npx -y -p mantis-browser mantis install
claude mcp add mantis -- npx -y -p mantis-browser mantis-mcp
npx -y -p mantis-browser mantis read https://example.com   # try it without an agent

Windows, Linux servers and other agents: SETUP.

Side-by-side replay of the same task with Mantis and Playwright MCP: Mantis finishes in 10 calls and about 292k input tokens, Playwright MCP in 22 calls and about 733k

One real task (Luna, logged runs replayed): about a third less time, over 2x fewer input tokens, about half the calls. This is a selected example from 16 long tasks; medians across all 16 are in Results. Full video.

Security and threat model: SECURITY.md.

How it works

Agent sends open/click to Mantis; Mantis reads the page in Chromium, numbers each control and returns only what changed; CAPTCHA, 2FA and payment go to you

What the agent sees

A shop page with a cookie popup becomes 8 numbered lines; after click #3 only the changes come back

Results

Mantis vs the accessibility tree (Playwright MCP) on public sites, gpt-6-luna and claude-haiku-5-5. Every cell is a per-run median; time is end-to-end wall time per run:

Long tasks (correct: 14 keyed tasks, 42 runs per cell; medians: all 16 tasks, 48 runs per cell; both approaches run in the same session):

	Luna Mantis	Luna tree	Haiku Mantis	Haiku tree
Correct	35/42	34/42	40/42	40/42
Input tokens (median)	244k	345k	268k	506k
Tool calls (median)	17	24	19	30
Time (median)	42s	66s	54s	85s

Short tasks (30 tasks, 90 runs per cell; tree and screenshot columns are the earlier 20261026 run):

	Luna Mantis	Luna tree	Luna screenshot	Haiku Mantis	Haiku tree	Haiku screenshot
Correct	88/90	86/90	90/90	90/90	88/90	88/90
Input tokens (median)	64k	99k	104k	38k	88k	33k
Tool calls (median)	3	4	7	3	5	6
Time (median)	16s	31s	35s	19s	30s	23s

Long tasks: accuracy within one run, 29-47% fewer input tokens, 29-37% fewer calls and about a third less time than the tree. Short tasks: accuracy equal or better than the tree, 35-57% fewer input tokens. Short-task times compare a newer Mantis build with the earlier tree and screenshot run, so treat that gap as indicative. Screenshots score 2 runs higher on Luna but use more tokens and time there; on Haiku they use fewer tokens.

Scores come from deterministic answer keys on the final page state. Two long iframe/tab tasks can't be keyed and are left out of the long-task counts. Method, screenshot baseline and caveats: bench/RESULTS.md.

Limitations

No canvas input: canvas, WebGL, maps and drawing apps are described only as canvas, with no coordinate click or draw tool.
Login and bot walls need ask_human, which needs a display.
Benchmarked only on read, navigate and form-fill tasks on public sites, with two models. The screenshot baseline is this project's own tool, and a few tasks were swapped after results (disclosed).
Page content is untrusted data; see SECURITY.md.
Small v0.1.x beta.