Resend MCP Server
resend-mcp
npm
v2.19.0
Source verified
Published by resend — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
[](https://smithery.ai/server/@resend/resend-mcp) [](https://www.npmjs.com/package/resend-mcp)
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 3 = 97. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −3 | capability blast radius (moderate) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 0
Tools 103
Each tool and what it can reach — statically extracted from the published source.
create-webhooknetwork egressremove-webhooknetwork egressreplay-webhook-eventnetwork egresssend-emailnetwork egressupdate-webhooknetwork egressadd-contact-to-segmentno sensitive capabilityadd-suppressionno sensitive capabilitybatch-add-suppressionsno sensitive capabilitybatch-remove-suppressionsno sensitive capabilitycancel-broadcastno sensitive capability
Show 93 more tools ↓
cancel-emailno sensitive capabilitycompose-broadcastno sensitive capabilitycompose-templateno sensitive capabilityconnect-to-editorno sensitive capabilitycreate-api-keyno sensitive capabilitycreate-automationno sensitive capabilitycreate-broadcastno sensitive capabilitycreate-contactno sensitive capabilitycreate-contact-importno sensitive capabilitycreate-contact-propertyno sensitive capabilitycreate-domainno sensitive capabilitycreate-domain-claimno sensitive capabilitycreate-segmentno sensitive capabilitycreate-templateno sensitive capabilitycreate-topicno sensitive capabilitydisconnect-from-editorno sensitive capabilityduplicate-automationno sensitive capabilityduplicate-templateno sensitive capabilityget-automationno sensitive capabilityget-automation-runsno sensitive capabilityget-broadcastno sensitive capabilityget-contactno sensitive capabilityget-contact-importno sensitive capabilityget-contact-propertyno sensitive capabilityget-domainno sensitive capabilityget-domain-claimno sensitive capabilityget-emailno sensitive capabilityget-email-metricsno sensitive capabilityget-logno sensitive capabilityget-received-emailno sensitive capabilityget-received-email-attachmentno sensitive capabilityget-segmentno sensitive capabilityget-sent-email-attachmentno sensitive capabilityget-suppressionno sensitive capabilityget-templateno sensitive capabilityget-tiptap-json-contentno sensitive capabilityget-topicno sensitive capabilityget-webhookno sensitive capabilityget-webhook-eventno sensitive capabilitylist-api-keysno sensitive capabilitylist-broadcast-clicked-linksno sensitive capabilitylist-broadcast-recipientsno sensitive capabilitylist-broadcastsno sensitive capabilitylist-contact-importsno sensitive capabilitylist-contact-propertiesno sensitive capabilitylist-contact-segmentsno sensitive capabilitylist-contact-topicsno sensitive capabilitylist-contactsno sensitive capabilitylist-domainsno sensitive capabilitylist-emailsno sensitive capabilitylist-logsno sensitive capabilitylist-oauth-grantsno sensitive capabilitylist-received-email-attachmentsno sensitive capabilitylist-received-emailsno sensitive capabilitylist-segmentsno sensitive capabilitylist-sent-email-attachmentsno sensitive capabilitylist-suppressionsno sensitive capabilitylist-templatesno sensitive capabilitylist-topicsno sensitive capabilitylist-webhook-event-attemptsno sensitive capabilitylist-webhook-eventsno sensitive capabilitylist-webhooksno sensitive capabilitymanage-eventsno sensitive capabilitypublish-templateno sensitive capabilityremove-api-keyno sensitive capabilityremove-automationno sensitive capabilityremove-broadcastno sensitive capabilityremove-contactno sensitive capabilityremove-contact-from-segmentno sensitive capabilityremove-contact-propertyno sensitive capabilityremove-domainno sensitive capabilityremove-segmentno sensitive capabilityremove-suppressionno sensitive capabilityremove-templateno sensitive capabilityremove-topicno sensitive capabilityrevoke-oauth-grantno sensitive capabilitysend-batch-emailsno sensitive capabilitysend-broadcastno sensitive capabilitysend-eventno sensitive capabilityshare-emailno sensitive capabilityupdate-api-keyno sensitive capabilityupdate-automationno sensitive capabilityupdate-broadcastno sensitive capabilityupdate-contactno sensitive capabilityupdate-contact-propertyno sensitive capabilityupdate-contact-topicsno sensitive capabilityupdate-domainno sensitive capabilityupdate-emailno sensitive capabilityupdate-segmentno sensitive capabilityupdate-templateno sensitive capabilityupdate-topicno sensitive capabilityverify-domainno sensitive capabilityverify-domain-claimno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (103 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 9
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v2.19.0 latest |
A 97/100 | 0 | 1.13.0 | 2026-09-07 |
v2.18.0 |
A 97/100 | 0 | 1.13.0 | 2026-09-04 |
v2.17.0 |
A 97/100 | 0 | 1.13.0 | 2026-09-01 |
v2.16.0 |
A 97/100 | 1 | 1.13.0 | 2026-08-25 |
v2.15.0 |
A 97/100 | 1 | 1.12.1 | 2026-08-24 |
Show 4 more versions ↓
v2.14.0 |
A 97/100 | 1 | 1.12.1 | 2026-08-21 |
v2.13.0 |
A 97/100 | 1 | 1.12.1 | 2026-08-20 |
v2.12.0 |
A 97/100 | 1 | 1.12.1 | 2026-08-10 |
v2.11.0 |
A 97/100 | 1 | 1.12.1 | 2026-08-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan resend-mcp --onlineOther implementations of Resend 6
Independent packages implementing the same tool, scanned with the same engine. Compare all 7 side by side →
Comprehensive MCP Server for Resend API - manage emails, domains, templates, contacts, and more via AI assistants
这是一个基于 [FastMCP](https://github.com/fastmcp/fastmcp) 框架构建的 MCP (Model Context Protocol) 工具包。
Complete MCP server for Resend API with all endpoints - send emails, manage domains, contacts, broadcasts, and more
MCP server for Resend — transactional email sending, contact management, and domain verification for Claude, Cursor, and AI agents
MCP server for Resend email API - send emails, manage contacts, audiences, and domains
An MCP server for sending emails via Resend API with stdio transport
More in AI & Agents
Authenticated MCP transport with HTTP Signatures for AAuth agents
Local-first MCP server for parallel AI coding agents to claim file ownership before edits, preventing stomping on each other in the same worktree.
Agent-agnostic intercommunication system — sessions, messaging, channels, shared state, and real-time events
MCP server for AI agent task communication and delegation with diagnostic lifecycle visibility
Programmatic add/link/unlink for MCP servers across 23 AI coding agents (Claude Code, Claude Desktop, Cursor, VS Code, Codex, Gemini CLI, Zed, Cline, OpenCode, Goose, Kiro, Windsurf, and more). Functional API with dry-run support.
MCP server layer exposing agent-mesh orchestrator as an MCP agent