Saccade

Perceptual visual regression, image evidence inspection and bounded decision proposals.

What does this entry provide?

Saccade is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 56/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. No automated install command is listed; check the repository for manual setup instructions. Review the last-pushed date and repository status before adding Saccade to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.

Snapshot facts

Source: Official MCP Registry
Quality: 56/100
Install method: manual
Repo: Tavrin/saccade
Repo updated: Oct 9, 2026

Install command

See source docs

Install method: manual

Review the upstream source before running this command.

GitHub project

Quality

Repo stars

Repo updated

Oct 9, 2026

How is this score calculated?

Weighted across six dimensions, scored 0-100.
Provenance (25): listed in an official or curated registry.
Installability (25): a runnable install command beats a declared transport, which beats a source checkout.
Maintenance (20): recency of the last push; archived entries score zero here.
Adoption (20): repository stars on a log curve.
Documentation (10) and description quality (10): parsed manifest or SKILL.md frontmatter, and a real description rather than a placeholder.

MCP manifest

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-10-09T20:06:47.813263Z",
      "publishedAt": "2026-10-09T20:06:47.813263Z",
      "statusChangedAt": "2026-10-09T20:06:47.813263Z"
    }
  },
  "server": {
    "name": "io.github.Tavrin/saccade",
    "title": "Saccade",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "version": "0.3.0",
    "packages": [
      {
        "version": "0.3.0",
        "transport": {
          "type": "stdio"
        },
        "identifier": "saccade",
        "registryType": "cargo",
        "registryBaseUrl": "https://crates.io",
        "packageArguments": [
          {
            "type": "positional",
            "value": "mcp"
          },
          {
            "name": "--root",
            "type": "named",
            "format": "filepath",
            "valueHint": "capture_root",
            "isRequired": true,
            "description": "Absolute existing directory containing readable captures."
          },
          {
            "name": "--out-root",
            "type": "named",
            "format": "filepath",
            "valueHint": "report_root",
            "isRequired": true,
            "description": "Absolute report directory; must not contain or be inside the capture root."
          }
        ]
      }
    ],
    "repository": {
      "url": "https://github.com/Tavrin/saccade",
      "source": "github"
    },
    "description": "Perceptual visual regression, image evidence inspection and bounded decision proposals."
  }
}

Report an issue with this listing