Developer · Local MCP server
Evalview MCP
Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.hidai25/evalview-mcp- Version
- 0.6.0
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-03-27
- Updated
- 2026-03-27
- Publisher
- hidai25 (GitHub)
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/hidai25) · how
- Listed under
- OpenAI MCP servers
- Repository
- github.com/hidai25/eval-view
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | evalview | 0.6.0 | stdio |
How to connect Evalview MCP
Evalview MCP runs locally from a Python package published to PyPI: evalview version 0.6.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx evalview. It reads the environment variable OPENAI_API_KEY (secret); set it in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"evalview-mcp": {
"command": "uvx",
"args": [
"evalview"
],
"env": {
"OPENAI_API_KEY": "<secret>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| Eurodns MCPModel Context Protocol server for the EuroDNS User API - domains, DNS zones, subscriptions and SSL. | Local · stdio |
| Eval Engine APIPay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI. | Remote · HTTPLive check: ✗ no handshake |
| EvalForge LiteCompare text LLMs across OpenRouter, Bedrock, Vertex AI and Foundry with automated grading. | Local · stdio |
| Evalscopebench MCPA paid remote MCP for AI SDK benchmark dashboard, built to return verdicts, receipts, usage logs, an. | Remote · HTTPLive check: ✗ no handshake |
| Evercraft WebRead public web content with Evercraft; search and browser automation stay behind safety gates. | Remote · HTTPLive check: ✓ handshake |
| Evernode MCPEvernode/HotPocket dApp helper: templates, non-determinism lint, lease math, live host lookup. | Local · stdio |
| Evidence Diff MCPExplain coarse Git and test-build evidence changes without source diff contents. Tools include... | Local · stdio |
| Evidence LedgerRead-only MCP: free OpenAI security evidence ledger (55 fields) + SaaSDossier release register. | Remote · HTTPLive check: ✓ handshake |