Skip to content
Agentmart
Submit a tool

Mantis

The web as short, numbered text for AI agents: a lean browser interface over Playwright.

Connector by perzianhq · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/perzianhq-mantis

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

The web as short, numbered text for AI agents: a lean browser interface over Playwright.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
6 read · 11 write · 1 delete · 6 not yet classified
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Node.js package

Tools by what they do 24

Read from the source code; the running server may list different tools.

Read 6 · Look things up without changing anything.

  • ask_human
  • bench_capture
  • find
  • look
  • read
  • tabs

Write 11 · Create, change, send or run things.

  • click
  • fill
  • hover
  • navigate
  • ocr
  • press
  • record_value
  • scroll
  • select
  • type
  • upload

Delete 1 · Delete, drop, revoke or wipe things.

  • forget

Not yet classified 6 · We could not tell from the name and description.

  • back
  • computer
  • data
  • media
  • open
  • wait_for

Files it touches

  • Any path the agent passes to its tools

Tools (24)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • ask_human

    Human handoff for CAPTCHA, 2FA, payment or login; never solves CAPTCHAs. Waits for a page change, then returns the page.

  • back

    Go back one page.

  • bench_capture

    Harness-only viewport capture; with `evaluate` (source of a function, as in browser_evaluate), also returns its result as text.

  • click

    Click element #id.

  • computer

    Description is built at runtime.

  • data

    Prefer; text only. Extract image/SVG/chart alt, caption, text or Chart.js/ECharts/Highcharts values. id from read()/media(), or CSS selector.

  • fill

    Prefer one mixed call for related text, dropdown, and checkbox fields; unrelated fields stay unchanged. Verify entity identity before editing. On failure or rerender it stops and reports partial completion; after confirmed completion, report it rather than re-inspecting.

  • find

    Case-insensitive whole-page text search, including trimmed content; returns #numbers, actionable row neighbours, and bounded local context. Use context_chars to expand just that local context; a matched heading is not a region label.

  • forget

    Clear region memory; next read shows everything.

  • hover

    Hover element #id and show changes.

  • look

    LAST RESORT; only image-returning tool (PNG, max 800px). Only after read/data/ocr failed. id or CSS selector.

  • media

    Description is built at runtime.

  • navigate

    Go to a URL. This benchmark-only browser navigation is separate from the computer tool.

  • ocr

    Text-only OCR for image/canvas. Use if data found nothing. id or CSS selector.

  • open

    Open URL as numbered page text; act by #number.

Show 9 more tools
  • press

    Press a key, e.g. Enter. For bottom-loaded feeds, try End (Control+End if no movement) to load more; repeat only while new items appear.

  • read

    Numbered text; act by #number. ~"x" names are guesses. "Same as before" retains #numbers; region/full/fresh expands it; full is paged with offset. Verify the entity identity before editing. Before finishing, re-read and visibly verify every task constraint (filters, sort, size, quantity, date range). After an action confirms completion, stop and report it rather than re-inspecting. If #number is stale, read() and retry; if on the wrong page, back() and keep searching.

  • record_value

    Record the requested integer.

  • scroll

    Scroll up/down/left/right (default down). id alone brings #id into view; id + direction scrolls its containing list/panel/table. For wide tables use right; without id, a scrollable container is used when the page cannot scroll.

  • select

    Choose option text in select or combobox #id.

  • tabs

    List tabs, or switch/close tab #id.

  • type

    Replace input #id text; submit presses Enter.

  • upload

    Set local file path(s) on #id.

  • wait_for

    Wait up to 10s: text states are present (or appears) / disappears; #id states are present / enabled. On timeout, inspect the returned current observation.

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Oct 24, 2026 (5 days ago)
Last release
Oct 25, 2026 (4 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.perzianhq/mantis
Version
0.1.6
Auth
No auth
Packages
npm mantis-browser
License
MIT
Repository
github.com/perzianhq/mantis
First seen
Oct 24, 2026
Last checked
Oct 26, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Mantis MCP server. Agent Mart. https://agentmart.dev/connectors/perzianhq-mantis (last updated 2026-10-26)