Send a test email, get SPF, DKIM, DMARC, TLS and IPv6 results plus sender rules. No key.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Create a temporary echo.email address. Send one email to it from the system under test, then call wait_for_report with the returned token and key. The address dies after 10 minutes without a wait_for_report call and accepts one message.
This tool takes no arguments.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http deliverability https://mcp.echo.email/mcp
Create a temporary echo.email address. Send one email to it from the system under test, then call wait_for_report with the returned token and key. The address dies after 10 minutes without a wait_for_report call and accepts one message.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Fetch a finished report as JSON: the digest plus every check (SPF trace, DKIM, DMARC, BIMI, TLS, IPv6, images, links, unsubscribe, headers, DNS log).
| Argument | Type | Description |
|---|---|---|
| report_id* | string |
{
"type": "object",
"required": [
"report_id"
],
"properties": {
"report_id": {
"type": "string"
}
}
}Wait up to timeout_s seconds (max 50) for the email sent to a test address to be analysed. Returns status waiting or received (call again), or done with a digest: score, SPF, DKIM, DMARC, TLS, IPv6 and the failing sender requirements.
| Argument | Type | Description |
|---|---|---|
| key* | string | Key from create_test_address |
| token* | string | Token from create_test_address (the address local part) |
| timeout_s | number |
{
"type": "object",
"required": [
"token",
"key"
],
"properties": {
"key": {
"type": "string",
"description": "Key from create_test_address"
},
"token": {
"type": "string",
"description": "Token from create_test_address (the address local part)"
},
"timeout_s": {
"type": "number",
"default": 45,
"maximum": 50,
"minimum": 1
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Oct 30, 2026.
Takes a password, API key or token as an argument, so the secret passes through the model's context and chat logs.
Fix: Read credentials from the server's own configuration (environment, OAuth) instead of a tool argument.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.