Both sit in the tools & integrations layer with similar commercial terms, so the practical split is language: Arcade targets Python and Playwright MCP targets TypeScript.
Tool-calling with per-user OAuth, so the agent acts as the user, not as root.
The per-user token model is what stops one user's agent reading another user's mailbox.
Drive a real local browser over MCP, using the accessibility tree.
| Arcade | Playwright MCP | |
|---|---|---|
| Licence | Open source | Open source |
| Pricing | freemium | open source |
| Self-hostable | Yes | Yes |
| Languages | Python, TypeScript | TypeScript |
| Install | — | npm install -g @playwright/mcp |
| Keys required | ARCADE_API_KEY | None |
Both sit in the tools & integrations layer with similar commercial terms, so the practical split is language: Arcade targets Python and Playwright MCP targets TypeScript. Arcade: Tool-calling with per-user OAuth, so the agent acts as the user, not as root. Playwright MCP: Drive a real local browser over MCP, using the accessibility tree.
Arcade can run on your own infrastructure. Playwright MCP can run on your own infrastructure.
Arcade is open source (freemium). Playwright MCP is open source (open source).
Every page here answers to Accept: text/markdown and returns the same content at roughly a tenth the tokens. No separate site, no toggle — same URL.
curl -s -H "Accept: text/markdown" https://newagent.build/compare/arcade-vs-playwright-mcp