- Passport.Me @passport/mcpYour Gmail, Calendar, Drive, GitHub, Oura, wallet and confirmed profile facts in any MCP client.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- FranklyMail Agentic Inbox @naylalabs/agentic-inboxRead and search FranklyMail email and prepare drafts, replies, and forwards for human approval.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Email @infoinlet-marketplace/mcp-emailEmail for AI agents — read inbox (IMAP), search, and send (SMTP).6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- NordicMCP — Google Mail @nordicmcp/google-mailHosted Gmail MCP server: read, search, and manage messages. Google OAuth2 handled by NordicMCP.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Work IQ Copilot MCP Server @microsoft/workiq-m365copilotSearch across M365 content including documents, emails, sites, files, and chats.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- muse.space @muse/mcpLet your agent into iCloud Mail, calendar and contacts. It gets actions, never your password.18% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Higgs Hub @higgshub/higgs-hubGmail, Outlook, Drive, OneDrive and calendars for AI agents. Many accounts, one endpoint, audit log.23% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- CommSync @commsync/commsyncOne inbox for SMS and email: read threads, search, manage contacts, and send texts and emails.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Inbox Benefits MCP @fvegiard/inbox-benefits-mcpRead-only multi-inbox benefits radar with local deduplication and explicit account health.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Gmail Agent by Nova (CIVAI) @civai/gmail-agentI do everything related to Gmail and productivity8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Nova Inbox Agent by Nova (CIVAI) @civai/nova-inbox-agentRead and send mail from your Nova Inbox (@nova.civai.co) for OTPs, directory signups, and inbound m…6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Bottled @bottled/bottledBranded email on your own domain: send, reply, search, aliases, contacts and campaigns.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Conduit Mail @conduitmail/conduit-mailYour mailbox for MCP clients: search, read, draft, send, rules and notes. Sending is off by default.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Attrove @attrove/mcpCatch conversations going quiet — watch outcomes and search Gmail, Slack, and meetings. One MCP.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Mailbox MCP @mailbox-mcp/mailbox-mcpRead, send, file and search email in any Gmail, Microsoft 365 or IMAP mailbox, plus its calendar.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- AI Email Triage Tool & Reply Draft Helper @ranovam/mail-triageEmail triage tool powered by AI: classifies your inbox, finds messages that need a reply, and…12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Lockally Email @lockally/emailStateful email for AI agents — read inboxes, reply in-thread, draft with approval.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Hedwig @hedwig-ai/hedwigRead, arrange, and build agents on your Hedwig email board from any AI client. Nothing ever sends.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- alfred_ @get-alfred/alfredYour real Gmail, Outlook and calendars, worked as you: read, draft, send, schedule, organize.21% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Refine Job Search @getrefine/refineJob search management: applications, interviews, offers, recruiter email, and company openings.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Infinivo AI Front Desk @infinivoai/front-deskRun a live AI intake desk for personal-injury law firms, or query pricing, proof and positioning.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- namailu.cz Agent Email @namailu/agent-emailnamailu.cz gives your AI agent its own email inbox: read and send mail over MCP, with OAuth.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Google Workspace @proscendia/google-workspacePermissioned access to Gmail, Drive and Calendar via the user's own Google account15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Microsoft 365 @proscendia/microsoft-365Permissioned access to Outlook, OneDrive and Teams via the user's own Microsoft account17% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
