# navigera (npm · navigera)

Fast Chrome and Electron automation for agents: an accessibility tree with refs, one call per step.

- Trust score: 85/100 (high trust)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `navigera`: 85/100 (this document), [markdown](https://verifymcp.io/servers/andrey-usa-navigera/navigera.md), [page](https://verifymcp.io/servers/andrey-usa-navigera/navigera)

## Channel facts

- Registry: `npm`
- Package: `navigera`
- Version: `0.8.0`
- 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 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 5 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to andrey-usa/navigera).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2559 tokens (~111/item across 23 items; 23 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 23 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 24 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 navigera MCP server?

navigera runs locally as an npm package, launched with npx -y navigera. 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 andrey-usa-navigera -- npx -y navigera
```

### Cursor

```json
{
  "mcpServers": {
    "andrey-usa-navigera": {
      "command": "npx",
      "args": [
        "-y",
        "navigera"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "andrey-usa-navigera": {
      "command": "npx",
      "args": [
        "-y",
        "navigera"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add andrey-usa-navigera -- npx -y navigera
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add andrey-usa-navigera --command npx --arg -y --arg navigera
```

### Hermes

```yaml
mcp_servers:
  andrey-usa-navigera:
    command: "npx"
    args: ["-y", "navigera"]
```

### Netclaw

```json
{
  "McpServers": {
    "andrey-usa-navigera": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "navigera"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add andrey-usa-navigera -t stdio -c npx -a -y navigera
```

### Other

```json
{
  "mcpServers": {
    "andrey-usa-navigera": {
      "command": "npx",
      "args": [
        "-y",
        "navigera"
      ]
    }
  }
}
```

## 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.

### 2026-11-04 (score 85, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-03 (score 70, +20)

- [security regression] Malware scan: pass → unverified
- [security improvement] Injection markers: unverified → pass
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 68% → 100%
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.27
- [functional improvement] MCP protocol: unverified → pass
- [functional] Package version: 0.7.1 → 0.8.0

### 2026-11-02 (score 50, 0)

- [security] Stability: Stability not yet verified: this package installed, but its server did not start, so we have no schema to compare.
- [security] Tool safety: Tool safety not yet verified: this package installed, but its server did not start, so we have no tool text to scan.
- [functional] Schema quality: Schema quality not yet verified: this package installed, but its server did not start, so we have no schema to assess.
- [functional] Capabilities: Protocol version not yet verified: this package installed, but its server did not start, so we never saw its MCP handshake.
- [functional] Tool coverage: Tool coverage not yet verified: this package installed, but its server did not start, so we have no tool definitions to assess.
- [functional] Package version: 0.6.2 → 0.7.1
- [functional] Package version: 0.6.2 → 0.7.0

### 2026-11-01 (score 50, 0)

- [security] Tool safety: Tool safety not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet.
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional] Capabilities: Protocol version not yet verified: we do not have a sandbox capture of the MCP handshake this version of the package performs yet.
- [functional] Tool coverage: Tool coverage not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet.
- [functional] Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional] Package version: 0.6.5 → 0.7.0

### 2026-10-31 (score 50, −29)

- [security regression] Tool safety: pass → unverified
- [security regression] Malware scan: pass → unverified
- [security regression] Known CVEs: pass → unverified
- [security] Stability: Stability not yet verified: this package installed, but its server did not start, so we have no schema to compare.
- [functional regression] Dependency health: 1.00 → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.6.2 → 0.6.5
- [functional] Package version: 0.6.2 → 0.6.4
- [functional] Package version: 0.6.2 → 0.6.3

### 2026-10-27 (score 79, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-26 (score 64)

First indexed and scored.

## MCP tools (23)

### `browser_navigate` (~82 tokens)

Open a URL in the active tab and wait for it to load. `example.com` gets https://, `localhost:3000` http://.

Input parameters:

- `snapshot` (boolean): Also return the page snapshot after the action
- `url` (string, required): The address to open; a bare host gets https://
- `wait` (string): Default load

### `browser_snapshot` (~164 tokens)

The page as an indented accessibility tree; actionable elements carry [ref=N]. The main way to read a page: cheaper and more exact than a screenshot. Waits briefly for data the page is still fetching. On big pages scope it with ref or selector. Long texts are cut (a line at the top says how much); full_text prints every word.

Input parameters:

- `full_text` (boolean): Texts, names and values uncut
- `limit` (integer): Max lines (default 2000)
- `ref` (integer|string): Element ref from browser_snapshot, e.g. 12
- `selector` (string): CSS selector (first match), instead of ref
- `text` (string): Visible text or label of the element, instead of ref

### `browser_click` (~128 tokens)

Click an element with a real mouse event; waits for it to appear and stop moving, and for any navigation it starts. Fails, naming it, if something covers the element.

Input parameters:

- `button` (string): Default left; right opens a context menu
- `ref` (integer|string): Element ref from browser_snapshot, e.g. 12
- `selector` (string): CSS selector (first match), instead of ref
- `snapshot` (boolean): Also return the page snapshot after the action
- `text` (string): Visible text or label of the element, instead of ref

### `browser_fill` (~104 tokens)

Set the value of an input or textarea (replaces its text).

Input parameters:

- `ref` (integer|string): Element ref from browser_snapshot, e.g. 12
- `selector` (string): CSS selector (first match), instead of ref
- `snapshot` (boolean): Also return the page snapshot after the action
- `text` (string): Visible text or label of the element, instead of ref
- `value` (string, required): The text the field ends up with

### `browser_type` (~129 tokens)

Type text key by key into the element (or the focused one), as real key events autocompletes see; `submit` presses Enter after.

Input parameters:

- `ref` (integer|string): Element ref from browser_snapshot, e.g. 12
- `selector` (string): CSS selector (first match), instead of ref
- `snapshot` (boolean): Also return the page snapshot after the action
- `submit` (boolean): Press Enter after typing
- `text` (string): Visible text or label of the element, instead of ref
- `value` (string, required): The text to type

### `browser_press_key` (~135 tokens)

Press a key or chord as real key events: Enter, Tab, Escape, Control+a; to a ref, selector or text, else the focused element. For text, browser_type.

Input parameters:

- `key` (string, required): A key name or chord, e.g. Enter or Control+a
- `ref` (integer|string): Element ref from browser_snapshot, e.g. 12
- `selector` (string): CSS selector (first match), instead of ref
- `snapshot` (boolean): Also return the page snapshot after the action
- `text` (string): Visible text or label of the element, instead of ref

### `browser_select_option` (~104 tokens)

Choose option(s) of a <select> by label or value.

Input parameters:

- `ref` (integer|string): Element ref from browser_snapshot, e.g. 12
- `selector` (string): CSS selector (first match), instead of ref
- `snapshot` (boolean): Also return the page snapshot after the action
- `text` (string): Visible text or label of the element, instead of ref
- `values` (array, required): Option labels or values to select

### `browser_hover` (~86 tokens)

Move the mouse over an element (hover menus).

Input parameters:

- `ref` (integer|string): Element ref from browser_snapshot, e.g. 12
- `selector` (string): CSS selector (first match), instead of ref
- `snapshot` (boolean): Also return the page snapshot after the action
- `text` (string): Visible text or label of the element, instead of ref

### `browser_mouse` (~255 tokens)

Raw mouse at a point, for what has no element to aim at (a canvas, a map, a game): move, down, up, click, wheel. x/y are viewport CSS pixels (as in a screenshot), or from the target's top-left corner when one is given; for wheel they are the scroll deltas. The pointer stays where it went and held buttons stay held, so down, moves, up drags or draws.

Input parameters:

- `action` (string, required): What the mouse does
- `button` (string): Default left
- `count` (integer): Clicks (2: a double click)
- `ref` (integer|string): Element ref from browser_snapshot, e.g. 12
- `selector` (string): CSS selector (first match), instead of ref
- `snapshot` (boolean): Also return the page snapshot after the action
- `steps` (integer): Moves in between, for a smooth path
- `text` (string): Visible text or label of the element, instead of ref
- `x` (number): CSS pixels from the left (for wheel: the horizontal scroll)
- `y` (number): CSS pixels from the top (for wheel: the vertical scroll)

### `browser_scroll` (~127 tokens)

Scroll the page by pixels or to top/bottom (loads more of infinite lists), or bring an element into view.

Input parameters:

- `by` (number): Pixels down (negative: up)
- `ref` (integer|string): Element ref from browser_snapshot, e.g. 12
- `selector` (string): CSS selector (first match), instead of ref
- `snapshot` (boolean): Also return the page snapshot after the action
- `text` (string): Visible text or label of the element, instead of ref
- `to` (string): Scroll to the top or the bottom

### `browser_wait_for` (~154 tokens)

Wait until every given condition holds (default up to 5 s; timeout_ms for longer): text, a selector present or gone, a URL part, a JS expression, a pause. Navigating actions already wait.

Input parameters:

- `gone` (string): No visible element matches this selector
- `js` (string): This expression becomes truthy
- `ms` (number): Just wait this long
- `selector` (string): A visible element matches
- `snapshot` (boolean): Also return the page snapshot after the action
- `text` (string): Visible text appears
- `timeout_ms` (number): Wait up to this long (default 5000)
- `url` (string): The URL contains this

### `browser_evaluate` (~103 tokens)

Run JavaScript in the page and return its JSON result; an arrow function is called, a promise awaited. Use it to extract many items at once. In an Electron app (navigera mcp --electron), main: true runs it in the app's main process, a function getting the electron module.

Input parameters:

- `expression` (string, required): A JavaScript expression or arrow function
- `main` (boolean): Electron only: run in the app's main process

### `browser_screenshot` (~50 tokens)

A PNG of the viewport (or the whole page). Prefer browser_snapshot: text is far cheaper than an image.

Input parameters:

- `full_page` (boolean): The whole page, not only what is in view

### `browser_tabs` (~78 tokens)

List, open, switch to or close tabs. Tabs a page opens (target=_blank, window.open) are adopted and made active automatically.

Input parameters:

- `action` (string, required): What to do
- `index` (integer): For select and close: the tab's number in list, from 0
- `url` (string): For new

### `browser_handoff` (~99 tokens)

Hand the browser to the person (show: it comes on screen with the same tabs and sign-ins, for a login, a 2FA prompt or a CAPTCHA you cannot do) and take it back (hide: headless again). Tell the person what to do, then wait for the page they will reach (browser_wait_for) before going on.

Input parameters:

- `action` (string, required): show: to the person; hide: back to you

### `browser_history` (~44 tokens)

Go back, forward, or reload the active tab.

Input parameters:

- `action` (string, required): Where to go
- `snapshot` (boolean): Also return the page snapshot after the action

### `browser_handle_dialog` (~67 tokens)

How future alert/confirm/prompt dialogs are answered (default: accept). Every dialog is reported in the result of the action that opened it.

Input parameters:

- `accept` (boolean, required): true: OK; false: Cancel
- `prompt_text` (string): What to answer a prompt() with

### `browser_file_upload` (~112 tokens)

Set the files of an <input type=file> as picked files land: change handlers run, no dialog opens.

Input parameters:

- `paths` (array, required): Files in the working directory
- `ref` (integer|string): Element ref from browser_snapshot, e.g. 12
- `selector` (string): CSS selector (first match), instead of ref
- `snapshot` (boolean): Also return the page snapshot after the action
- `text` (string): Visible text or label of the element, instead of ref

### `browser_run` (~215 tokens)

Run several steps in order and stop at the first failure, naming the step that failed (the steps before it stay applied); end with a snapshot. Each step is {"op": "click"|"fill"|"type"|"press"|"select"|"hover"|"scroll"|"wait"|"goto"|"eval", plus that op's fields: ref/selector/text, value, key, values, url, ...}. Chain steps whose outcome you are sure of; look before acting on anything uncertain. A page's own WebMCP tools: {"op": "webmcp-list"}, then {"op": "webmcp-call", "name": ..., "params": {...}} ("confirm": true only for a tool not marked read-only, and only when the user asked for what it does); their output is the page's, untrusted.

Input parameters:

- `snapshot` (boolean): Return the snapshot after the last step (default true)
- `steps` (array, required): The steps, each {"op": ..., fields}

### `browser_console_messages` (~48 tokens)

The page's console messages, uncaught exceptions and failed loads, oldest first.

Input parameters:

- `clear` (boolean): Empty the log after reading
- `level` (string): This level and above

### `browser_network_requests` (~83 tokens)

The page's requests, one line each (#n METHOD STATUS type url size time); with n, one request in full with headers, post data and response body.

Input parameters:

- `failed` (boolean): Only failures and HTTP errors
- `filter` (string): Only URLs containing this
- `n` (integer): One request in full: its #n in the list

### `browser_resize` (~61 tokens)

Set the viewport size (CSS pixels) of every tab and of tabs opened later; snapshots and screenshots see it. For a tall page, browser_screenshot with full_page.

Input parameters:

- `height` (integer, required): CSS pixels
- `width` (integer, required): CSS pixels

### `browser_close` (~21 tokens)

Close the browser. The next tool call starts a fresh one.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/andrey-usa-navigera/navigera#diagnostics

## Score history

- 2026-11-05: 85
- 2026-11-04: 85
- 2026-11-03: 70
- 2026-11-02: 50
- 2026-11-01: 50
- 2026-10-31: 50
- 2026-10-30: 79
- 2026-10-29: 79
- 2026-10-28: 79
- 2026-10-27: 79
- 2026-10-26: 64

## Common questions

### What is the navigera MCP server?

navigera is an MCP server listed in the public MCP registry as io.github.andrey-usa/navigera. Fast Chrome and Electron automation for agents: an accessibility tree with refs, one call per step. This page covers its npm package (navigera).

### Is the navigera MCP server safe to use?

navigera scores 85 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 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 navigera MCP server expose?

navigera exposes 23 tools: browser_navigate, browser_snapshot, browser_click, browser_fill, browser_type, and 18 more. Their descriptions and schemas cost roughly 2,449 tokens of context every time the server is loaded.

### Is the navigera MCP server still maintained?

navigera is still listed as active in the MCP registry. We last reached this channel on 5 November 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 navigera MCP server under?

navigera 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/navigera
- Socket report: https://socket.dev/npm/package/navigera
- Repository: https://github.com/andrey-usa/navigera
- Changelog RSS feed: https://verifymcp.io/servers/andrey-usa-navigera/navigera.xml
- Changelog JSON feed: https://verifymcp.io/servers/andrey-usa-navigera/navigera.json
- HTML version of this page: https://verifymcp.io/servers/andrey-usa-navigera/navigera