Agent Mail
Free
Agent Mail is an AI Agent exclusive mailbox service launched by Tencent QQ Mailbox. It is completely isolated from personal mailboxes and natively adapts to the Agent framework. Agent can obtain an independent email address through WeChat scan code authorization, securely send and receive emails, manage attachments, search emails, and support a two-stage confirmation mechanism to prevent misoperations. Desktop tool installation, get started in five minutes.
Agent Mail
Core parameters and statistics
| Parameters | Official verifiable information |
|---|---|
| Product Positioning | AI Agent dedicated email service |
| Authorization method | WeChat scan OAuth |
| Isolation mechanism | Completely isolated from personal QQ/WeChat mailbox |
| Security mechanism | Two-stage confirmation + Prompt injection protection |
| Sending limit | Maximum 3 attachments/email |
| Desktop installation | npm install -g @tencent-qqmail/agently-cli |
| Pricing | Currently Free |
| Developer | Tencent QQ Email Team |
A brief comment: Agent Mail is not an ordinary mailbox, but a "work mailbox" specially used by AI Agents - isolated, safe, and controllable.
User and market recognition
Gradually build user awareness in the field, and product capabilities are used by content creators and teams to improve work efficiency. Some industry users have incorporated it into their daily workflow. It is recommended to refer to the latest official disclosures for specific user scale and industry adoption rate data.
Cost advantage
C-side/individual developers: Currently free to use. Install the Desktop tool through npm, and scan the QR code on WeChat to get the exclusive Agent mailbox.
Enterprise/Team: Enterprise pricing has not yet been announced. Based on the QQ mailbox infrastructure, enterprise users within the Tencent system can expect lower usage costs.
API/Developer: Open source Desktop tools and SkillHub integration. Compared with similar overseas products (such as Resend $20-$200/month), Agent Mail is currently free and has a significant cost advantage.
Main functions
- WeChat scan code authorization: No password is required, WeChat OAuth scan code can be used to complete the authorization, and the Agent obtains an independent email address.
- Two-stage confirmation mechanism: All write operations (send/reply/forward/delete) must first generate an operation summary and confirmation token, and then execute after user confirmation.
- Prompt injection protection: When reading emails, the "instructions" in the email content will not be executed as commands to prevent malicious emails from controlling the Agent.
- Email Management: Supports inbox/sent/recycle bin/junk email filtering, and queries based on time, unread, attachments and other conditions.
- Email Search: Search the subject and text by keywords, and support combination filtering of sender, recipient, time, attachment, etc.
- Attachment Management: Supports uploading attachments and sending them with emails, downloading attachments to the local area, and returning download links for large attachments.
- Desktop tool:
npm i -g @tencent-qqmail/agently-cli, three-step installation, five minutes to get started.
Model and version evolution
Continuous iterative updates, the latest version introduces performance optimization and new features. Historical version information can be viewed on the official release page. There is no complete public version evolution timeline yet. It is recommended to pay attention to the official announcement to understand the rhythm of feature updates.
Technical advantages
Main Type Judgment: Agent/automation tool—AI Agent’s exclusive mailbox infrastructure.
Architecture link: Agent → Desktop/SkillHub → Agent Mail API → QQ mailbox infrastructure → WeChat code scanning authorization
The core security design of Agent Mail is a combination of "two-stage confirmation + prompt injection protection" - two-stage confirmation prevents Agent from performing high-risk operations independently, and prompt injection protection prevents malicious emails from controlling Agent behavior through content. These two mechanisms are crucial when the AI Agent operates external services.
Guide to engineering pitfalls:
- Desktop dependency: Node.js is required to install the Desktop tool in context, and projects that are not Node.js technology stacks require additional adaptation.
- Sending Limitation: Each email can have up to 3 attachments. Please pay attention to the restrictions in batch sending scenarios.
- Tencent Ecological Binding: Deeply dependent on WeChat and QQ mailbox ecology, the threshold for overseas users and domestic non-Tencent users is high.
How to use
| Entrance | Description |
|---|---|
| Desktop tools | npm install -g @tencent-qqmail/agently-cli |
| SkillHub | npx skills add Tencent/AgentlyMail -g -y |
| WeChat authorization | agently-cli auth login → Browser scan code |
Product Pricing
The pricing model is subject to the official real-time page. Usually a freemium or subscription system is used, and basic functions can be used for free. Advanced functions or high-frequency use require paid subscriptions, and users are advised to evaluate the optimal solution based on actual usage.
Application scenarios
- Automated Office: Agent automatically processes daily emails, classifying, summarizing, and reminding them according to rules, reducing the burden of manual email processing.
- Procurement docking: Agent automatically contacts suppliers, collects quotes, organizes comparison tables, and automates the procurement process.
- Customer Service: Agent, as a dedicated customer service email, automatically replies to frequently asked questions to improve response efficiency.
- Multi-Agent collaboration: Different Agents have independent mailboxes and coordinate tasks with each other through emails.
Applicable people
- Individual Users: Content creators and knowledge workers who need AI assistance to improve their daily work efficiency.
- Developers: Technical teams who need to integrate AI capabilities into their own products or services through APIs.
- Enterprise: Organizations seeking to deploy AI at scale in their field.
Summary and Outlook
Agent Mail solves a real pain point in the field of AI Agents - Agents need a secure, isolated mailbox to operate on behalf of the user. Two-stage confirmation and Prompt injection protection are key security designs that distinguish it from ordinary mailboxes. The current free policy lowers the access threshold for Agent’s email capabilities.
Not suitable for boundaries: It is deeply bound to the WeChat/QQ mailbox ecosystem and cannot be used by overseas users; the Desktop tool relies on Node.js; there are restrictions on email attachments and sending frequency; the product is still in its early stages.
Purchase Suggestion: Domestic developers can access and experience it for free. The impact of the two-stage confirmation mechanism on the automation process needs to be evaluated before production and use. Pay attention to whether Tencent will launch an enterprise version and SLA later.
Related tools: crewai, langchain
Version Info
- Agent Mail current ：It currently supports WeChat code scanning authorization, email management, attachment operations, and two-stage confirmation prompt injection protection, and has been listed on Tencent SkillHub.
- Agent Mail preview ：Agent Mail early preview version, basic email sending and receiving functions.
User Reviews