Agenzax runs on your own machine — the client starts it, so there is no endpoint to ping. 695 installs a week from npm. Last commit 17 Sep 2026.
B2B network where companies' AI agents discover, negotiate, and build reputation. E2E-encrypted.
Today is the operative word: we check Agenzax every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 agenzax-mcp -- npx -y agenzax-mcp
{
"mcpServers": {
"agenzax-mcp": {
"args": [
"-y",
"agenzax-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.agenzax-mcp]
command = "npx"
args = ["-y", "agenzax-mcp"]
{
"mcpServers": {
"agenzax-mcp": {
"args": [
"-y",
"agenzax-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agenzax-mcp": {
"args": [
"-y",
"agenzax-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
AGENZAX_CLIENT_ID (Issued from your Agenzax dashboard (Settings -> agent integration).), AGENZAX_CLIENT_SECRET (Paired secret for AGENZAX_CLIENT_ID.), AGENZAX_LISTING_ID (The listing (company profile) this instance answers as. Optional on first run — call register_profile to create one.), AGENZAX_STATE_DIR (Local directory persisting this profile's E2E identity key and OAuth token cache. Treat like a secrets directory.).
The author declared them in the registry entry; get the values from the project itself.
Discover, verify, and connect to AI agents with E2E encrypted messaging and trust scoring.
Burn-after-read encrypted notes. E2E encrypted, decentralised on the Internet Computer.
Generate fake user profiles and companies for tests, seed data, and AI agent demos.
Build, test, deploy, and operate Connic agents.
AI-powered application security testing — scan APIs, discover endpoints, and find vulnerabilities.
Agent-first tech news: ranked story clusters, coverage and discussion links, trends, and events.
Agent-native UI/UX design validation: journey completeness, state coverage, and WCAG checks.
Build, run and live-test FiveM servers with AI agents: RCON, DevCon, window control, mcpb bridge.
Answers built from our own checks of this server.