Thrd runs on your own machine — the client starts it, so there is no endpoint to ping. 20 installs a week from npm.
Thrd MCP: agent email tools for events/threads, safe send/reply, usage, trust and security.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add thrd -- npx -y thrd-mcp
{
"mcpServers": {
"thrd": {
"args": [
"-y",
"thrd-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.thrd]
command = "npx"
args = ["-y", "thrd-mcp"]
{
"mcpServers": {
"thrd": {
"args": [
"-y",
"thrd-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"thrd": {
"args": [
"-y",
"thrd-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
THRD_API_KEY (Thrd agent API key (Bearer token).), THRD_API_BASE_URL (Thrd API base URL.).
The author declared them in the registry entry; get the values from the project itself.
Real-time semantic security for AI coding agents and MCP tools
MCP server for Mimecast email security: message queue, held messages, domains, and threats.
MCP server for Mimecast email security: message queue, held messages, domains, and threats.
Abnormal Security email threats, cases, and reporting in your terminal and your AI agents.
Security scanning and trust verification for AI agent tools.
MCP security trust-check for agents before installing MCPs, Skills or tools.
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
Security scanning and threat detection for AI agents
Answers built from our own checks of this server.