What is eval-view?
eval-view is a MCP server by hidai25 that regression testing for AI agents: save golden baselines, detect behavioral drift and block regressions in CI. It is listed under Developer tools and has 139 GitHub stars.
| Type | Mcp server |
|---|---|
| Author | hidai25 |
| Repository | hidai25/eval-view |
| Popularity | 139 GitHub stars |
| Category | Developer tools |
| Security | Low risk (96/100) |
| Rank | #514 of 4,418 MCP servers; #141 in Developer tools |
| License | Apache-2.0 |
| Last commit | 2026-10-16 |
| Stars this week | +2 |
| Runs | Locally |
| Language | Python |
| Platforms | macOS, Windows, Linux |
Is eval-view safe to install?
eval-view scores 96/100 on the MCPMods security check: Low risk. No checks raised a concern. It passed 5 of 6 checks.
MCP server results come from listing signals: who publishes it, where your data goes and what it can do. The code itself is not scanned yet.
| Check | Result |
|---|---|
| Community-built server | Note |
| Runs on your machine only | Pass |
| No credentials mentioned | Pass |
| Read-only by description | Pass |
| No code execution | Pass |
| Source on GitHub | Pass |
How do I install eval-view?
- Find the launch command. The README says how the server starts (npx, uvx, docker or a remote URL) and which API keys it needs.
https://github.com/hidai25/eval-view
- Add it to Claude Code. Replace the part after -- with the command from the README. Remote servers use --transport http with a URL.
claude mcp add eval-view -- <command from README> claude mcp add --transport http eval-view <server-url>
- Check it connected. This lists your MCP servers and their status.
claude mcp list
Or ask Claude to set it up
Paste this into Claude Code and it installs eval-view for you:
Add the "eval-view" MCP server from https://github.com/hidai25/eval-view to Claude Code. Read its README for the launch command and any API keys I need, run claude mcp add, then check that it connects.