Connect MultiMail to JetBrains IDEs via MCP

Add email capabilities to the JetBrains AI Assistant in IntelliJ, PyCharm, WebStorm, and more through MCP integration.


JetBrains IDEs — IntelliJ IDEA, PyCharm, WebStorm, GoLand, and others — support MCP servers through the AI Assistant plugin. This lets you extend the AI Assistant with external tools like MultiMail, adding email capabilities to your IDE without switching between applications.

MCP configuration in JetBrains IDEs is managed through the AI Assistant settings panel. The MultiMail server connects via stdio transport, and once configured, its tools are available when you interact with the AI Assistant. JetBrains also supports SSE transport for remote MCP servers.

For developers deeply invested in the JetBrains ecosystem, this integration means you can handle email from within the IDE that already understands your code. Send release notes from IntelliJ, reply to support emails from PyCharm, or manage contacts from WebStorm — all with JetBrains' deep code analysis providing context.

Get started

1

Get your MultiMail API key

Sign up at multimail.dev and create an API key from your dashboard. This key authenticates all MCP server requests.

2

Ensure AI Assistant is installed

The AI Assistant plugin comes bundled with recent JetBrains IDEs. Go to Settings > Plugins and verify that 'AI Assistant' is installed and enabled. Update to the latest version for MCP support.

3

Open AI Assistant MCP settings

Navigate to Settings > Tools > AI Assistant > MCP Servers (or search for 'MCP' in settings). This is where you configure external MCP servers.

4

Add the MultiMail MCP server

Click 'Add' to configure a new MCP server. Set the transport to stdio and enter the server configuration.

json
{
  "mcpServers": {
    "multimail": {
      "command": "npx",
      "args": ["-y", "@multimail/mcp-server"],
      "env": {
        "MULTIMAIL_API_KEY": "mm_live_your_key_here"
      }
    }
  }
}
5

Create an agent mailbox

In the MultiMail dashboard, create a mailbox for the AI Assistant to use. Start with gated_send oversight mode so all outbound emails require approval.

6

Verify the connection

Open the AI Assistant panel and ask it to list your mailboxes. If configured correctly, you'll see your MultiMail mailboxes. The MCP server status should also appear in the AI Assistant settings.


Available MCP tools

ToolDescriptionExample
send_emailSend an email from your agent mailbox to any recipient.Email the QA team after implementing a fix in IntelliJ.
reply_emailReply to a received email, maintaining the thread context.Reply to a code review email with your implementation rationale.
check_inboxCheck a mailbox for new or unread messages.Check for new CI/CD notification emails between coding sessions.
read_emailRead the full content of a specific email including headers and body.Read a detailed specification email before starting implementation.
create_mailboxCreate a new agent mailbox on your MultiMail account.Create a project-specific mailbox for each JetBrains project.
list_mailboxesList all mailboxes on your MultiMail account.View available mailboxes to choose the right sender.
get_threadRetrieve an entire email thread to see the full conversation history.Review a requirements discussion thread before implementation.
search_contactsSearch your contact list by name, email, or tags.Find the project manager's email for a status update.
add_contactAdd a new contact to your MultiMail contact list.Add a new team member's email after onboarding.
tag_emailTag or categorize an email for organization and filtering.Tag emails by JIRA ticket number for traceability.
list_pendingList all emails currently awaiting human approval.Review all pending emails before your standup meeting.
decide_emailApprove or reject a pending email in the oversight queue.Approve a sprint summary email after reviewing its content.

Usage examples

JetBrains MCP configuration
json
{
  "mcpServers": {
    "multimail": {
      "command": "npx",
      "args": ["-y", "@multimail/mcp-server"],
      "env": {
        "MULTIMAIL_API_KEY": "mm_live_your_key_here"
      }
    }
  }
}

Standard MCP server configuration for JetBrains AI Assistant.

Database migration notification
text
Look at the database migration files I just created. Summarize the schema changes (new tables, altered columns, dropped indexes) and email the summary to [email protected] with subject 'Schema Migration Review Needed'.

Ask the AI Assistant to analyze schema changes and notify the team.

Test failure reporting
text
Run the tests in the current module. If any fail, analyze the failures, identify the likely root cause for each, and send a report to the author of the most recent commit that touched those files.

Have the AI Assistant analyze test failures and email a report.

API documentation email
text
Analyze the REST controllers in src/main/java/api/. Generate a summary of all endpoints with their HTTP methods, parameters, and return types. Email this API reference to the frontend team at [email protected].

Generate API docs from code annotations and email them.


Best practices

Works across all JetBrains IDEs

The MCP configuration applies to whichever JetBrains IDE you use — IntelliJ IDEA, PyCharm, WebStorm, GoLand, Rider, CLion, or others. The AI Assistant plugin and MCP support are shared across the JetBrains platform.

Use JetBrains' code analysis in emails

JetBrains IDEs have deep code analysis capabilities — type inference, dependency graphs, and inspection results. Ask the AI Assistant to include these insights in emails, such as sending a dependency analysis or code quality report to your team.

Configure per-project MCP servers

JetBrains supports project-level settings. You can configure different MultiMail API keys for different projects, allowing each project to use its own mailbox and oversight settings.

Ensure Node.js is in the IDE's PATH

JetBrains IDEs may use a different PATH than your terminal. If the MCP server fails to start, verify that Node.js and npx are accessible from the IDE's environment. You can configure this in Settings > Tools > Terminal or by specifying the full path to npx.


Common questions

Which JetBrains IDEs support MCP servers?
MCP support is available through the AI Assistant plugin, which is compatible with all JetBrains IDEs including IntelliJ IDEA, PyCharm, WebStorm, GoLand, Rider, CLion, PhpStorm, and RubyMine. You need a recent version of the AI Assistant plugin with MCP support enabled.
Do I need a JetBrains AI Assistant subscription?
Yes, the AI Assistant plugin requires a JetBrains AI subscription for full functionality, including MCP tool use. The MCP server configuration is part of the AI Assistant's advanced features. Check JetBrains' pricing page for current subscription options.
Can I use MultiMail with JetBrains' database tools?
Yes, you can combine JetBrains' built-in database tools with MultiMail. For example, ask the AI Assistant to query your database, format the results, and email them as a report. The AI Assistant can use both JetBrains' native features and MCP tools in the same interaction.
Why can't the MCP server find npx?
JetBrains IDEs may use a restricted PATH that doesn't include your Node.js installation. To fix this, either specify the full path to npx in the command field (e.g., /usr/local/bin/npx) or configure the IDE's terminal environment in Settings > Tools > Terminal to include your Node.js path.
Does JetBrains support SSE transport for MCP?
Yes, JetBrains AI Assistant supports both stdio and SSE transport for MCP servers. The MultiMail MCP server uses stdio by default, which is simpler to configure. SSE transport is useful if you want to host the MCP server remotely or share it across multiple IDE instances.

More MCP clients

The only agent email with a verifiable sender

Email infrastructure built for AI agents. Verifiable identity, graduated oversight, and a 38-tool MCP server. Formally verified in Lean 4.