A hosted MCP server for your AI agents
Connect Claude, Cursor or VS Code to BillionSend over the Model Context Protocol. Agents send email, check status and manage contacts and domains, with the same rules as the REST API.
What MCP server does
Sign in, no secrets to paste
The client opens your browser. You sign in with your two-factor code if it is on, pick one team or all teams, and untick any permission you do not want to grant. Nothing sensitive sits in the client's config.
Your role applies to every call
A connected app acts with your team role. A tool your role does not cover is not offered to the client at all.
Tools for sending and for the audience
Send and schedule email, read status and usage, manage contacts, segments, topics, templates, domains and webhooks. Received mail and inboxes have their own permissions.
Same pipeline as the API
Verified domains, suppressions, unsubscribes, quotas and team scoping all apply. An unverified sender fails exactly as it fails over REST.
Untrusted data stays marked
Tool results wrap data written by your end users in a notice, and received message text is fenced between random markers. An agent can tell content from instruction.
Agent keys for unattended agents
A key for an agent with no browser: read only, or read plus send. A team holds up to 20 active agent keys, and any tool can be switched off for the whole team.
Connect Claude Code
Add the server, then run /mcp inside Claude Code and choose billionsend to sign in. Cursor and VS Code take the same URL in their MCP config.
claude mcp add --transport http billionsend https://api.billionsend.com/mcp