Skip to content
Custom Connectors

Connect SendGrid to Claude Code

Let Claude draft campaigns, manage lists, and send mail in SendGrid. From the terminal, inside the sessions where you already work.

How do you connect SendGrid to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect SendGrid, you add a SendGrid MCP server: a small hosted service that exposes SendGrid's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own SendGrid account. No API keys pasted into config files.

claude mcp add --transport http sendgrid https://your-connector-url/mcp

Then run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.

What can Claude Code do in SendGrid once connected?

Full read-write SendGrid access lets Claude draft a campaign or transactional message, build it from a dynamic template, add or remove contacts from a list, schedule a send, and trigger delivery once you approve. The work that used to live in the SendGrid dashboard happens in the same place you are already working.

  • Draft a single sender or marketing email and send it after you approve
  • Create or update a dynamic template and its versioned content
  • Add or remove contacts from a marketing list or suppression group
  • Schedule a campaign send for a chosen time
  • Generate and rotate an API key with scoped permissions
  • Pull delivery, bounce, and open stats and propose a follow-up send

One connector, every Claude surface

The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same SendGrid access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.

Build it yourself, or have it built?

If you live in the terminal, you can absolutely write your own MCP server against the SendGrid API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when SendGrid changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build SendGrid connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.

Frequently asked questions

Does the same SendGrid connector work in claude.ai and Claude Code?
Yes. It is one remote MCP server. Claude Code adds it with a single "claude mcp add" command; claude.ai and Claude Desktop add it as a custom connector in Settings. Each person signs in with their own SendGrid account, so access always matches what that person can already see and do.
Do I need to host or maintain anything myself?
No. The connector runs as a hosted service we operate: we handle uptime, token health, API changes on SendGrid's side, and MCP spec migrations under the monthly plan. Your side is one command in the terminal and an OAuth sign-in.
Is it safe to give a coding agent write access to SendGrid?
Write access is scoped, not blanket. Read tools and write tools are separated, destructive actions like deleting or sending are gated behind your explicit approval, and the connector can never exceed the permissions of the SendGrid account it signs in with. Revoking access is one click in SendGrid.

Tell us what you run. We'll build the connector.

Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.