@squidlerio/mcp
An MCP proxy that connects AI clients to the remote Squidler MCP server while providing local Chrome session management for testing localhost URLs. It enables transparent tool forwarding and allows browser-based test cases to run through a local browser instead of cloud instances.
README
@squidlerio/mcp
MCP proxy that sits between an AI client (Claude, Cursor, etc.) and the remote Squidler MCP server. It forwards all tools, resources, and prompts transparently, while adding local Chrome session management for testing localhost URLs.
How it works
AI Client (stdio) ←→ MCP Proxy ←→ Remote Squidler MCP (HTTP)
↕
Local Chrome ←→ CDP Proxy (WebSocket)
The proxy intercepts test_case_run calls — when local Chrome mode is enabled, it automatically creates a CDP session and routes the test through your local browser instead of the cloud worker's Chrome.
Install
npm install -g @squidlerio/mcp
Configuration
| Variable | Required | Default | Description |
|---|---|---|---|
SQUIDLER_API_KEY |
Yes | — | API key for the remote Squidler MCP server |
SQUIDLER_API_URL |
No | https://mcp.squidler.io |
Remote MCP server URL |
The CDP proxy URL is derived automatically from the API URL.
Usage
As an MCP server (stdio)
Add to your MCP client configuration:
{
"mcpServers": {
"squidler": {
"command": "npx",
"args": ["-y", "@squidlerio/mcp"],
"env": {
"SQUIDLER_API_KEY": "your-api-key"
}
}
}
}
CLI
# Download Chrome headless shell for local testing
squidler-mcp download-chrome
# Start MCP proxy via CLI
squidler-mcp mcp-proxy
Local session tools
These tools are added by the proxy (not available on the remote server):
local_session_start— Enable local Chrome mode. Acceptsheadless(boolean, default: true). Chrome is launched on the firsttest_case_run.local_session_stop— Disable local Chrome mode and stop any active session.local_session_status— Check if local Chrome mode is enabled and if a session is active.
When local Chrome mode is enabled, test_case_run automatically creates/recycles a CDP session and routes through your local Chrome. Back-to-back tests get a fresh Chrome instance each time.
Development
bun install
bun run start # Run CLI
bun run mcp-proxy # Run MCP proxy
bun run build # Build for npm publishing
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.