
Snapdiff
ai.snapdiffPublished by snapdiff.aiv0.5.0Updated Nov 10, 2026
Visual-diff & change-detection tools that catch agentic UI drift for coding agents.
Overview
Lets a coding assistant capture screenshots, visually diff web pages, and verify UI changes against a baseline via the SnapDiff API.
- What you can do
- Exposes four tools: verify a UI change against a stated intent and return a verdict plus next action, compare two pages or a page against a stored baseline with a diff percentage and highlighted image, capture a screenshot of any URL, and render HTML/CSS to an image. It calls the SnapDiff REST API and runs locally as a stdio subprocess, so Playwright-backed localhost tools run on your machine. The same tool surface is also offered by the hosted endpoint.
- When to use it
- Useful when a coding agent needs to check that a UI edit produced the intended visual change and no regressions, or when you want ad-hoc page diffs, screenshots, or generated images such as OG cards without leaving the assistant.
- Requirements
- Node.js with npx to run the npm package locally; a SnapDiff API key supplied in the SNAPDIFF_API_KEY environment variable; network access to the SnapDiff API. The optional SNAPDIFF_API_URL variable overrides the API base.
Installation
In SourceWeft
- Open Snapdiff in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
@corralimited/snapdiff-mcp
Standalone MCP server for SnapDiff. Exposes four tools to local agents:
- Compare two web pages visually — diff percentage plus a highlighted diff image
- Capture a screenshot of any URL
- Check whether a page changed vs. a previous capture
- Render HTML/CSS to an image (OG cards, social images, email headers)
Hits the public SnapDiff REST API. Bring your own API key.
Quickstart
Get an API key at https://snapdiff.ai/dashboard, then drop the snippet for your agent below.
Claude Code
Or edit ~/.claude/settings.json:
Cursor
~/.cursor/mcp.json (or project-level .cursor/mcp.json):
Cline (VS Code)
Cline > MCP Servers > Edit Config:
Zed
~/.config/zed/settings.json:
Continue
~/.continue/config.yaml:
Anything else with a generic stdio MCP slot
Tools
Schemas live in src/tools/ and are exported from @corralimited/snapdiff-mcp/tools.
The hosted SnapDiff backend imports the same schemas so its in-process /mcp endpoint and this
standalone stdio server expose an identical surface — agents see the same tool names, descriptions,
and parameters whether they connect to https://api.snapdiff.ai/mcp or run this server locally.
Remote HTTP access
This package speaks stdio only — your editor spawns it as a subprocess, and the Playwright-backed localhost tools run on your machine, where your dev server actually is. It does not open a port.
If you need an HTTP endpoint, use the hosted one at https://mcp.snapdiff.ai/mcp,
which authenticates every request with your API key and exposes the same tool surface.
Configuration
There are no CLI flags beyond --help.
License
MIT — see LICENSE.
Source: README.md at commit e420175
Tools
0Version history
1- v0.5.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts