$ loading_
Enable AI agents to send, receive, and manage email workflows programmatically.
The available material is sparse, but the tool claims email send/receive, inbox/thread management, and webhook handling. Although no credentials or remote endpoints are declared, its functionality inherently touches communication data and may involve local code execution, so the overall posture is caution rather than high risk. Open-source MIT licensing is a positive factor, but low community adoption and unknown maintenance reduce supply-chain confidence.
The material explicitly states 'no keys/environment variables required'; no API key, account password, or other sensitive credential requirement is disclosed. Based on the provided facts, credential exposure appears low, though the docs do not clarify whether any implicit local session or config is used for the email platform.
The tool is described as sending/receiving email and managing inboxes, threads, and webhooks, which typically implies handling and possibly transmitting communication content; however, no remote endpoints are declared, leaving egress scope unclear. No clearly unrelated or suspicious destination is identified, so this is caution rather than high risk.
The system flags this tool as 'executes-code,' indicating it has the normal MCP-server capability to run local processes/code. The material does not show requests for abnormal system privileges or clearly unrelated dangerous execution, so this is rated caution as an inherent tool capability.
Per the description, it can send and receive emails and manage inboxes, threads, and webhooks, implying access to message content, contacts, and related metadata—data that can be moderately to highly sensitive. The material does not specify file-system scope, and no clearly excessive access beyond the email use case is described, so this is caution.
The project is open source under the MIT license, which is a meaningful risk-reducing factor because the code can in principle be audited. However, it comes from a third-party registry, shows 0 GitHub stars, has unknown maintenance status, and lacks a README, which weakens confidence in verifiability and upkeep. No closed-source behavior, impersonation, or overtly malicious sign is shown, so this is caution.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "sendook-mcp" yet — see the docs or source repo.
Use the Sendook MCP to send follow-up emails to customers who attended yesterday’s product demo but have not replied. Include a thank-you note, a product resource link, and personalize each email with the customer’s name.
A batch of follow-up emails sent successfully, with delivery status or failure reasons returned.
Use the Sendook MCP to read email threads from the support@ inbox from the last 7 days, group them by topic, and flag high-priority conversations that need a human reply.
An organized thread list with topic classification and high-priority flags.
Use the Sendook MCP to monitor webhook events for new emails and replies; when a customer reply arrives, extract the sender, subject, and body summary, then write it into the internal task system.
An automated webhook workflow that outputs structured email data and completes task synchronization.
Enable AI agents to securely send emails with SMTP and attachments.
Enable AI assistants to send SMTP emails with attachments and connection testing.
Enable AI agents to send physical mail and receive scanned inbound mail.
Send transactional emails, track status, and manage contacts through MCP.
Connect AI agents to email for sending, organizing, and workflow automation.
Let AI agents send, receive, poll, and manage emails automatically.