MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Autonomous web form inspector and schema auto-mapper matching input attributes, autocomplete hints, and regex validations to agent state.
MCPLink only★ 7
Autonomous web form inspector and schema auto-mapper matching input attributes, autocomplete hints, and regex validations to agent state.
MCPLink only★ 7
MCP server for native Qt application automation. Inject into any running QWidget or QML app, snapshot the UI tree, find elements by text/type/property, click, type and read state from Claude, Cursor o
MCPLink only★ 6
Autonomous DOM state tree mutation observer & selector healer (Browser Use)
SkillLink only★ 8
Telos is a local workbench that runs MCP tools, keeps durable state and writes a receipt for each action.
MCPLink only★ 4Few stars
Utsuri transforms code changes into evidence-based, human-readable visual reviews. It connects Git hunks, intent, real-browser rendering, structural evidence, coverage, and human review state in one l
SkillLink only★ 2Few stars
Multi-platform publishing middleware with REST/MCP interfaces, task state, deduplication, retries and API/Playwright adapters.
MCPLink only★ 5
Manual-orchestration agent farm: spawn Claude Code subagents and headless workers on demand, with sqlite state and per-agent permission scopes
SkillLink only★ 1Few stars
HTML collaboration workspace for AI agents and humans. Agents add components via CLI, humans interact via browser, state flows back as structured JSON.
SkillLink only★ 5
End-to-end TapPay shopping and checkout skill that combines wallet readiness, merchant selection, browser checkout execution, payment field handling, and stale-state recovery into one continuous contr
SkillLink only★ 4Few stars
Claude Code skill for browser automation with persistent page state. Fork of SawyerHood/dev-browser.
SkillLink only★ 3Few stars
AI browser agent testing for staging apps: sign in as a real account state (free, paid, lapsed, team), follow a plain-English goal, verify against the database. Agent skill for Claude Code, Codex.
SkillLink onlyFew stars
Playwright for terminals — MCP server that lets AI agents interact with TUI/CLI applications through structured Terminal State Tree detection
MCPLink only★ 1Few stars
Parallel orchestrated development with worktree-isolated subagents, shared state, and Playwright verification. Claude Code plugin.
SkillLink onlyFew stars
Human-reviewed browser agent harness using Trackly MCP, Codex computer use, state-bound approval, and fail-closed recovery.
MCPLink onlyFew stars
Who stands behind it
