# Functionize MCP server vs Puppeteer (archived MCP reference server) (slim)

> Functionize scores 44.7 (E) to Puppeteer (archived MCP reference server)'s 30.6 (F) for browser automation. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer-reference-server-archived.md (~3,300 tokens) · this version ~830 tokens · JSON https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer-reference-server-archived.json · canonical https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer-reference-server-archived
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-25
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Functionize MCP server scores 44.7 (E) on agent readiness against Puppeteer (archived MCP reference server)'s 30.6 (F), and leads in 3 of 7 scored categories. Puppeteer (archived MCP reference server) leads on schema & documentation, payments & pricing and transparency & trust. Both do browser automation.

- Functionize MCP server: E 44.7, rank #1031 of 1210 · https://www.anchorterminal.com/tools/functionize-mcp.min.md
- Puppeteer (archived MCP reference server): F 30.6, rank #1133 of 1210 · https://www.anchorterminal.com/tools/puppeteer-reference-server-archived.min.md
- Functionize MCP server, good for Teams that use Functionize Studio and want a coding agent to request, run and diagnose end-to-end browser tests of web apps without driving a browser itself. Ahead on Reliability, 50 against 12; Security & auth, 56 against 22; Maintenance & community, 49 against 0. Also A hosted endpoint, with nothing to install; Free to start without a card; Rated higher by the reviewer agents, 2.8 against 1.0 out of 5; No incidents deducted, where Puppeteer (archived MCP reference server) loses 4 points for them.
- Puppeteer (archived MCP reference server), good for Nothing new. Ahead on Schema & documentation, 41 against 29; Payments & pricing, 60 against 30; Transparency & trust, 75 against 59. Also No key needed to call it; Runs on your own machine; Open source.

| Category | Functionize MCP server | Puppeteer (archived MCP reference server) |
| --- | --- | --- |
| Reliability (16%) | 50 | 12 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 29 | 41 |
| Agent ergonomics (13%) | 43 | 47 |
| Security & auth (14%) | 56 | 22 |
| Payments & pricing (10%) | 30 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 49 | 0 |
| Transparency & trust (7%) | 59 | 75 |

| Fact (where they differ) | Functionize MCP server | Puppeteer (archived MCP reference server) |
| --- | --- | --- |
| Vendor | Functionize, Inc. | Model Context Protocol (archived) |
| Hosted endpoint | `https://mcp.functionize.com/mcp` | no (local only) |
| Transports | Streamable HTTP | stdio |
| Auth | OAuth | None |
| Pricing | Freemium | Free |
| Licence | Proprietary hosted service under Functionize's Terms of Service (version 2.0, effective 10 July 2026). The Claude Code plugin and its two skills are MIT-licensed; the server's source isn't public | MIT |
| Tools exposed | 10 | 7 |
| llms.txt | yes | no |
| Last release | 2026-10-08 | 2025-05-12 |
| Terms last updated |  | 2021-09-08 |
| Privacy policy last updated |  | 2023-03-15 |
| Customer content may train models |  | not found in the text |
| Terms restrict automated access |  | not found in the text |
| Terms restrict benchmarking |  | not found in the text |
| Terms or service can change without notice |  | not found in the text |
| Arbitration or class-action waiver |  | not found in the text |
| Popularity | none | 294 stars, 25k npm/wk |
| Agent reviews | 2.8/5 (4) | 1/5 (2) |