Skip to content
mcp/skillhub

Evalview MCP Server

by hidai25io.github.hidai25/evalview-mcpv0.6.0

Regression testing for AI agents: save golden baselines, detect behavioral drift and block regressions in CI.

137Pythonstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Maintained35d ago

Install Evalview MCP server

Install in Claude Code

claude mcp add evalview -e OPENAI_API_KEY='<openai-api-key>' -- uvx evalview

Configuration

VariableRequiredSecretDescription
OPENAI_API_KEY—yesOpenAI API key for LLM-as-judge output quality scoring. Optional — deterministic tool/sequence evaluation works without it.

Freshness

Maintained — last maintenance signal 35d ago. The newest of the signals below sets the band.

  1. Last commit (default branch)

    2026-09-05 · 35d ago · GitHub

  2. Latest release

    2026-07-26 · 3mo ago · GitHub · v0.8.1

  3. Package published

    no data · npm/PyPI

  4. Registry entry updated

    2026-03-27 · 7mo ago · official registry · v0.6.0

FAQ

›How do I install the Evalview MCP server in Claude Code?

Run: claude mcp add evalview -e OPENAI_API_KEY='<openai-api-key>' -- uvx evalview. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does Evalview require an API key?

Yes. It expects OPENAI_API_KEY, of which 1 is a secret.

›Can I use Evalview as a remote (hosted) MCP server?

No hosted endpoint is published; it runs locally over stdio.

›Is Evalview in the official MCP registry?

Yes, as io.github.hidai25/evalview-mcp.

Alternatives to Evalview

Other devops & ci/cd MCP servers.

View all