
Babelwrap MCP
- Updated April 7, 2026
- babelwrap/babelwrap-mcp
BabelWrap MCP is a MCP server that connects AI agents to BabelWrap-powered web browsing over stdio.
About
BabelWrap MCP is a stdio Model Context Protocol server that exposes BabelWrap’s browsing capabilities to Claude Code, Cursor, and other MCP hosts. developers who ship agent-assisted products use it when tasks depend on rendered pages, logins, or multi-step navigation that raw HTTP clients cannot handle reliably. Registration is npm-driven with a single secret, BABELWRAP_API_KEY, which keeps setup short for indies who already juggle API keys for LLM providers. The server is early-stage (0.1.0) but clearly scoped: one integration surface between your agent and BabelWrap rather than a full testing framework. Pair it with validation or launch research when you need the agent to verify competitor flows or documentation sites, but install it during build when you are hardening agent tooling. Treat it as a live-browser bridge, not a replacement for your own backend or for offline unit tests.
- stdio MCP server (npm package babelwrap-mcp, v0.1.0)
- Requires BABELWRAP_API_KEY from babelwrap.com
- Positions BabelWrap as agent-grade web browsing beyond static fetch
- GitHub source: babelwrap/babelwrap-mcp
Babelwrap MCP by the numbers
- Data as of Aug 10, 2026 (Skillselion catalog sync)
claude mcp add --env BABELWRAP_API_KEY=YOUR_BABELWRAP_API_KEY babelwrap-mcp -- npx -y babelwrap-mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | babelwrap-mcp |
|---|---|
| Transport | STDIO |
| Auth | Required |
| Last updated | April 7, 2026 |
| Repository | babelwrap/babelwrap-mcp ↗ |
What it does
Wire your coding agent to real browser sessions through BabelWrap when you need live pages, forms, or authenticated sites without hand-rolling Playwright glue.
Who is it for?
Best when you're adding trustworthy browser automation to an agent workflow during integration work.
Skip if: Skip if you only need read-only static page text or want a self-hosted browser farm with no BabelWrap account.
What you get
After you register the server with BABELWRAP_API_KEY, your agent can drive BabelWrap browsing workflows from the same MCP session as your code edits.
- Registered stdio MCP server in your agent config
- Agent-callable BabelWrap browsing tools behind your API key
- Repeatable browser tasks without copying automation scripts into the repo
By the numbers
- Server schema version 2025-12-11
- Package version 0.1.0
- Transport: stdio
README.md
BabelWrap MCP Server
An MCP server that gives AI agents web browsing superpowers via the BabelWrap API.
Works with Claude Desktop, Cursor, Claude Code, and any MCP-compatible client.
Installation
# Using uvx (recommended -- no install required)
uvx babelwrap-mcp
# Using pip
pip install babelwrap-mcp
# Using pipx (isolated environment)
pipx install babelwrap-mcp
Setup
1. Get an API Key
Sign up at babelwrap.com and create an API key from your dashboard.
2. Configure Your MCP Client
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"babelwrap": {
"command": "uvx",
"args": ["babelwrap-mcp"],
"env": {
"BABELWRAP_API_KEY": "bw_your_api_key_here"
}
}
}
}
If you installed with pip or pipx, use the binary directly:
{
"mcpServers": {
"babelwrap": {
"command": "babelwrap-mcp",
"args": [],
"env": {
"BABELWRAP_API_KEY": "bw_your_api_key_here"
}
}
}
}
Claude Code
claude mcp add babelwrap -- uvx babelwrap-mcp
Then set your API key as an environment variable:
export BABELWRAP_API_KEY="bw_your_api_key_here"
Available Tools
| Tool | Description |
|---|---|
babelwrap_new_session |
Create a new browser session |
babelwrap_close_session |
Close a browser session |
babelwrap_navigate |
Navigate to a URL |
babelwrap_snapshot |
Get current page state |
babelwrap_click |
Click an element |
babelwrap_fill |
Fill a form field |
babelwrap_submit |
Submit a form |
babelwrap_extract |
Extract structured data |
babelwrap_screenshot |
Take a screenshot |
babelwrap_press |
Press a keyboard key |
babelwrap_scroll |
Scroll the page |
babelwrap_hover |
Hover over an element |
babelwrap_upload |
Upload a file |
babelwrap_back / babelwrap_forward |
Browser history |
babelwrap_wait_for |
Wait for a condition |
babelwrap_list_pages / babelwrap_switch_page |
Multi-tab support |
Environment Variables
| Variable | Required | Description |
|---|---|---|
BABELWRAP_API_KEY |
Yes | Your BabelWrap API key |
BABELWRAP_API_URL |
No | API base URL (default: https://api.babelwrap.com/v1) |
Documentation
Full documentation at babelwrap.com/docs/mcp
License
MIT
Recommended MCP Servers
How it compares
MCP integration to a hosted browsing API, not an in-repo Playwright skill or local headless script pack.
FAQ
Who is BabelWrap MCP for?
and small-team developers using Claude Code or Cursor who need agents to interact with real websites via BabelWrap.
When should I use BabelWrap MCP?
Use it during build integrations when tasks require logged-in flows, SPAs, or multi-page navigation your agent cannot complete with HTTP alone.
How do I add BabelWrap MCP to my agent?
Install the npm package babelwrap-mcp, set BABELWRAP_API_KEY in your MCP host config, and register the stdio server entry from the official repository.