Bridge your knowledge base and email with MCP. Send notes as emails, capture inbox items as tasks, and manage correspondence from Obsidian.
Obsidian is a knowledge management application built on local markdown files with a rich plugin ecosystem. Through AI plugins like Copilot or Smart Connections that support MCP, you can integrate MultiMail's email tools directly into your note-taking workflow — turning notes into emails and emails into notes.
MCP configuration in Obsidian varies by plugin. Most MCP-enabled AI plugins provide a settings panel where you configure servers, or use a JSON configuration file within the plugin's settings directory. The MultiMail server connects via stdio transport, making it compatible with Obsidian's desktop environment.
This integration shines for knowledge workers who use Obsidian as their second brain. Draft meeting notes and email them to attendees, capture incoming email as linked notes, or use your vault's context to compose informed responses — all without leaving Obsidian.
Sign up at multimail.dev and create an API key from your dashboard. This key authenticates all MCP server requests.
In Obsidian, go to Settings > Community Plugins and install an AI plugin that supports MCP, such as Obsidian Copilot or Smart Connections. Enable the plugin after installation.
Open the AI plugin's settings and navigate to the MCP server configuration section. Add the MultiMail server.
In the MultiMail dashboard, create a mailbox for your Obsidian AI assistant. Start with gated_send oversight mode so outbound emails require your approval.
Open the AI plugin's chat interface in Obsidian and ask it to list your MultiMail mailboxes. If the MCP server is connected, your mailboxes will appear in the response.
| Tool | Description | Example |
|---|---|---|
| send_email | Send an email from your agent mailbox to any recipient. | Email meeting notes from your current Obsidian note to all attendees. |
| reply_email | Reply to a received email, maintaining the thread context. | Reply to a question email using context from your knowledge base. |
| check_inbox | Check a mailbox for new or unread messages. | Check for new emails and create Obsidian tasks from them. |
| read_email | Read the full content of a specific email including headers and body. | Read an email and link its content to relevant notes in your vault. |
| create_mailbox | Create a new agent mailbox on your MultiMail account. | Create a mailbox for a new research project or newsletter. |
| list_mailboxes | List all mailboxes on your MultiMail account. | View available mailboxes before choosing which to send from. |
| get_thread | Retrieve an entire email thread to see the full conversation history. | Pull a full email discussion into your vault as a reference note. |
| manage_contacts | Search your contact list by name, email, or tags. | Find a collaborator's email to share research notes. |
| manage_contacts | Add a new contact to your MultiMail contact list. | Save a contact from a received email for future correspondence. |
| tag_email | Tag or categorize an email for organization and filtering. | Tag emails to match your Obsidian vault's tagging system. |
| list_pending | List all emails currently awaiting human approval. | Review pending emails while reviewing your daily notes. |
| decide_email | Approve or reject a pending email in the oversight queue. | Approve a note-sharing email after verifying the content. |
No code, no dashboard. Paste this to your AI agent — it connects MultiMail, creates an inbox, and builds the flow for you.
Use MultiMail to create a two-way bridge between your Obsidian vault and email. Send notes as emails to share knowledge, and read incoming emails to capture insights as new notes. This keeps your vault as the single source of truth.
Use MultiMail's tag_email tool with the same tags you use in Obsidian. This creates consistency between your email organization and your knowledge graph, making it easy to find related content across both systems.
Add an email check to your daily note routine. Ask the AI to check your inbox and summarize new messages as bullet points that you can include in your daily note, keeping a log of correspondence alongside your other daily activities.
MCP support in Obsidian depends on the AI plugin you use. Not all AI plugins support MCP yet. Check the plugin's documentation or GitHub repository for MCP compatibility before setting up. Obsidian Copilot and Smart Connections are common options.
Email infrastructure built for AI agents. Verifiable identity, graduated oversight, and a hosted MCP server. Formally verified in Lean 4.