MCP Tools Directory
← Browse integrations

Developer tools

SendGrid Secure

Free account · sign-in required

Contact SendGrid Secure

Loading secure sign-in…

Tools for autonomous AI agents

About this integration

Security-first SendGrid MCP server: dry-run default, recipient allowlists, rate caps, audit log.

Transport
stdio
Authentication
api-key
Initial setup
credentials
Runtime
unattended
Evidence
documented
Version
0.1.0
Package
sendgrid-mcp-secure
Last compatibility test
Not independently tested

Connect your agent

sendgrid-mcp-secure

Email sends are irreversible and the confirm token is available to the calling model; the publisher describes it as defense in depth, not human approval. No email or API call was sent.

Capabilities: Preview transactional emails, Send a previously previewed payload, Read templates and delivery statistics, Manage suppressions

Connected profiles

Additional details

Registry identifier

io.github.Choppaaahh/sendgrid-mcp-secure

Source ↗ · Checked 2026-09-17
Published version

0.1.0

Source ↗ · Checked 2026-09-17
Metadata license

CC0-1.0; package licenses are separate

Source ↗ · Checked 2026-09-17
Package ecosystem

pypi

Source ↗ · Checked 2026-09-17
Required configuration names

SENDGRID_API_KEY

Source ↗ · Checked 2026-09-17
Source artifact

sendgrid-mcp-secure

Source ↗ · Checked 2026-09-18
Source manifest version

0.1.1

Source ↗ · Checked 2026-09-18
Unattended configuration

The MCP host launches the package through uvx over stdio; dry-run is the documented default even when the process stays available.

Source ↗ · Checked 2026-09-18
Authentication and prerequisites

A restricted-scope SendGrid API key is supplied only through SENDGRID_API_KEY in the server environment.

Source ↗ · Checked 2026-09-18
Connection configuration

Configure uvx sendgrid-mcp-secure and keep SENDGRID_MCP_MODE=dry-run until the operator explicitly enables live mode.

Source ↗ · Checked 2026-09-18
Review scope

Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.

Source ↗ · Checked 2026-09-18