Malt MCP Server
Lets you read your freelance profile, view statistics, and manage mission conversations on Malt.fr.
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., "@Malt MCP Server show my latest mission conversations"
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.
Malt MCP Server
MCP server for Malt.fr. Lets Claude (or any MCP client) read your freelance profile, stats, and missions.
Tools
Tool | Description | Status |
| Log in to Malt interactively from Claude Desktop | working |
| Get freelance profile info (bio, daily rate, skills, rating). Omit username to fetch your own profile. | working |
| View profile stats (views, response rate, missions) | working |
| List mission conversations from messaging | working |
| Get full details of a specific mission (budget, skills, messages) | working |
| Close the browser and free resources | working |
Related MCP server: LinkedIn MCP Server
📦 Claude Desktop MCP Bundle
Prerequisites: Claude Desktop.
One-click installation:
Download the latest
.mcpbfrom releasesDouble-click the
.mcpbfile to install it into Claude DesktopAsk Claude "connecte-moi a Malt" - a browser opens, you log in, done
Call any Malt tool
No terminal needed. Session is saved in ~/.malt-mcp/ and reused across restarts.
Google OAuth doesn't work (blocked by Google when automated). Use email/password.
🚀 uvx Setup (Universal)
Prerequisites: uv installed.
Add to your MCP client config (Claude Desktop, Claude Code, or any MCP-compatible client):
{
"mcpServers": {
"malt": {
"command": "uvx",
"args": ["malt-mcp@latest"],
"env": { "UV_HTTP_TIMEOUT": "300" }
}
}
}@latest pulls the newest version from PyPI on each launch. First auth-requiring call opens a browser for login.
To log in ahead of time:
uvx malt-mcp@latest --loginDocker (coming soon)
⚙️ CLI Options
Option | Description |
| Open browser to log in and save session |
| Clear stored browser profile |
| Show browser window (debug) |
| Set log level (DEBUG, INFO, WARNING, ERROR) |
| Browser timeout in ms (default: 5000) |
❗ Troubleshooting
Login issues:
Google OAuth won't work. Use email/password.
Session expired? Re-run
uvx malt-mcp@latest --login.Cloudflare challenge on first load is normal - the browser handles it, give it a few seconds.
Timeout issues:
Pages not loading? Try
--timeout 10000. Slow connections might need15000.
Browser issues:
Headless mode doesn't work - Cloudflare blocks it. The browser window is expected.
First run downloads Chromium (~200 MB via Patchright). One-time thing.
Upgrading from v0.3.x? Run
uvx malt-mcp@latest --logoutthen--login. The browser engine changed from system Chrome to managed Chromium.
🔒 How it works
Under the hood, this is browser automation via Patchright (Playwright fork). No API, no reverse-engineering - it drives a real browser like you would.
Credentials stay local. Cookies live in
~/.malt-mcp/profile/, nowhere else.Read-only. Nothing is modified on your Malt account (for now).
Runs locally. The server talks to Malt.fr and nothing else.
Malt's TOS may prohibit automated tools. Don't bulk-scrape. Use responsibly.
🐍 Development
Contributions welcome! See CONTRIBUTING.md for architecture guidelines.
git clone https://github.com/LeoMbm/malt-mcp.git
cd malt-mcp
uv sync --group dev
pre-commit installRun the MCP Inspector (local testing):
uv run mcp dev malt_mcp_server/server.pyRun tests:
uv run pytest --cov -vType check:
uv run ty checkLicense
Available Tools
6 toolsauthenticateA
Log in to Malt interactively.
Opens a browser window to the Malt login page. The user must log in manually (email/password only -Google OAuth won't work). Waits up to 5 minutes, then the session is saved for future calls.
Inputs: no named parameters. Returns: object
close_sessionADestructive
Close the browser and free resources.
Call this when you're done with Malt tools. The next tool call will reopen the browser automatically if needed.
Inputs: no named parameters. Returns: object
get_mission_detailsARead-only
Get details of a specific mission conversation.
Click on a conversation matching the given name and extract the project offer details: title, description, preferences, skills, and message history.
Inputs: name (required). Returns: object
get_missionsARead-only
Get your Malt inbox: conversations and project offers.
Returns a list of conversations and project offers sorted by date, with client name, company, last message, and status.
Inputs: no named parameters. Returns: result
get_profileBRead-only
Get a Malt freelance profile.
Inputs: username. Returns: object
get_statisticsARead-only
Get your Malt freelance statistics.
Returns Super Malter points, visibility stats (favorites, search appearances, profile views), project reviews/rating, and keyword rankings.
Inputs: no named parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
All six tools have clearly distinct purposes: authentication, session management, mission listing, mission details, profile retrieval, and statistics. No overlap or confusion.
Tool names follow a consistent pattern using lowercase and underscores. Verbs like 'authenticate' and 'close' are appropriately paired with nouns where needed (e.g., get_mission_details, get_missions).
With six tools, the set is well-scoped for a freelance platform. Each tool serves a necessary function without redundancy or bloat.
The tools cover the core user journey: login, browsing missions, viewing details, checking profile and stats. The set is complete for its intended read-oriented scope.
Maintenance
Related MCP Connectors
I do everything related to Browser Automation & Management
Read, crawl and act on websites, signed in as the user, and turn any site into an API.
Automate any website: discover, run and create browser scripts that work behind logins.
Stealth scraping & search. Bypasses Cloudflare, DataDome & LinkedIn via Cyborg HITL approach.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables extraction of comprehensive LinkedIn profile data including experience, education, skills, and contact information through browser automation. Requires manual LinkedIn credentials input and uses anti-detection measures for reliable scraping.5-
- AlicenseAqualityBmaintenanceEnables AI assistants to interact with LinkedIn by scraping profiles, companies, job postings, and getting personalized job recommendations using authenticated browser automation.175,729 PyPI4,213Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables browsing, retrieving, and downloading meeting recordings and transcripts from Grain via browser automation, bypassing the need for enterprise API access.2Apache 2.0
- AlicenseAqualityDmaintenanceAutomates LinkedIn profile management, SEO optimization, job search, and content publishing via Playwright.10156 npmMIT