Email Guard MCP
Email safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks. It provides deterministic detection of known attack patterns against email transport and secrets without using LLMs in the detection path.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Scan inbound emails for prompt injection or phishing patterns
- Scan outbound emails for secret leaks
- Determine package safety before installation
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
email-guard-mcp 1.3.0
{
"version": "1.3.0",
"transport": "stdio",
"identifier": "email-guard-mcp",
"registryType": "npm"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"email-guard-mcp": {
"command": "npx",
"args": [
"-y",
"email-guard-mcp@1.3.0"
]
}
}
}Cline
{
"mcpServers": {
"email-guard-mcp": {
"command": "npx",
"args": [
"-y",
"email-guard-mcp@1.3.0"
]
}
}
}VS Code
{
"servers": {
"email-guard-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"email-guard-mcp@1.3.0"
]
}
}
}Claude Desktop
{
"mcpServers": {
"email-guard-mcp": {
"command": "npx",
"args": [
"-y",
"email-guard-mcp@1.3.0"
]
}
}
}Let your agent find its tools
Find servers like Email Guard MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.