FireKey MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@FireKey MCP Server Start the profile named 'QA' and give me the Puppeteer WebSocket URL"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
FireKey MCP Server
MCP server for FireKey browser profile management. Allows AI tools like Claude Desktop, Cursor, and Claude Code to manage browser profiles through natural language.
The server exposes 15 tools through stdio and connects to FireKey's authenticated localhost API. It manages browser profiles and returns automation connection information; it does not itself read web pages or click page elements. FireKey's desktop app also communicates with its backend, so a local MCP connection does not mean the product is fully offline.
Guides
Create, start and stop your first profile: a small, explicit lifecycle check before using real accounts.
Add extensions: Chrome Store URL or local package?: a desktop workflow with a four-page Chinese visual checklist, input requirements and a one-profile verification checklist. This is not an MCP extension-install tool.
Related MCP server: BrowserPilot
Prerequisites
FireKey desktop app running with Local API enabled (Settings → Local API & MCP)
Node.js 18+
Quick Start
npx firekey-mcp --api-key YOUR_API_KEYConfiguration
For a first integration test, follow Create and start your first FireKey profile. It includes an explicit target, pass/fail checks, and troubleshooting before connecting any real account.
Claude Desktop
Edit claude_desktop_config.json:
{
"mcpServers": {
"firekey": {
"command": "npx",
"args": ["-y", "firekey-mcp", "--api-key", "YOUR_API_KEY"]
}
}
}Claude Code
Add to .mcp.json:
{
"mcpServers": {
"firekey": {
"command": "npx",
"args": ["-y", "firekey-mcp", "--api-key", "YOUR_API_KEY"]
}
}
}Cursor
Add to MCP settings:
{
"mcpServers": {
"firekey": {
"command": "npx",
"args": ["-y", "firekey-mcp", "--api-key", "YOUR_API_KEY"]
}
}
}Options
Option | Env Variable | Description | Default |
|
| FireKey Local API port | Auto-detect |
|
| API key for authentication | — |
Port is auto-discovered from FireKey's data directory. Manual override only needed if running multiple instances.
To avoid putting the key in command-line arguments, you can use the supported FIREKEY_API_KEY environment variable in your MCP client's local configuration:
{
"mcpServers": {
"firekey": {
"command": "npx",
"args": ["-y", "firekey-mcp"],
"env": {
"FIREKEY_API_KEY": "YOUR_API_KEY"
}
}
}
}Keep configurations containing a real key private. Never commit them or include keys, cookies, proxy credentials, or live automation endpoints in public logs or screenshots. Tools such as profile deletion, cache clearing, and cookie reading should only be invoked for an explicitly authorized target.
Verified lifecycle
A programmatic MCP client test on September 9, 2026 successfully created a blank profile with no proxy, started it in headless mode, received Puppeteer/Selenium connection information, verified its running state, stopped it, and verified it was no longer running. The desktop UI also showed the demo profile as stopped. This test did not cover long-term session persistence or a Claude/Cursor conversation.
Available Tools
Browser Management
browser_start — Start a browser profile, returns WebSocket endpoints for Puppeteer/Selenium
browser_stop — Stop a running browser
browser_active — List currently running browsers
Profile Management
profile_list — List profiles with filtering and pagination
profile_create — Create a new profile with fingerprint/proxy settings
profile_update — Update profile settings
profile_delete — Delete profiles (soft delete)
profile_move — Move profiles to a group
profile_delete_cache — Clear profile cache (cookies, history, etc.)
profile_cookies — Get cookies from a profile
Group Management
group_list — List profile groups
group_create — Create a new group
group_update — Update a group
Proxy Management
proxy_list — List saved proxies
proxy_create — Create a new proxy
Example Usage
Once configured, you can use natural language in Claude:
"List all my browser profiles"
"Create a Windows profile with Chrome 143 and random fingerprint"
"Start the profile with this verified public ID and keep its automation endpoint private"
"Stop only the demo profile with this verified public ID"
"Create a group called 'QA' and move the profile named 'QA-Demo' into it, using its returned public ID"
Development
cd mcp-server
npm install
npm run build
node dist/index.js --api-key YOUR_KEYAvailable Tools
15 toolsbrowser_activeA
List currently running browser profiles with their WebSocket endpoints.
Inputs: profile_id.
browser_startC
Start a browser profile. Returns WebSocket endpoints for Puppeteer/Selenium automation.
Inputs: cdp_mask, headless, profile_id, profile_no, +4 more.
browser_stopB
Stop a running browser profile.
Inputs: profile_id, profile_no.
group_createB
Create a new profile group.
Inputs: group_name (required), remark.
group_listA
List profile groups with optional name search.
Inputs: page, page_size, group_name.
group_updateC
Update an existing group.
Inputs: group_id (required), remark, group_name.
profile_cookiesA
Get cookies from a browser profile (from running browser via CDP, or from local files).
Inputs: profile_id (required).
profile_createC
Create a new browser profile with fingerprint and proxy settings.
Inputs: group_id (required), os, ram, name, +26 more.
profile_deleteA
Delete browser profiles (soft delete to trash).
Inputs: profile_id (required).
profile_delete_cacheA
Delete cached data for browser profiles (cookies, history, localStorage, etc.).
Inputs: type (required), profile_id (required).
profile_listA
List browser profiles with pagination and filtering.
Inputs: page, limit, group_id, sort_type, +3 more.
profile_moveB
Move profiles to a different group.
Inputs: group_id (required), profile_id (required).
profile_updateC
Update an existing browser profile.
Inputs: profile_id (required), name, remark, user_proxy_config, +1 more.
proxy_createC
Create a new proxy configuration.
Inputs: host (required), port (required), type (required), user, +4 more.
proxy_listB
List saved proxy configurations.
Inputs: page, limit, proxy_id.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 15 tools
Each tool targets a distinct resource-action pair: groups, proxies, browser execution, and profile management are clearly separated. Even closely related tools like profile_delete and profile_delete_cache are unambiguous from their names.
Tool names consistently use a resource_action pattern in snake_case (group_create, proxy_list, browser_start, profile_update). Minor deviations like profile_cookies and browser_active are not actions, but they are still predictable and readable.
15 tools is within the well-scoped range and each tool addresses a concrete need for browser profile management, proxy management, group organization, and runtime browser control. There are no redundant or trivial tools.
Profile and browser management are well covered, but auxiliary resources have notable lifecycle gaps: proxies cannot be updated or deleted, and groups cannot be deleted. This leaves no way to remove stale proxy configurations or groups, which agents may need to do.
Maintenance
Related MCP Connectors
Cloud browsers for AI agents: saved logins, residential IPs, live human takeover, 57 browser tools.
30+ web-access and AI APIs behind one key: search, scraping, browsers, voice, OCR and LLMs.
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
The most secure anti-detect browser, for people and AI agents. Agents create, start and drive isolated, fingerprint-protected Browz browser profiles: open pages, click, type, fill forms, read pages and take screenshots, each profile with its own fingerprint and proxy.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with the TgeBrowser Local API to create, manage, and automate isolated browser environments. It supports comprehensive browser automation tasks including navigation, element interaction, and fingerprint configuration through natural language.7 npmMIT
- AlicenseBqualityDmaintenanceEnables AI to control browsers via natural language for web automation, testing, and data scraping. Supports Chrome-based browsers and integrates with any MCP-compatible AI tool.173MIT
- AlicenseCqualityDmaintenanceEnables AI-powered browser automation with real profiles, supporting interaction, navigation, form filling, and advanced features like visual overlays and self-healing selectors.42Apache 2.0
- AlicenseBqualityDmaintenanceControls Octo Browser antidetect profiles and automates browser tasks through natural language, enabling profile lifecycle management, web scraping, and full browser automation via CDP.37MIT