proton-bridge-mcp
MCP server for reading and searching Proton Mail via Proton Mail Bridge, providing tools to list mailboxes, list/search messages, and get message details with TLS certificate pinning.
README
proton-bridge-mcp (Python wrapper)
A pip/uvx-installable wrapper around proton-bridge-mcp, an MCP server for reading and searching Proton Mail via Proton Mail Bridge.
This package contains no Python implementation. It's a thin shim that execs into the real Node.js implementation via npx. It exists so Python-oriented MCP tooling (uvx, pipx, pip install) can install and run it without needing to know it's Node underneath.
Unofficial, community project. Not affiliated with or endorsed by Proton AG.
Requirements
- Node.js 18+ must be installed and on
PATH(specificallynpx). This wrapper cannot function without it — there is no pure-Python fallback. - A Proton Mail plan that supports Bridge, with Proton Mail Bridge running
Install
pip install proton-bridge-mcp
# or
uvx proton-bridge-mcp
Setup
Run the interactive setup wizard once (fetches and pins Bridge's TLS certificate, verifies login, writes credentials to ~/.config/proton-bridge-mcp/, chmod 600):
proton-bridge-mcp-setup
Register with an MCP client
Claude Code:
claude mcp add proton-mail -s user -- proton-bridge-mcp
Claude Desktop / other MCP clients:
{
"mcpServers": {
"proton-mail": {
"command": "proton-bridge-mcp"
}
}
}
Why does this exist separately from the npm package?
The actual server (list_mailboxes, list_messages, search_messages, get_message tools; TLS certificate pinning instead of disabled verification; the setup wizard) lives entirely in the Node.js project: https://github.com/alpharomercoma/proton-bridge-mcp. That's the canonical implementation, source of truth for behavior, and where issues/PRs about actual functionality belong. This repo only exists to make it reachable from pip/uvx workflows.
License
MIT — see LICENSE.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.