/5.0
Scored across 3 tools
Disambiguation5/5
Each tool has a distinct purpose: listing benchmarks, getting details, and performing evaluation. No overlap or ambiguity.
Naming Consistency5/5
All tool names use lower_snake_case with clear verbs (list, get, evaluate) and follow a predictable pattern.
Tool Count5/5
With 3 tools covering the essential workflow of discovering, inspecting, and using benchmarks, the count is appropriate and well-scoped.
Completeness5/5
The tool set covers the complete user-facing workflow: discover benchmarks, get details, and evaluate. No obvious gaps for the intended purpose.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
3 tool updates
- First observed
evaluate - First observed
get_benchmark - First observed
list_benchmarks
Related MCP Connectors
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
Cloudflare Workers MCP server: llm-output-quality-monitor
Cloudflare Workers MCP server: ai-eval
MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables Claude and other MCP-compatible clients to access Scorecard's evaluation tools for running experiments, generating synthetic data, and analyzing model performance. It is designed to be deployed on Cloudflare Workers and integrates securely with Scorecard's API using Clerk for authentication.-
- AlicenseBqualityDmaintenanceAn MCP-style stdio server for evaluating AI agent outputs, enabling CI-friendly quality gates, regression comparisons, and canary promotion decisions.3MIT
- AlicenseAqualityCmaintenanceA local MCP server that packages LLM evaluation gates as reusable CI/CD primitives, enabling AI agents to run datasets against models, score responses, and enforce quality thresholds.10MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.