[External Plugin]: Figranium

[asernasr]

Plugin name

figranium

Short description

Figranium gives GitHub Copilot deterministic browser automation through MCP. Connect to a self-hosted Figranium instance to create and execute reusable visual browser tasks for scraping, data extraction, testing, scheduling, and other browser workflows instead of having agents improvise every browser interaction.

GitHub repository

figranium/figranium-mcp

Plugin path inside the repository

No response

Ref to review

No response

Commit SHA to review

ca6f65622e83f5958aef9666004f88742109d54c

Version

1.3.0

License identifier

Apache-2.0

Author name

Aser Nasr

Author URL

No response

Homepage URL

No response

Keywords

browser-automation
mcp
web-scraping
automation
copilot

Additional notes for reviewers

No response

Submission checklist

• The plugin lives in a public GitHub repository.
• The ref and/or sha I provided is immutable (release tag and/or full 40-character commit SHA), not a branch.
• This submission follows this repository's contribution, security, and responsible AI policies.
• This plugin is not already listed in the Awesome Copilot marketplace.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

✅ External plugin intake passed

This submission passed automated intake validation and quality checks and is ready for maintainer review.

• Plugin: figranium

• Repository: https://github.com/figranium/figranium-mcp

• SHA: ca6f65622e83f5958aef9666004f88742109d54c

Reviewer signals

These are non-blocking heuristics for maintainer review; they are not evidence of misconduct or low quality.

Signal	Result
Repository age	39 day(s)
Repository activity	0 watchers; 0 forks
Repository counts	5 stars · 0 watchers · 0 forks · 0 open issues/PRs

Quality gate summary

Legend: ✅ pass · ⚠️ warning · 🛑 fail

Gate	Status
spec compliance (non-blocking)	✅ pass
vally lint	✅ pass
install smoke test	✅ pass
version match	✅ pass
ref/sha consistency	⚪ not_run
canvas structure	⚪ not_run

• spec compliance: pass
• vally lint: pass
• install smoke test: pass
• version match: pass
• ref/sha consistency: not_run
• canvas structure: not_run
• overall: pass

spec compliance output (✅ pass)

Agent Plugins v1.0.0 manifest checks passed for plugin.json.

vally lint output (✅ pass)

0 skill(s) linted

install smoke test output (✅ pass)

Install smoke test succeeded. Verified /tmp/external-plugin-quality-FkWl7n/copilot-home/.copilot/installed-plugins/external-plugin-intake/figranium/plugin.json.

Version match output

- ca6f65622e83f5958aef9666004f88742109d54c: matched version "1.3.0" at "plugin.json".

Ref/SHA consistency output

Ref/SHA consistency gate skipped because one of source.ref or source.sha was not provided.

Canvas structure output

Canvas structure gate skipped because plugin is not tagged with "canvas".

Canonical external.json payload

{
  "name": "figranium",
  "description": "Figranium gives GitHub Copilot deterministic browser automation through MCP. Connect to a self-hosted Figranium instance to create and execute reusable visual browser tasks for scraping, data extraction, testing, scheduling, and other browser workflows instead of having agents improvise every browser interaction.",
  "version": "1.3.0",
  "author": {
    "name": "Aser Nasr"
  },
  "repository": "https://github.com/figranium/figranium-mcp",
  "license": "Apache-2.0",
  "keywords": [
    "browser-automation",
    "mcp",
    "web-scraping",
    "automation",
    "copilot"
  ],
  "source": {
    "source": "github",
    "repo": "figranium/figranium-mcp",
    "sha": "ca6f65622e83f5958aef9666004f88742109d54c"
  }
}

View workflow run

[aaronpowell]

I'm struggling to understand the value of this in the context of an agentic workflow, and the context of Copilot. Copilot already has easy install for Playwright as a browser automation engine, and from what I can tell Playwright underpins how Figranium performs its tasks anyway. It seems that this is a visual designer on building the workflows that Playwright will execute, and a visual editor isn't really that useful for an agentic workflow as the agent doesn't need to "see" things.

[asernasr]

The visual editor is for the human to design it and the agent to run it like an API, not a browser. Think Apify but self hosted. The human builds the task and the agent calls it even if the target platform doesn't have an API or an MCP server.