# io.github.perzianhq/mantis (npm · mantis-browser)

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

- Trust score: 81/100 (high trust)
- Change this week: +14
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-25

## Components

- npm · `mantis-browser`: 81/100 (this document), [markdown](https://verifymcp.io/servers/perzianhq-mantis/mantis-browser.md), [page](https://verifymcp.io/servers/perzianhq-mantis/mantis-browser)

## Channel facts

- Registry: `npm`
- Package: `mantis-browser`
- Version: `0.1.5`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-25.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 36 of 107 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to perzianhq/mantis).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1045 tokens (~52/item across 20 items; 20 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 76/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 27% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 20 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 20 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.perzianhq/mantis MCP server?

io.github.perzianhq/mantis runs locally as an npm package, launched with npx -y mantis-browser. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add perzianhq-mantis -- npx -y mantis-browser
```

### Cursor

```json
{
  "mcpServers": {
    "perzianhq-mantis": {
      "command": "npx",
      "args": [
        "-y",
        "mantis-browser"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "perzianhq-mantis": {
      "command": "npx",
      "args": [
        "-y",
        "mantis-browser"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add perzianhq-mantis -- npx -y mantis-browser
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "perzianhq-mantis": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mantis-browser"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add perzianhq-mantis --command npx --arg -y --arg mantis-browser
```

### Hermes

```yaml
mcp_servers:
  perzianhq-mantis:
    command: "npx"
    args: ["-y", "mantis-browser"]
```

### Netclaw

```json
{
  "McpServers": {
    "perzianhq-mantis": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "mantis-browser"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add perzianhq-mantis -t stdio -c npx -a -y mantis-browser
```

### Other

```json
{
  "mcpServers": {
    "perzianhq-mantis": {
      "command": "npx",
      "args": [
        "-y",
        "mantis-browser"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-25 (score 81, +1)

- [functional improvement] Security disclosure: fail → pass

### 2026-10-24 (score 80, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-23 (score 64, −5)

- [security regression] Malware scan: pass → unverified
- [security improvement] Provenance: fail → pass
- [security] The attested source repository moved: perzianhq/mantis
- [functional regression] Schema quality: 45 → 52
- [functional regression] Tool coverage: 38% → 27%
- [functional] Package version: 0.1.2 → 0.1.4

### 2026-10-22 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-18 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 66, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-10-16 (score 66)

First indexed and scored.

## MCP tools (20)

### `open` (~26 tokens)

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

Input parameters:

- `url` (string, required)

### `read` (~190 tokens)

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.

Input parameters:

- `fresh` (boolean): Expand seen regions too (this call only)
- `full` (boolean): Untrimmed bounded excerpt; use offset for the next excerpt
- `offset` (integer): Character offset for the next full excerpt
- `region` (string): Label substring, e.g. "nav"; if none matches, text inside a region also works

### `find` (~66 tokens)

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.

Input parameters:

- `context_chars` (integer)
- `text` (string, required)

### `forget` (~16 tokens)

Clear region memory; next read shows everything.

### `click` (~19 tokens)

Click element #id.

Input parameters:

- `id` (integer, required)

### `type` (~38 tokens)

Replace input #id text; submit presses Enter.

Input parameters:

- `id` (integer, required)
- `submit` (boolean)
- `text` (string, required)

### `select` (~32 tokens)

Choose option text in select or combobox #id.

Input parameters:

- `id` (integer, required)
- `option` (string, required)

### `fill` (~63 tokens)

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.

Input parameters:

- `fields` (array, required)

### `press` (~49 tokens)

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.

Input parameters:

- `key` (string, required)

### `scroll` (~72 tokens)

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.

Input parameters:

- `direction` (string)
- `id` (integer)

### `back` (~13 tokens)

Back one page in history.

### `wait_for` (~72 tokens)

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

Input parameters:

- `id` (integer)
- `state` (string)
- `text` (string)
- `timeout_seconds` (number)

### `hover` (~22 tokens)

Hover element #id and show changes.

Input parameters:

- `id` (integer, required)

### `upload` (~45 tokens)

Set local file path(s) on #id.

Input parameters:

- `files` (array)
- `id` (integer, required)
- `path` (string)
- `paths` (array)

### `tabs` (~32 tokens)

List tabs, or switch/close tab #id.

Input parameters:

- `action` (string)
- `id` (integer)

### `media` (~43 tokens)

Only if read is insufficient: media → data (prefer) → ocr → look (last resort) → ask_human. Numbered images/canvases/charts.

### `data` (~58 tokens)

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

Input parameters:

- `id` (integer)
- `selector` (string): CSS selector

### `ocr` (~43 tokens)

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

Input parameters:

- `id` (integer)
- `selector` (string): CSS selector

### `look` (~53 tokens)

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

Input parameters:

- `id` (integer)
- `selector` (string): CSS selector

### `ask_human` (~93 tokens)

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

Input parameters:

- `reason` (string, required): What the human must do
- `timeout_seconds` (number): Default 300
- `until` (string): url_change | selector_gone:<css> | selector_present:<css>; default: URL or content change

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/perzianhq-mantis/mantis-browser#diagnostics

## Score history

- 2026-10-25: 81
- 2026-10-24: 80
- 2026-10-23: 64
- 2026-10-22: 69
- 2026-10-21: 68
- 2026-10-20: 68
- 2026-10-19: 67
- 2026-10-18: 67
- 2026-10-17: 66
- 2026-10-16: 66

## Common questions

### What is the io.github.perzianhq/mantis MCP server?

io.github.perzianhq/mantis is an MCP server listed in the public MCP registry as io.github.perzianhq/mantis. The web as short, numbered text for AI agents: a lean browser interface over Playwright. This page covers its npm package (mantis-browser).

### Is the io.github.perzianhq/mantis MCP server safe to use?

io.github.perzianhq/mantis scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 October 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.perzianhq/mantis MCP server expose?

io.github.perzianhq/mantis exposes 20 tools: open, read, find, forget, click, and 15 more. Their descriptions and schemas cost roughly 1,045 tokens of context every time the server is loaded.

### Is the io.github.perzianhq/mantis MCP server still maintained?

io.github.perzianhq/mantis is still listed as active in the MCP registry. We last reached this channel on 25 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.perzianhq/mantis MCP server under?

io.github.perzianhq/mantis declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/mantis-browser
- Socket report: https://socket.dev/npm/package/mantis-browser
- Repository: https://github.com/perzianhq/mantis
- Changelog RSS feed: https://verifymcp.io/servers/perzianhq-mantis/mantis-browser.xml
- Changelog JSON feed: https://verifymcp.io/servers/perzianhq-mantis/mantis-browser.json
- HTML version of this page: https://verifymcp.io/servers/perzianhq-mantis/mantis-browser