JMAP MCP Server
JMAP-MCP
MCP 経由でメールを読んでください!
導入
JMAP-MCPは、JMAP(JSON Mail Access Protocol)サーバーと連携するように設計されたコネクタで、モデルコンテキストプロトコル(MCP)を介してメールを読み取ることができます。このプロジェクトは、Fastmail JMAPサーバーとの統合を具体的に示しています。
Related MCP server: email-mcp
設定
前提条件: Node.js がインストールされていることを確認してください。
リポジトリのクローンを作成する: このリポジトリをローカル マシンにクローンします。
依存関係をインストールします。プロジェクト ディレクトリに移動して、次を実行します。
npm install
APIトークンの設定
メールサーバー(例:Fastmail)で認証するには、JMAP APIトークンを設定する必要があります。APIトークンはサーバー設定から取得してください。
アプリケーションを実行するときに、 JMAP_SESSION_URLおよびJMAP_TOKEN環境変数を設定します。
MCP構成
JMAP-MCPを使用するには、MCP設定ファイルでmcpServerとして設定する必要があります。設定例を以下に示します。
{
"mcpServers": {
"emails": {
"command": "npx",
"args": ["-y", "@jahfer/jmap-mcp-server"],
"env": {
"JMAP_SESSION_URL": "https://api.fastmail.com/jmap/session", // for example
"JMAP_TOKEN": "<your-jmap-token>"
}
}
}
}使用法
MCP で設定が完了すると、MCP 内でサーバー定義と対話するコマンドまたは機能を使用して、JMAP プロトコル経由で電子メールを読み取ることができます。
Available Tools
3 toolsget_email_contentD
| Name | Required | Description | Default |
|---|---|---|---|
| inputSchema | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_mailboxesD
| Name | Required | Description | Default |
|---|---|---|---|
| inputSchema | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_emailsD
| Name | Required | Description | Default |
|---|---|---|---|
| inputSchema | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
3 tool updates
- First observed
get_email_content - First observed
get_mailboxes - First observed
search_emails
TDQS
Scored across 3 tools
The three tools have clearly distinct purposes: get_email_content retrieves specific email content, get_mailboxes lists mailboxes, and search_emails searches across emails. There is no overlap in functionality, making it easy for an agent to select the right tool for each task.
All tool names follow a consistent verb_noun pattern with snake_case (get_email_content, get_mailboxes, search_emails). The naming is predictable and readable throughout the set.
With only 3 tools, the set feels thin for an email server, as it lacks operations like creating, updating, or deleting emails or mailboxes. While the tools cover basic retrieval and search, the scope is limited and may not support full email workflows.
The tool surface is significantly incomplete for an email domain, missing essential CRUD operations such as send_email, delete_email, create_mailbox, or update_email. This will likely cause agent failures when attempting comprehensive email management tasks.
Maintenance
Related MCP Connectors
Programmable email inbox for AI agents — JMAP, PoW auth, stdio MCP server.
Your IMAP mailbox as an MCP server: read, search and (if you allow it) organize mail. Open source.
MCP server for Nylas — read email, calendars, events and contacts, and send email or create events.
MCP server for MailTempo's public free temporary email inboxes.
Related MCP Servers
- AlicenseAqualityAmaintenanceLocal MCP server for Hey.com email - read, search, send, reply, and manage the screener via stored session cookies. Runs over stdio, stores no credentials.3712MIT
- AlicenseAqualityDmaintenanceLocal MCP server for multi-account IMAP/SMTP email (iCloud + Gmail via app-specific passwords). Never marks mail read. Cross-folder search, idempotent sends, TLS verified.8MIT
- AlicenseAqualityCmaintenanceMCP server for reading, searching, and sending ProtonMail emails via the ProtonMail Bridge.162GPL 3.0
- AlicenseNot gradedqualityCmaintenanceA minimal MCP server for reading, searching, managing, and sending email over IMAP and SMTP.MIT