EvalView
Regression testing for AI agents with golden baselines, CI/CD integration, and multi-framework support.
Provides regression testing capabilities for AI agent workflows including golden baseline comparisons, CI/CD pipeline integration, and support for multiple frameworks like LangGraph, CrewAI, OpenAI, and Claude. Tests can evaluate tool usage, execution sequences, and output quality with optional LLM-as-judge scoring.
Source
Repository: https://github.com/hidai25/eval-view
Maintain EvalView?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[EvalView on getagentictools](https://getagentictools.com/mcp/hidai25-eval-view?ref=badge) Related mcp
Roblox Studio Runtime Controls and debugs live Roblox Studio sessions from local assistant workflows.
OBS Studio Enables control of OBS Studio through WebSocket protocol, allowing scene management, source control, streaming operations, and tra
Context Engine Compresses noisy logs, RAG results, and code context into high-signal input for AI agents.
Coze Workflows Bridges Coze workflow automation with MCP clients for listing, executing, and managing Coze workflows through conversational inter
ARC-1 MCP server for SAP ABAP systems — read, navigate, and execute ABAP code from AI agents.
iPhone Mirroir Controls a real iPhone through macOS iPhone Mirroring with screenshot, tap, swipe, type, and OCR capabilities.