Authenticated email gateway for AI agents — per-agent inboxes, HITL approval, SPF/DKIM verified.
MCPpedia last refreshed this data
dev.e2a/mcp-server is an MCP server that authenticated email gateway for AI agents — per-agent inboxes, HITL approval, SPF/DKIM verified. Its tool list has not been published yet, requires no API key, and scores 60/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"e2a": {
"url": "https://api.e2a.dev/mcp"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Receive inbound over webhook · WebSocket · REST · MCP. Send through an HTTP API. Every sender — human or agent — identity-verified.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y '@e2a/cli' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked @e2a/cli against OSV.dev.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in communication / ai-ml
MCP client bridge: connects to MCP servers and registers their tools on ctx.tools
An autonomous agent that conducts deep research on any data using any LLM providers
The official MCP server implementation for the Perplexity API Platform
1000+ scientific tools for AI scientists: life science, reserach, literature, and more.
MCP Security Weekly
Get CVE alerts and security updates for dev.e2a/mcp-server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Receive inbound over webhook · WebSocket · REST · MCP. Send through an HTTP API. Every sender — human or agent — identity-verified.
A Token Canopy product
/v1 is now generally available — shipped in v1.5.0.
Hosted (e2a.dev) · Quickstart · Examples · Concepts · API · SDKs · MCP · Deploy · FAQ
[!IMPORTANT] The core
/v1API and SDKs are stable and generally available (GA) as of v1.5.0: no breaking changes within/v1. That tag is the compatibility baseline — every later release is audited against it. A small, explicitly enumerated surface is still beta and may change before it is declared stable — contacts & outreach, scheduled sending (send_at), email templates & starter templates, the reviews (HITL) queue, agent protection config, agent-scoped suppressions, managed unsubscribe, message lifecycle diagnostics, and thethread_idmessage-read field. Beta surface is markedx-stability-level: betain the OpenAPI spec and(beta)in the docs; where only specific values of a stable field are beta (thescheduledsend status, the screening/review-hold event types, theblocked_by_policyerror code), the field carriesx-experimental-valuesnaming exactly those values. Everything else is covered by the GA freeze. See the full matrix in docs/api.md → Stability: GA and beta surface. Existingv1.0.xapplication/cherry-pick tags predate the API freeze and are not/v1compatibility baselines.
e2a is an authenticated email gateway for AI agents. It receives inbound mail, evaluates SPF, every DKIM signature, and DMARC, and delivers structured authentication evidence over whichever channel fits your runtime. Outbound goes back out through an HTTP API, with an optional human-in-the-loop approval gate.
Four ways to plug an agent in:
https://api.e2a.dev/mcp) and your agent gets an inbox toolset (`list_me