Get Gather
A containerized service that enables MCP clients to interact with data and perform actions through a remote browser environment. It supports live streaming of the container desktop and offers proxy configuration for location-based browser sessions.
README
Get Gather
GetGather is a containerized service that allows MCP clients to interact with your data and act on your behalf.
Quickstart
0. Prerequisite
Install Docker.
1. Start the container
1.A: Use docker-compose
Download the docker-compose.yml file and run
docker-compose up
1.B: Use docker run directly
Run the container with Docker or Podman:
docker run -v /etc/localtime:/etc/localtime:ro -p 23456:23456 ghcr.io/mcp-getgather/mcp-getgather
On MacOS -v /etc/localtime:/etc/localtime:ro is needed for the service to use your local timezone,
and on Linux it's -v /etc/timezone:/etc/timezone:ro instead.
On windows, the timezone has to be set directly as -e TZ=America/Los_Angeles.
Optionally, with --env-file if you have an env file.
docker run --env-file ~/getgather.env -p 23456:23456 ghcr.io/mcp-getgather/mcp-getgather
2. Connect to MCP clients
For VS Code, Cursor, and other MCP clients which support remote MCP servers:
{
"mcpServers": {
"getgather": {
"url": "http://127.0.0.1:23456/mcp"
}
}
}
For Claude Desktop:
{
"mcpServers": {
"getgather": {
"command": "npx",
"args": ["mcp-remote", "http://127.0.0.1:23456/mcp", "--allow-http"]
}
}
}
For Codex CLI, use a ~/.codex/config.toml file:
[mcp_servers.getgather]
command = "npx"
args = ["mcp-remote", "http://127.0.0.1:23456/mcp", "--allow-http"]
(Optional) Enable url opener tool
Choose one of the following options if you'd like the MCP clients to automatically open the authentication link in a browser.
- Add playwright-mcp server.
- In Claude Desktop, enable "Control Chrome" in "Settings" -> "Extensions".
3. Read more
To live stream the container desktop, go to http://localhost:23456/live.
Development documentation is located in the docs directory:
Access AI-enhanced documentation for this repository at deepwiki.com/mcp-getgather/mcp-getgather.
Build and run locally
After cloning the repo:
docker build -t mcp-getgather .
docker run -p 23456:23456 mcp-getgather
Proxy Configuration
Get Gather supports using an external proxy service for browser sessions. To enable proxy support, set the following environment variables:
BROWSER_HTTP_PROXY=http://your-proxy-server:port
BROWSER_HTTP_PROXY_PASSWORD=your-proxy-password
The proxy service should use hierarchical location-based routing if location information is provided. The username format sent to the proxy server will be:
- Basic:
profile_id - With location:
profile_id-city_X_state_Y_country_Z
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.