Browsegrab

Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

Not yet automatically verified

We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag — we're steadily working through the catalog.

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "browsegrab": {
      "command": "uvx",
      "args": [
        "browsegrab"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Documentation Overview

browsegrab

한국어 문서 · llms.txt

Token-efficient browser agent for local LLMs — Playwright + accessibility tree + MarkGrab, MCP native.

browsegrab is a lightweight browser automation library designed for local LLMs (8B-35B parameters). It combines Playwright's accessibility tree with MarkGrab's HTML-to-markdown conversion to achieve 5-8x fewer tokens per step compared to alternatives like browser-use.

Features

Token-efficient: ~500-1,500 tokens/step (vs 4,000-10,000 for browser-use)
Local LLM first: Optimized for vLLM, Ollama, and OpenAI-compatible endpoints
MCP native: Built-in MCP server with 8 browser automation tools
MarkGrab integration: HTML → clean markdown for content extraction
Accessibility tree + ref system: Stable element references (e1, e2, ...) without vision models
Success pattern caching: Zero LLM calls on repeated workflows
5-stage JSON parser: Robust action parsing for local LLM outputs
Minimal dependencies: Only playwright + httpx in core

Installation

Terminal

pip install browsegrab
playwright install chromium

With optional features:

Terminal

pip install browsegrab[mcp]      # MCP server support
pip install browsegrab[content]  # MarkGrab content extraction
pip install browsegrab[cli]      # CLI with rich output
pip install browsegrab[all]      # Everything

Quick Start

Python API

server.ts

from browsegrab import BrowseSession

async with BrowseSession() as session:
    # Navigate and get accessibility tree snapshot
    await session.navigate("https://example.com")
    snap = await session.snapshot()
    print(snap.tree_text)
    # - heading "Example Domain" [level=1]
    # - link "Learn more": [ref=e1]

    # Click using ref ID
    result = await session.click("e1")
    print(result.url)  # https://www.iana.org/help/example-domains

    # Type into search box
    await session.navigate("https://en.wikipedia.org")
    snap = await session.snapshot()
    await session.type("e4", "Python programming", submit=True)

    # Extract compressed content (AX tree + markdown)
    content = await session.extract_content()

CLI

bash

# Accessibility tree snapshot
browsegrab snapshot https://example.com

# JSON output
browsegrab snapshot https://example.com -f json

# Extract content (AX tree + markdown)
browsegrab extract https://en.wikipedia.org/wiki/Python

# Agentic browse (requires LLM endpoint)
browsegrab browse https://example.com "Find the about page"

MCP Server

bash

browsegrab-mcp  # Start MCP server (stdio)

Claude Desktop / Cursor / VS Code config:

config.json

{
  "mcpServers": {
    "browsegrab": {
      "command": "browsegrab-mcp"
    }
  }
}

8 MCP tools: browser_navigate, browser_click, browser_type, browser_snapshot, browser_scroll, browser_extract_content, browser_go_back, browser_wait

How It Works

Agent Browse Loop

mermaid

flowchart LR
    A["🌐 URL + Goal"] --> B["Navigate"]
    B --> C["AX Tree Snapshot\n~200–500 tokens"]
    C --> D{"LLM\nDecision"}
    D -->|"click / type / scroll"| E["Execute Action"]
    E --> C
    D -->|"goal reached"| F["Extract Content\n(MarkGrab)"]
    F --> G["✅ Result"]

Token Efficiency

browsegrab separates structure (accessibility tree) from content (MarkGrab markdown), sending only what the LLM needs:

mermaid

flowchart TD
    A["Raw HTML"] --> B["Accessibility Tree"]
    A --> C["MarkGrab Markdown"]
    B --> D["Structure: ~200–500 tokens\nInteractive elements with ref IDs"]
    C --> E["Content: ~300–800 tokens\nClean markdown · on-demand"]
    D --> F["Combined: ~500–1,300 tokens/step\n⚡ 5–8× fewer than browser-use"]
    E --> F

Token efficiency (measured)

Page	Interactive elements	Tokens	browser-use equivalent
example.com	1	~60	~500+
Wikipedia article	452	~1,254	~10,000+

Architecture

server.ts

browsegrab/
├── config.py                 # Dataclass configs (env var loading)
├── result.py                 # Result types (ActionResult, BrowseResult, ...)
├── session.py                # BrowseSession orchestrator
├── browser/
│   ├── manager.py            # Playwright lifecycle (async context manager)
│   ├── snapshot.py           # Accessibility tree + ref system
│   ├── selectors.py          # 4-strategy selector resolver
│   └── actions.py            # navigate, click, type, scroll, go_back, wait
├── dom/
│   ├── ref_map.py            # ref ID ↔ element bidirectional mapping
│   └── compress.py           # AX tree + MarkGrab → compressed context
├── llm/
│   ├── base.py               # LLMProvider ABC
│   ├── provider.py           # vLLM, Ollama, OpenAI-compatible
│   ├── prompt.py             # System prompts (~400 tokens)
│   └── parse.py              # 5-stage JSON fallback parser
├── agent/
│   ├── history.py            # Sliding window history compression
│   ├── cache.py              # Domain-based success pattern cache
│   └── loop_guard.py         # Duplicate action detection
├── __main__.py               # CLI (click)
└── mcp_server.py             # FastMCP server (8 tools)

Configuration

All settings via environment variables (BROWSEGRAB_* prefix):

bash

# Browser
BROWSEGRAB_BROWSER_HEADLESS=true
BROWSEGRAB_BROWSER_TIMEOUT_MS=30000

# LLM (for agentic browse)
BROWSEGRAB_LLM_PROVIDER=vllm          # vllm | ollama | openai
BROWSEGRAB_LLM_BASE_URL=http://localhost:8000/v1
BROWSEGRAB_LLM_MODEL=Qwen/Qwen3.5-32B-AWQ

# Agent
BROWSEGRAB_AGENT_MAX_STEPS=10
BROWSEGRAB_AGENT_ENABLE_CACHE=true

Part of the QuartzUnit Ecosystem

Library	Role
markgrab	Passive extraction (URL → markdown)
snapgrab	Passive capture (URL → screenshot)
docpick	Document OCR → structured JSON
browsegrab	Active automation (goal → browser actions → results)

Development

bash

git clone https://github.com/QuartzUnit/browsegrab.git
cd browsegrab
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
playwright install chromium

# Unit tests (no browser needed)
pytest tests/ -m "not e2e"

# Full suite including E2E
pytest tests/ -v

License

MIT

_{Part of the QuartzUnit ecosystem — composable Python libraries for data collection, extraction, search, and AI agent safety.}

Read the full README →View source on GitHub →

Related MCP Servers

View all in Browser Automation View all alternatives

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

Last commit

5mo ago

Most recent push to the default branch.

Directory activity

1 views

Config copies, upvotes, and views on AllMCPs.

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Browsegrab

Add the following block to your claude_desktop_config.json under mcpServers: "mcpServers": { "browsegrab": { "command": "uvx", "args": ["browsegrab"] } }

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/browsegrab?style=directory)](https://allmcps.com/mcp/browsegrab)

HTML Embed

<a href="https://allmcps.com/mcp/browsegrab"><img src="https://allmcps.com/api/badge/browsegrab?style=directory" alt="Browsegrab on AllMCPs" /></a>

Technical Specs & Signals

CategoryBrowser Automation

11/12 checks healthy over the last 45d

36Quality signal: Fair · 36/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools16/30

Adoption & activity1/15

Community engagement0/10

A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 2d ago via OSV.dev · browsegrab (PyPI)

★ Spotlight Slot

Feature Your MCP Server

Get maximum visibility for your server across our directory, search results, and detail pages.

Spotlight Your Server

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge — proof is checked automatically, then reviewed by our team.

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 📂 Browser Automation →Best MCP servers for Browser Automation →Best Playwright MCP servers →Alternatives to Browsegrab →Install in Claude Desktop Install in Cursor Install in VS Code Setup guides for all 13 MCP clients

Browsegrab

Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

Not yet automatically verified

We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag — we're steadily working through the catalog.

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "browsegrab": {
      "command": "uvx",
      "args": [
        "browsegrab"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Documentation Overview

browsegrab

한국어 문서 · llms.txt

Token-efficient browser agent for local LLMs — Playwright + accessibility tree + MarkGrab, MCP native.

Features

Token-efficient: ~500-1,500 tokens/step (vs 4,000-10,000 for browser-use)
Local LLM first: Optimized for vLLM, Ollama, and OpenAI-compatible endpoints
MCP native: Built-in MCP server with 8 browser automation tools
MarkGrab integration: HTML → clean markdown for content extraction
Accessibility tree + ref system: Stable element references (e1, e2, ...) without vision models
Success pattern caching: Zero LLM calls on repeated workflows
5-stage JSON parser: Robust action parsing for local LLM outputs
Minimal dependencies: Only playwright + httpx in core

Installation

Terminal

pip install browsegrab
playwright install chromium

With optional features:

Terminal

pip install browsegrab[mcp]      # MCP server support
pip install browsegrab[content]  # MarkGrab content extraction
pip install browsegrab[cli]      # CLI with rich output
pip install browsegrab[all]      # Everything

Quick Start

Python API

server.ts

from browsegrab import BrowseSession

async with BrowseSession() as session:
    # Navigate and get accessibility tree snapshot
    await session.navigate("https://example.com")
    snap = await session.snapshot()
    print(snap.tree_text)
    # - heading "Example Domain" [level=1]
    # - link "Learn more": [ref=e1]

    # Click using ref ID
    result = await session.click("e1")
    print(result.url)  # https://www.iana.org/help/example-domains

    # Type into search box
    await session.navigate("https://en.wikipedia.org")
    snap = await session.snapshot()
    await session.type("e4", "Python programming", submit=True)

    # Extract compressed content (AX tree + markdown)
    content = await session.extract_content()

CLI

bash

# Accessibility tree snapshot
browsegrab snapshot https://example.com

# JSON output
browsegrab snapshot https://example.com -f json

# Extract content (AX tree + markdown)
browsegrab extract https://en.wikipedia.org/wiki/Python

# Agentic browse (requires LLM endpoint)
browsegrab browse https://example.com "Find the about page"

MCP Server

bash

browsegrab-mcp  # Start MCP server (stdio)

Claude Desktop / Cursor / VS Code config:

config.json

{
  "mcpServers": {
    "browsegrab": {
      "command": "browsegrab-mcp"
    }
  }
}

8 MCP tools: browser_navigate, browser_click, browser_type, browser_snapshot, browser_scroll, browser_extract_content, browser_go_back, browser_wait

How It Works

Agent Browse Loop

mermaid

flowchart LR
    A["🌐 URL + Goal"] --> B["Navigate"]
    B --> C["AX Tree Snapshot\n~200–500 tokens"]
    C --> D{"LLM\nDecision"}
    D -->|"click / type / scroll"| E["Execute Action"]
    E --> C
    D -->|"goal reached"| F["Extract Content\n(MarkGrab)"]
    F --> G["✅ Result"]

Token Efficiency

browsegrab separates structure (accessibility tree) from content (MarkGrab markdown), sending only what the LLM needs:

mermaid

flowchart TD
    A["Raw HTML"] --> B["Accessibility Tree"]
    A --> C["MarkGrab Markdown"]
    B --> D["Structure: ~200–500 tokens\nInteractive elements with ref IDs"]
    C --> E["Content: ~300–800 tokens\nClean markdown · on-demand"]
    D --> F["Combined: ~500–1,300 tokens/step\n⚡ 5–8× fewer than browser-use"]
    E --> F

Token efficiency (measured)

Page	Interactive elements	Tokens	browser-use equivalent
example.com	1	~60	~500+
Wikipedia article	452	~1,254	~10,000+

Architecture

server.ts

browsegrab/
├── config.py                 # Dataclass configs (env var loading)
├── result.py                 # Result types (ActionResult, BrowseResult, ...)
├── session.py                # BrowseSession orchestrator
├── browser/
│   ├── manager.py            # Playwright lifecycle (async context manager)
│   ├── snapshot.py           # Accessibility tree + ref system
│   ├── selectors.py          # 4-strategy selector resolver
│   └── actions.py            # navigate, click, type, scroll, go_back, wait
├── dom/
│   ├── ref_map.py            # ref ID ↔ element bidirectional mapping
│   └── compress.py           # AX tree + MarkGrab → compressed context
├── llm/
│   ├── base.py               # LLMProvider ABC
│   ├── provider.py           # vLLM, Ollama, OpenAI-compatible
│   ├── prompt.py             # System prompts (~400 tokens)
│   └── parse.py              # 5-stage JSON fallback parser
├── agent/
│   ├── history.py            # Sliding window history compression
│   ├── cache.py              # Domain-based success pattern cache
│   └── loop_guard.py         # Duplicate action detection
├── __main__.py               # CLI (click)
└── mcp_server.py             # FastMCP server (8 tools)

Configuration

All settings via environment variables (BROWSEGRAB_* prefix):

bash

# Browser
BROWSEGRAB_BROWSER_HEADLESS=true
BROWSEGRAB_BROWSER_TIMEOUT_MS=30000

# LLM (for agentic browse)
BROWSEGRAB_LLM_PROVIDER=vllm          # vllm | ollama | openai
BROWSEGRAB_LLM_BASE_URL=http://localhost:8000/v1
BROWSEGRAB_LLM_MODEL=Qwen/Qwen3.5-32B-AWQ

# Agent
BROWSEGRAB_AGENT_MAX_STEPS=10
BROWSEGRAB_AGENT_ENABLE_CACHE=true

Part of the QuartzUnit Ecosystem

Library	Role
markgrab	Passive extraction (URL → markdown)
snapgrab	Passive capture (URL → screenshot)
docpick	Document OCR → structured JSON
browsegrab	Active automation (goal → browser actions → results)

Development

bash

git clone https://github.com/QuartzUnit/browsegrab.git
cd browsegrab
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
playwright install chromium

# Unit tests (no browser needed)
pytest tests/ -m "not e2e"

# Full suite including E2E
pytest tests/ -v

License

MIT

_{Part of the QuartzUnit ecosystem — composable Python libraries for data collection, extraction, search, and AI agent safety.}

Read the full README →View source on GitHub →

Related MCP Servers

View all in Browser Automation View all alternatives

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

Last commit

5mo ago

Most recent push to the default branch.

Directory activity

1 views

Config copies, upvotes, and views on AllMCPs.

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Browsegrab

Add the following block to your claude_desktop_config.json under mcpServers: "mcpServers": { "browsegrab": { "command": "uvx", "args": ["browsegrab"] } }

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/browsegrab?style=directory)](https://allmcps.com/mcp/browsegrab)

HTML Embed

<a href="https://allmcps.com/mcp/browsegrab"><img src="https://allmcps.com/api/badge/browsegrab?style=directory" alt="Browsegrab on AllMCPs" /></a>

Technical Specs & Signals

CategoryBrowser Automation

11/12 checks healthy over the last 45d

36Quality signal: Fair · 36/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools16/30

Adoption & activity1/15

Community engagement0/10

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 2d ago via OSV.dev · browsegrab (PyPI)

★ Spotlight Slot

Feature Your MCP Server

Get maximum visibility for your server across our directory, search results, and detail pages.

Spotlight Your Server

Own this project?

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.