aldred-guard-mail
mcpsmithery# Secure email inbox protected against prompt injection attempts, malware, viruses and more This MCP server acts as a secure gateway between your AI agents and email systems, protecting against common email-borne threats before content ever reaches your LLM. Every message is scanned for prompt injection attempts, malware, viruses, spam, and other malicious content, ensuring your agents only process trusted, sanitized emails. ## Features * **Prompt Injection Protection** – Detects and neutralizes prompt injection attacks embedded in email content. * **Malware & Virus Scanning** – Prevents AI agents from processing malicious attachments and infected messages. * **Spam & Phishing Detection** – Filters unwanted and deceptive emails before they reach your workflows. * **Secure MCP Integration** – Connect AI agents through the Model Context Protocol (MCP) for controlled, secure email access. * **Safe Email Processing** – Delivers clean, validated email content while blocking or quarantining suspicious messages. * **Enterprise Ready** – Designed for AI-powered automation, customer support, assistants, and autonomous workflows. ## Ideal For * AI customer support agents * Email automation workflows * Autonomous assistants * Enterprise AI applications * Security-conscious MCP deployments Keep your AI productive while ensuring email remains a trusted source of information.
By Smithery | 18 findings | Scanned 7/12/2026 | tooltrust-scanner/v0.3.19
Risk Summary
Safe With Normal ControlsDep Visibility is the main signal, but overall risk remains within an acceptable range.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (18)
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
send_emailget_attachment_urlFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
register_user:input parameter "password" accepts a credential (informational; not evidence of insecure handling)
Fix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
register_usersend_emaillist_inboxlist_spamlist_quarantineget_emailmove_to_inboxupdate_spam_settingsupdate_security_settingsget_quotaget_attachment_urlFix: Review and remediate the identified issue.
declared capabilities: HTTP requests
send_emaildeclared capabilities: filesystem access
update_spam_settingsupdate_security_settingsdeclared capabilities: network access
get_attachment_urlFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y aldred-guard-mail"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)