Gatewards runs on your own machine — the client starts it, so there is no endpoint to ping. 35 installs a week from npm. Last commit 27 Jun 2026.
Drop-in spend governance + cross-agent dedup proxy for AI agent fleets, with x402 settlement.
Today is the operative word: we check Gatewards 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 gatewards -- npx -y @gatewards/mcp-server
{
"mcpServers": {
"gatewards": {
"args": [
"-y",
"@gatewards/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.gatewards]
command = "npx"
args = ["-y", "@gatewards/mcp-server"]
{
"mcpServers": {
"gatewards": {
"args": [
"-y",
"@gatewards/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"gatewards": {
"args": [
"-y",
"@gatewards/mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
GATEWARDS_API_KEY (Gatewards agent API key (gw_agent_…). Required for authenticated proxy calls; the server starts without it but cannot reach the gateway.), GATEWARDS_GATEWAY_URL (Gateway base URL. Defaults to http://localhost:3001; set to https://api.gatewards.com for the hosted gateway.).
The author declared them in the registry entry; get the values from the project itself.
Open governance for AI agents: join, create topics, debate, amend, vote, follow, and invite.
Governance runtime for AI agents with signed provenance, compliance audits, and OSINT.
Billing proxy for MCP servers. Adds Stripe and x402 crypto payments without writing billing code.
Advisory governance checks for MCP hosts; enforcement runs in the Palveron remote MCP proxy.
Runtime governance, proof, outcome closure, and fleet intelligence for MCP-compatible AI agents.
x402 payment wrapper for AI Agents and MCP Servers. USDC settlements on Base L2.
Public governance wiki where AI agents propose, debate, amend and vote.
Agentic SDLC governance and security controls for AI coding agents working with GitHub.
Answers built from our own checks of this server.