GoLogin logo

GoLogin

Community
gologinapp

MCP server for managing Gologin browser profiles, proxies, fingerprints and cloud browser sessions through AI conversations

Publishergologinapp
Repositorygologin-mcp
LanguageTypeScript
Forks
9
Stars
22
Available tools
58
Transport typestdio
Categories
LicenseMIT
Links
  • Connect tools to AI workflows

    GoLogin exposes MCP capabilities that can be used by compatible AI clients and agents.

  • 58 available tools

    Browse the callable actions below, including names and descriptions when provided by the server.

  • Ready-to-copy setup

    Use the installation snippets to configure this server in your preferred MCP client.

  • Open source signals

    22 stars and 9 forks from the linked repository.

GoLogin MCP Server for AI Agents

npm version License: MIT

Manage GoLogin browser profiles, proxies, fingerprints, folders, and cloud browser sessions through AI conversations. This Model Context Protocol (MCP) server connects your AI client to the GoLogin API.

Quickstart

You need Node.js 22 or newer, an active GoLogin account, and a GoLogin API token. Node.js 22 and 24 LTS have been tested on macOS Apple Silicon.

  1. Sign in to your GoLogin account, open API & MCP, and generate a token in the API tab.
  2. Add this configuration to your MCP client, replacing the token placeholder. Merge it into any existing mcpServers configuration.
json
{
  "mcpServers": {
    "gologin-mcp": {
      "command": "npx",
      "args": ["-y", "gologin-mcp"],
      "env": {
        "API_TOKEN": "your-gologin-api-token-here"
      }
    }
  }
}
  1. Restart or reload your client's MCP connection, then ask: "Show me my GoLogin profiles."

The client starts the server automatically. -y lets npm install the package without an interactive confirmation. This server reads API_TOKEN; the GOLOGIN_TOKEN variable used by other GoLogin CLIs is not an alias here.

For a terminal startup check, with API_TOKEN already set in your environment:

bash
npx -y gologin-mcp

The server communicates over standard input/output (stdio) and waits for an MCP client. It does not open a browser or provide an interactive command prompt by itself.

What You Can Do

  • Create, read, update, delete, and organize browser profiles.
  • Configure profile proxies and refresh browser fingerprints.
  • Manage folders and their profile membership.
  • Read account information.
  • Start and stop browser profiles in the GoLogin cloud.

Cloud startup returns a connection URL. This server does not expose page navigation, click, form-filling, or local Orbita launch tools. For page automation, use a separate browser automation client or the GoLogin Agent Browser CLI.

The MCP process runs locally; GoLogin API requests and cloud browser sessions require network access. Cloud availability and API operations depend on your account permissions and plan.

Tools

Tool names are generated from the HTTP method and path in the GoLogin OpenAPI specification, which the server loads at startup. The following is a selection of available tools, not a fixed list of aliases. Query tools/list in your MCP client for the current names and input schemas.

ToolDescription
get_profile_v2List and search profiles, with pagination and folder filters
post_profile_customCreate a profile with partial settings such as name, OS, and proxy
get_profile_idRead a profile by ID
put_profile_id_customUpdate selected profile settings
delete_profileDelete the profiles listed in profilesToDelete
patch_profile_proxy_many_v2Configure proxies for one or more profiles
patch_profile_fingerprintsRefresh fingerprints for the profiles listed in browsersIds
get_proxy_v2List proxies
get_foldersList folders
post_folders_folderCreate a folder by name
patch_folders_folderAdd or remove profiles from a folder
delete_folders_folderDelete a folder by name
post_profile_id_webStart a profile in the cloud and return a connection URL
delete_profile_id_webStop a cloud profile
get_userRead account information

For example, an MCP client can send this tools/call request to read a profile:

json
{
  "name": "get_profile_id",
  "arguments": {
    "id": "your-profile-id"
  }
}

Arguments follow each tool's input schema. Path and query parameters, and request body fields, are passed as top-level arguments.

Example Prompts

  • "Show me my GoLogin profiles."
  • "Create a Linux profile named 'Research'."
  • "Rename profile PROFILE_ID to 'Research US'."
  • "Update profile PROFILE_ID to use these proxy settings."
  • "Refresh the fingerprint for profile PROFILE_ID."
  • "Create a folder named 'Research' and add profile PROFILE_ID to it."
  • "Start profile PROFILE_ID in the cloud and give me the connection URL."
  • "Stop the cloud session for profile PROFILE_ID."
  • "Show my GoLogin account information."

Setup for MCP Clients

Claude Desktop

Open Settings > Developer > Edit Config and add the Quickstart configuration to claude_desktop_config.json. Fully quit and restart Claude Desktop, then check that gologin-mcp and its tools are available.

See the official local MCP setup guide for configuration paths and troubleshooting.

Cursor

Add the Quickstart configuration to ~/.cursor/mcp.json for your user account, or .cursor/mcp.json for a project. Reload the MCP connection and enable the server's tools. Keep configurations containing API tokens out of version control.

See Cursor's MCP documentation for current client settings.

Other MCP Clients

Use a client that supports local stdio MCP servers. Configure npx as the command, -y and gologin-mcp as its arguments, and API_TOKEN in the server environment. The configuration format and location depend on the client.

Troubleshooting

  • Server does not connect: check that Node.js and npx are available to the client, then restart its MCP connection. The server also needs access to docs-download.gologin.com to load its tool definitions.
  • API returns 401 Unauthorized: check the API_TOKEN passed to the server and the token's validity in GoLogin. Restart the connection after changing it.
  • Tool name not found: refresh the tool list and use the names returned by tools/list; names such as list_profiles and start_browser are not built-in aliases.
  • Cloud startup fails: check the API response and your account's cloud access. Local MCP startup does not itself start Orbita on your computer.

Development

bash
git clone https://github.com/gologinapp/gologin-mcp.git
cd gologin-mcp
npm ci
npm run build

To run your local build with API_TOKEN already configured:

bash
node dist/index.js

Before publishing, run:

bash
npm run release:check

The package includes only the built server, package metadata, README, and license. The release check verifies this allowlist so local state, databases, credentials, and development files cannot be included as extra files. npm publish runs the same check automatically.

MCP Registry Releases

server.json describes this server for the official MCP Registry under io.github.gologinapp/gologin-mcp. The npm package declares the same identifier in mcpName.

Keep the versions in package.json, package-lock.json, and server.json aligned. Publish the checked npm package first, then run Publish to MCP Registry from the repository's Actions tab on main. The workflow verifies that the npm release contains the correct Registry identifier and authenticates using GitHub OIDC, without a separate Registry token. It does not publish to npm.

Links

License

MIT, copyright GoLogin.

Installation

TypingMind
Prerequisites:

Node.js 18+

{
  "mcpServers": {
    "gologin-mcp": {
      "command": "npx",
      "args": [
        "gologin-mcp"
      ],
      "env": {
        "API_TOKEN": "your-gologin-api-token-here"
      }
    }
  }
}

Available Tools

  • batch_operations

    Execute multiple API operations in batch. Supports creating multiple profiles, updating multiple proxies, etc.

  • get_all_profiles

    Get all profiles

  • get_a_random_fingerprint

    Get a random fingerprint

  • update_proxy_for_multiple_profiles

    Update proxy for multiple profiles

  • update_chrome_extensions_for_multiple_profiles

    Update chrome extensions for multiple profiles

  • update_bookmarks_for_multiple_profiles

    Update bookmarks for multiple profiles

  • get_profile_by_id

    Get profile by id

  • update_profile

    Update profile

  • update_user_agent_of_profile

    Update user agent of profile

  • find_cookies_of_profile

    Find cookies of profile

  • update_cookies_for_profile

    Update cookies for profile

  • delete_multiple_profiles

    Delete multiple profiles

  • create_profile_with_templates

    Create profile with templates

  • update_profile_with_partial_parameters

    Update profile with partial parameters

  • refresh_profile_fingerprint

    Refresh profile fingerprint

  • update_multiple_profiles_names

    Update multiple profiles names

  • clone_multiple_profiles

    Clone multiple profiles

  • run_profile_in_the_cloud

    Run profile in the cloud

  • stop_profile_in_the_cloud

    Stop profile in the cloud

  • export_profiles

    Export profiles

  • import_profiles

    Import profiles

  • get_latest_useragent

    Get latest useragent

  • add_member_to_workspace

    Add member to workspace

  • update_member_permissions

    Update member permissions

  • remove_member_from_workspace

    Remove member from workspace

  • create_multiple_shares

    Create multiple shares

  • delete_folder_share

    Delete folder share

  • find_proxy_by_id

    Find proxy by id

  • update_proxy

    Update proxy

  • delete_proxy

    Delete proxy

  • get_list_of_all_proxies

    Get list of all proxies

  • get_list_of_shared_proxies

    Get list of shared proxies

  • create_multiple_proxies

    Create multiple proxies

  • delete_multiple_proxies

    Delete multiple proxies

  • create_gologin_high_quality_proxy

    Create gologin high quality proxy

  • get_used_traffic_data_of_gologin_proxies

    Get used traffic data of gologin proxies

  • get_user_info

    Get user info

  • create_dev_token

    Create dev token

  • get_all_tags

    Get all tags

  • search_for_particular_tags

    Search for particular tags

  • add_tag_to_profiles

    Add tag to profiles

  • update_tag

    Update tag

  • remove_tag_from_profiles

    Remove tag from profiles

  • delete_tag

    Delete tag

  • get_all_workspaces

    Get all workspaces

  • create_workspace

    Create workspace

  • get_workspace_info

    Get workspace info

  • delete_workspace

    Delete workspace

  • rename_workspace

    Rename workspace

  • get_profiles_count

    Get profiles count

  • get_all_profiles_in_workspace

    Get all profiles in workspace

  • delete_multiple_profiles_in_workspace

    Delete multiple profiles in workspace

  • transfer_profile

    Transfer profile

  • get_list_of_deleted_profiles

    Get list of deleted profiles

  • restore_deleted_profiles

    Restore deleted profiles

  • get_all_folders

    Get all folders

  • create_folder

    Create folder

  • add_or_remove_profiles_from_folder

    Add or remove profiles from folder

Use GoLogin MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once GoLogin is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.

Setup guide to use the local connector

Use this when the MCP server needs access to local files, apps, or private resources on your computer.

1

Open the MCP settings

In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.

  1. Open TypingMind in your browser.
  2. Click the Settings icon.
  3. Go to Advanced Settings.
  4. Open the Model Context Protocol section.
  5. Click Setup Connector and choose This Device.
TypingMind MCP connector setup screen with This Device selected
2

Run the connector command

Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.

  1. Copy the setup command shown by TypingMind.
  2. Open Terminal on macOS or Windows Terminal on Windows.
  3. Paste and run the command.
  4. Approve the package install if Terminal asks you to proceed.
  5. Keep the Terminal window running while using MCP tools.
3

Add GoLogin as a server

When the connector status is Ready, click Edit Servers and paste the MCP server configuration.

  1. Wait until the connector status shows Ready.
  2. Click Edit Servers.
  3. Paste the GoLogin MCP server configuration.
  4. Save the server list.
  5. Refresh if you want to confirm the connector is still ready.
TypingMind MCP settings showing active server and Edit Servers button
{
  "mcpServers": {
    "gologin": {
      "command": "npx",
      "args": [
        "-y",
        "gologin-mcp"
      ]
    }
  }
}
4

Use it across models

Save the server list, open Plugins, enable the GoLogin MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.

  1. Open the Plugins page in TypingMind.
  2. Enable the GoLogin MCP tools.
  3. Start a chat and choose the AI model you want to use.
  4. Use the MCP tools in chat or assign them to an AI agent.
  5. Switch to another AI model whenever needed without reconnecting MCP.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use GoLogin to help me with this task?
GoLogin
Sure. I read it.
Here is what I found using GoLogin.

Frequently asked questions

What is the GoLogin MCP server used for?

GoLogin is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use GoLogin MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use GoLogin with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use GoLogin MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With GoLogin connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect GoLogin MCP to TypingMind?

GoLogin runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.

What tools does GoLogin MCP provide in TypingMind?

GoLogin exposes 58 MCP tools that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use GoLogin MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If GoLogin requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇