Add email capabilities to msty's desktop AI chat through MCP. Send, read, and manage email with local or cloud models.
msty is a desktop AI chat application that supports multiple LLM providers, both local and cloud-based, with built-in MCP server integration. Adding MultiMail gives msty email capabilities that work with whichever model you prefer — whether it's a local Ollama model or a cloud provider like OpenAI or Anthropic.
MCP servers in msty are configured through the application's settings interface. msty supports both stdio and SSE transport, and the setup process is streamlined with a visual configuration panel. Once connected, MultiMail tools are available in all conversations.
For users who want a clean, focused desktop chat app with email capabilities, msty and MultiMail make a practical pair. msty's knowledge bases and prompt library features complement MultiMail's email tools, letting you compose well-informed emails using your curated knowledge.
Sign up at multimail.dev and create an API key from your dashboard. This key authenticates all MCP server requests.
In the MultiMail dashboard, create a mailbox for msty to use. Set oversight to gated_send so all outbound emails require your approval.
In msty, go to Settings and find the MCP Servers section. msty provides a UI for adding and managing MCP server connections.
Add a new MCP server in msty's settings with the MultiMail configuration.
Start a new conversation in msty and ask the AI to list your MultiMail mailboxes. If connected, you'll see your mailboxes returned. Check msty's MCP status indicator for connection health.
| Tool | Description | Example |
|---|---|---|
| send_email | Send an email from your agent mailbox to any recipient. | Send a quick message drafted with help from your preferred model. |
| reply_email | Reply to a received email, maintaining the thread context. | Reply to a message using msty's prompt library for consistent tone. |
| check_inbox | Check a mailbox for new or unread messages. | Check for new emails from msty's clean desktop interface. |
| read_email | Read the full content of a specific email including headers and body. | Read an email and have the AI summarize key points. |
| create_mailbox | Create a new agent mailbox on your MultiMail account. | Create a dedicated mailbox for a new use case. |
| list_mailboxes | List all mailboxes on your MultiMail account. | View available mailboxes before composing an email. |
| get_thread | Retrieve an entire email thread to see the full conversation history. | Review a conversation thread before writing a response. |
| manage_contacts | Search your contact list by name, email, or tags. | Find a contact to send them a message. |
| manage_contacts | Add a new contact to your MultiMail contact list. | Save a new contact from a received email. |
| tag_email | Tag or categorize an email for organization and filtering. | Tag emails to organize them by topic or priority. |
| list_pending | List all emails currently awaiting human approval. | Review queued emails in a focused batch. |
| decide_email | Approve or reject a pending email in the oversight queue. | Approve a well-drafted email for delivery. |
No code, no dashboard. Paste this to your AI agent — it connects MultiMail, creates an inbox, and builds the flow for you.
msty's knowledge base feature lets you upload documents that the AI references during conversations. Upload your company's email guidelines, FAQ, or product documentation so email responses are consistent and accurate.
msty has a built-in prompt library for saving and reusing prompts. Create templates for common email tasks like weekly updates, customer responses, or meeting summaries. This ensures consistency and saves time on repetitive email operations.
msty supports multiple model providers. Use a fast local model for quick inbox checks and a more capable cloud model for composing important emails. The MCP tools work the same regardless of which model you're using.
msty supports both stdio and SSE transport for MCP servers. The MultiMail server uses stdio by default, which works well for desktop usage. If you need SSE for a remote setup, msty can handle that too.
Email infrastructure built for AI agents. Verifiable identity, graduated oversight, and a hosted MCP server. Formally verified in Lean 4.