io.github.perzianhq/mantis
The web as short, numbered text for AI agents: a lean browser interface over Playwright.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
mantis-browserclaude mcp add mantis -- npx -y mantis-browser@0.1.10{
"mcpServers": {
"mantis": {
"command": "npx",
"args": [
"-y",
"mantis-browser@0.1.10"
]
}
}
}Documentation
From the project's README on GitHub, refreshed weekly. Links open on 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
Frequently asked questions
What is io.github.perzianhq/mantis?
The web as short, numbered text for AI agents: a lean browser interface over Playwright.
How do I install io.github.perzianhq/mantis?
It runs on your machine. In Claude Code: claude mcp add mantis -- npx -y mantis-browser@0.1.10. For other clients, paste the JSON configuration from this page into their MCP settings.
Does io.github.perzianhq/mantis need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is io.github.perzianhq/mantis open source?
Yes. Its code is on GitHub under the MIT license.
Who maintains io.github.perzianhq/mantis?
It is published by perzianhq. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.