Utuh watcher runs on your own machine — the client starts it, so there is no endpoint to ping. 71 installs a week from npm. Last commit 14 Sep 2026.
Sweep bonded completeness claims on Creditcoin against Ethereum, and refute one that omits an event.
We read the source, 4 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
this.child = spawn(command, args, { stdio: ['pipe', 'pipe', 'pipe'], env: { ...process.env, PRIVATE_KEY: '' } });
"creditArgs": "0x00000000000000000000000026880c8980cd54827543bd34c6c613253c69347b00000000000000000000000000000000000000000000000000000000000002600000000000000000000000000000000000000000000000000000000000000001000000000000000000000000c8c9053c4e2c0590df684c12e5f2610efec9575b7e79a…
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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 utuh-mcp -- npx -y utuh-mcp
{
"mcpServers": {
"utuh-mcp": {
"command": "npx",
"args": [
"-y",
"utuh-mcp"
]
}
}
}
[mcp_servers.utuh-mcp]
command = "npx"
args = ["-y", "utuh-mcp"]
{
"mcpServers": {
"utuh-mcp": {
"command": "npx",
"args": [
"-y",
"utuh-mcp"
]
}
}
}
{
"servers": {
"utuh-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"utuh-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
PRIVATE_KEY (A funded Creditcoin CC3 Testnet key, needed only by refute_claim — which also demands confirm: true. Every other tool reads the chain and spends nothing).
Offline, read-only tools that verify AI claims against evidence and replay conformance vectors.
Verify agent actions against the system of record and get signed completion receipts.
Coding agents in one repo see each other, get warned before shared edits, and message.
Independent verifier for AI agents: checks agent claims and doc promises against the code.
A verifiable museum of the agent era; browse and authenticate exhibits against Bitcoin.
Create watch-together rooms, scheduled watch parties and branded class links. No sign-up.
Let coding agents on one machine message and wake each other. Run `harness-summit install` first.
A moderated forum where AI agents read, cite and post under one house rule: claims need evidence.
Answers built from our own checks of this server.