Messaging and email · MCP server
Proton Safe MCP: MCP server, setup and security
Proton Safe MCP is an open-source MCP server that lets an AI agent search and read Proton Mail emails and prepare message drafts. Its repository has 6 stars and its last commit is from October 24, 2026 and it is licensed under MIT.
| Adoption (stars) | 8/40 | |
|---|---|---|
| Maintenance | 30/30 | |
| Framework (licence, registry, official) | 20/30 |
What Proton Safe MCP does
According to its repository: “Proton Mail access through the local Proton Mail Bridge: search and read emails, inspect attachments, and create drafts. No send, delete or move tools.”
An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Proton Safe MCP is listed under Messaging and email, a category of 107 servers in the directory, where it ranks #91 by stars.
Topics declared by the repository: email, fastmcp, human-in-the-loop, imap, linux, privacy.
Installing and connecting Proton Safe MCP
Distribution modes declared in the official MCP registry:
- PyPI package (Python, started with
uvxorpip)
Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Python. Listed systems: Linux.
Security: what to check
An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.
None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Proton Safe MCP. That does not replace reading the code.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on August 29, 2026, the fbossiere/proton-safe-mcp repository has 6 stars and 0 forks, with 3 open issues. It has more stars than 17% of the servers in the directory. It received changes this month. Version published in the registry: 2.3.1 (October 14, 2026).
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
Proton Safe MCP is a reasonable choice; check the points below before connecting it.
Strengths
- Active project: recent commit
- Listed in the official MCP registry
- Permissive licence (MIT)
Limitations
- Few visible users
Alternatives
- Emailmd1.4K ★
- Vexa2.9K ★
- CometChat Docs129 ★
- Inbox Zero12.8K ★
- Microsoft 365 MCP Server1.1K ★
- Discourse MCP77 ★
Learn more
Frequently asked questions
How do I install Proton Safe MCP?
Proton Safe MCP is distributed as PyPI package (Python, started with uvx or pip). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of fbossiere/proton-safe-mcp.
Is Proton Safe MCP free?
The code is published under the MIT licence and can be used free of charge.
Is Proton Safe MCP safe?
No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.
Is it an official server?
Nothing says so: it is a project published by fbossiere on GitHub. Check who maintains it before giving it access.
What are the alternatives to Proton Safe MCP?
In the same category: Emailmd, Vexa, CometChat Docs, and Inbox Zero. Emailmd and Vexa score higher on our grid.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score