BugBug

io.github.bugbug-ioPublished by GitHub account bugbug-iov14.22.0Updated Nov 5, 2026

BugBug test automation workflows for AI agents

VerifiedStreamable HTTPWeb executableBrowser AutomationDeveloper Tools

Overview

AI-generated overview

Hosted BugBug MCP endpoint that lets an AI client inspect, plan, author and debug BugBug test automation projects and runs.

What you can do
  • Inspect BugBug projects, tests, suites, profiles and project details
  • Plan test coverage and create or maintain tests from an approved plan
  • Author, review and repair element selectors, steps and BugBug YAML
  • Investigate failed runs with run details, diagnostics, screenshots and DOM snapshots
  • Review and refactor tests, groups, components and suites
  • Summarize project and run health for QA and product reporting
When to use it
Use it when you want an AI coding client such as Cursor, Claude Code, Codex, VS Code or Copilot to work directly with BugBug tests and test results, from coverage planning through debugging failed runs.
Requirements
Remote MCP endpoint at mcp.bugbug.io reached over streamable HTTP, with OAuth sign-in completed by the chosen AI client. A BugBug account on a Pro plan or higher is required for MCP access; skills alone are available on all plans. The README's installer is run via npx with a supported client name.
Before you install
The connection can change BugBug resources, not just read them; the README states changes require the user's explicit authorization, so confirm before approving writes. OAuth grants the client access to your BugBug account. The installer does not accept a token, so sign-in happens in the client.

Installation

In SourceWeft

  1. Open BugBug in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.bugbug-io%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "bugbug": {
      "type": "http",
      "url": "https://mcp.bugbug.io/mcp"
    }
  }
}

README

[BugBug logo]

BugBug Agent Plugin

Install BugBug's skills and hosted MCP connection into your AI client with the BugBug CLI:

sh
npx @bugbug-io/cli plugin --agent=<agent>

Choose exactly one supported client: cursor, claude, vscode, codex, or copilot. Use --dry-run to preview the installation.

The installer does not accept --token. The AI client you select completes its own MCP OAuth sign-in after installation. The plugin connects to the production endpoint at https://mcp.bugbug.io/mcp.

Features

  • Ready in one command — Set up Claude Code, Codex, Cursor, GitHub Copilot, or VS Code with the BugBug CLI; the selected client completes OAuth sign-in.
  • Turn requirements into coverage — Use BugBug's workflow guidance and live project context to plan coverage, then create tests from an approved plan.
  • Build with live BugBug context — Combine 50 MCP tools and 8 workflow prompts with 9 skills so your agent can inspect the tests, suites, profiles, and project details it needs.
  • Debug from evidence — Investigate failed runs with run details, failure diagnostics, screenshots, and DOM snapshots, guided by a safe debugging workflow.
  • Keep suites reliable as they grow — Review selectors, tests, reusable components, and suites with BugBug-specific guidance before making targeted improvements.
  • Turn run history into decisions — Summarize project and run health for actionable QA and product insights, using live data instead of guesswork.

Skills provide safe workflow guidance; MCP supplies the live BugBug data and actions. Changes to BugBug resources require the user's explicit authorization.

What you get

Skills are available on all BugBug plans. MCP access requires Pro or higher.

Bundled skills

SkillCapability
bugbug-context-discoveringDiscover the BugBug project, repository, and tested-application context.
bugbug-project-reportingCreate read-only project health reports for PM and QA audiences.
bugbug-selectors-authoringAuthor, review, repair, and optimize element selectors.
bugbug-steps-authoringChoose step types and create or update step payloads.
bugbug-test-run-debuggingInvestigate test runs and classify failures.
bugbug-tests-authoringCreate and maintain tests from an approved plan.
bugbug-tests-planningPlan end-to-end and UI test coverage.
bugbug-tests-refactoringAnalyze and refactor tests, groups, components, and suites.
bugbug-yaml-authoringCreate, validate, repair, and explain BugBug YAML.

When to use it

Use the plugin when you want an AI coding client to work with BugBug tests and test results. Use its skills for workflow guidance and its MCP connection for live BugBug data, runs, exports, diagnostics, and explicit mutations.

For the complete MCP registry, see the MCP server docs.

Source: README.md at commit c109192

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

18
  1. v14.22.0LatestNov 5, 2026
  2. v14.21.0Nov 3, 2026
  3. v14.20.0Oct 29, 2026
  4. v14.18.0Oct 22, 2026
  5. v14.17.0Oct 22, 2026
  6. v14.16.0Oct 20, 2026
  7. v14.15.1Oct 15, 2026
  8. v14.13.0Oct 15, 2026
  9. v14.12.0Oct 13, 2026
  10. v14.11.0Oct 7, 2026
  11. v14.10.0Oct 7, 2026
  12. v14.9.0Oct 6, 2026
  13. v14.8.0Oct 1, 2026
  14. v14.7.2Sep 29, 2026
  15. v14.7.0Sep 24, 2026
  16. v14.6.0Sep 22, 2026
  17. v14.5.0Sep 17, 2026
  18. v14.4.3Sep 16, 2026

Score

85% 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 daysRequired25 pts
  • Auth declaredRequired10 pts
  • 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