io.github.perzianhq/mantis
The web as short, numbered text for AI agents: a lean browser interface over Playwright.
Installation
Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).
mantis-browserclaude mcp add mantis -- npx -y mantis-browser@0.1.10{
"mcpServers": {
"mantis": {
"command": "npx",
"args": [
"-y",
"mantis-browser@0.1.10"
]
}
}
}Documentation
Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.
Lets AI agents browse the web as short, numbered text instead of screenshots.
perzian.dev/mantis · by Perzian
It works with Claude Code, Codex, Cursor or your own agent as an MCP server. Install in two commands.
How it works
What the agent sees
Results
Same tasks, same pass criteria, three ways to browse. Mantis vs the accessibility tree (Playwright MCP) vs screenshots.
Long multi-step workflows (long-local-v1: 16 local tasks with in-page hazards, 3 runs per approach, code-graded). Score is out of 48; time is mean agent execution per run.
| Model | Mantis | Accessibility tree | Screenshots | |
|---|---|---|---|---|
gpt-6-luna | Correct | 48/48 | 48/48 | 42/48 |
| Time | 103s | 132s | 163s | |
| Input tokens | 17.3M | 28.0M | 31.0M | |
| Tool calls | 1190 | 1685 | 2774 | |
claude-haiku-5-5 | Correct | 48/48 | 48/48 | 48/48 |
| Time | 42s | 59s | 64s | |
| Input tokens | 12.1M | 18.7M | 27.1M | |
| Tool calls | 1501 | 1827 | 2876 |
Real sites (live-v1 v1.7: 30 tasks, 3 runs per approach, judged blind). Success out of 90:
| Model | Mantis | Accessibility tree | Screenshots |
|---|---|---|---|
gpt-6-luna | 89 | 90 | 85 |
claude-haiku-5-5 | 87 | 86 | 89 |
Net: Accuracy is on par with the tree (within 1 run of 90 on real sites, equal on long workflows). The roughly 30% saving in tokens and calls was measured on long workflows that run on local fixtures, not live sites; on real-site tasks, which are shorter, the difference is smaller. Accuracy claims cover read/navigate tasks on public sites with Luna and Haiku. The screenshot baseline is our own minimal tool, not a product's.
Where Mantis is better
- Long workflows. Same accuracy as the tree, with 22–29% less time, 35–38% fewer input tokens and 18–29% fewer tool calls, because each step returns only what changed.
- Versus screenshots. Fewer tokens and calls everywhere; Luna also missed 6 of 48 where Mantis and the tree did not.
- Short tasks. Roughly a tie with the tree. The edge grows with task length.
Method and caveats: bench/RESULTS.md.
Learn more
- How it works in detail
- Claude skill: teaches Claude how to read Mantis output
- Install, configuration and tool reference
- Re-running the benchmarks
License
MIT
Questions fréquentes
Qu'est-ce que io.github.perzianhq/mantis ?
The web as short, numbered text for AI agents: a lean browser interface over Playwright.
Comment installer io.github.perzianhq/mantis ?
Il s'exécute sur votre machine. Dans Claude Code : claude mcp add mantis -- npx -y mantis-browser@0.1.10. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.
Faut-il une clé API pour io.github.perzianhq/mantis ?
Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.
io.github.perzianhq/mantis est-il open source ?
Oui. Son code est sur GitHub sous licence MIT.
Qui maintient io.github.perzianhq/mantis ?
Il est publié par perzianhq. AI.tn le référence sans le maintenir ni le recommander.
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.