Chp MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 34 installs a week from npm. Last commit 13 Sep 2026.
Spend approval gate for AI agents: budget caps, HITL thresholds, signed audit hash.
Today is the operative word: we check Chp MCP 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 chp-mcp -- npx -y @cubiczan/chp-mcp
{
"mcpServers": {
"chp-mcp": {
"args": [
"-y",
"@cubiczan/chp-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.chp-mcp]
command = "npx"
args = ["-y", "@cubiczan/chp-mcp"]
{
"mcpServers": {
"chp-mcp": {
"args": [
"-y",
"@cubiczan/chp-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"chp-mcp": {
"args": [
"-y",
"@cubiczan/chp-mcp"
],
"command": "npx"
}
}
}
Runtime authority for AI agents: credential mediation, spend cap, approval gates, audit log.
Token and context budget for AI agents. Tracks spend and gates the session.
Spend control for AI agents - cost attribution, budget caps, and signed runs as MCP tools.
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
A local receipt and approval gate for AI agent sessions. The agent can act, but it cannot sign.
Budget & cost control for AI agents — per-agent spend caps + rate limits before each call.
Governed USDC wallet for AI agents — policy gates, spending caps, and Ed25519-signed receipts.
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Answers built from our own checks of this server.