Evalview MCP

Snapshot testing for AI agents. Record what your agent does today. Get told when it silently changes. It runs locally over stdio via the published package.

People connecting AI & ML tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-08-23 · ★ 129 · #10 OF 95 MAINTAINED AI & ML · VERIFIED 2026-08-25

Apache-2.0 · Python servers · how we verify → /methodology

01 · Install Evalview MCP

before you install - you'll need

The README does not document required environment variables for a basic install.

Claude Code

claude mcp add hidai25-eval-view -- uvx evalview

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "hidai25-eval-view": {
      "command": "uvx",
      "args": [
        "evalview"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license Apache-2.0 - declared in the repository

pypi package evalview - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.hidai25 is GitHub-verified and matches the repo owner

03 · What Evalview MCP can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v0.8.1 · 2026-07-26

EvalView 0.8.1 - the release that was written in July and never actually shipped. PyPI has been serving 0.8.0 since May; this closes that gap and folds in a new flag plus two bugs found while adding it. · Added · PEP…

v0.8.0 · 2026-05-15

Bump to 0.8.0. See CHANGELOG.md for the full entry. · Headline features since 0.7.1: · Record/replay cassettes for evalview simulate (#228) · --schedule cron syntax for evalview monitor (#224)

v0.7.1 · 2026-05-02

What's new in 0.7.1 · Added · TOML test cases - TestCaseLoader now understands .toml alongside .yaml/.yml (#209). Same schema, different on-disk encoding for teams that already author config in TOML. Uses stdlib…

04 · Who maintains Evalview MCP

evalview-mcp is maintained by hidai25. It's the only MCP server we track from this author; the repo dates to Nov 2025.

05 · Facts

category
AI & ML - ranked #10 of 95 actively-maintained AI & ML servers as of 2026-08-25.
release cadence
1 release in the last 90 days (latest 2026-07-26)
registry
io.github.hidai25/evalview-mcp (active, first published 2026-02-25 · 2 versions)
packages
pypi:evalview

06 · Evalview MCP FAQ

What is Evalview MCP?

Snapshot testing for AI agents. Record what your agent does today. Get told when it silently changes. It runs locally over stdio via the published package.

Is Evalview MCP still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-23 and it shipped 1 release in the last 90 days. We re-verify nightly.

How do I install Evalview MCP?

Run `uvx evalview`. The README does not document required environment variables for a basic install. You can also paste the ready-made client config above.

Does Evalview MCP run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Evalview MCP

More AI & ML MCP servers · Completion Kit · Klaket MCP · Ragscore · Mcpbridge · DEVONthink MCP (istefox)

More Python MCP servers · Shots · Akf · Hollaugo Financial Research MCP Server · Ha MCP · Honey Labs · see all