Haltproof runs on your own machine — the client starts it, so there is no endpoint to ping. 141 installs a week from pypi. Last commit 25 Sep 2026.
Fail-closed deterministic checks and hash-chained receipts for AI agent outputs via MCP.
What the code does
We read the source, 18 h ago · rules ccca72095570
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.
const result = spawnSync(checkCommand, [PYTHON_CLI_NAME], {
proc = subprocess.run(
return dict(os.environ)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
Connect this server
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 haltproof -- uvx haltproof-cli{
"mcpServers": {
"haltproof": {
"args": [
"haltproof-cli"
],
"command": "uvx"
}
}
}[mcp_servers.haltproof]
command = "uvx"
args = ["haltproof-cli"]{
"mcpServers": {
"haltproof": {
"args": [
"haltproof-cli"
],
"command": "uvx"
}
}
}{
"mcpServers": {
"haltproof": {
"args": [
"haltproof-cli"
],
"command": "uvx"
}
}
}Alternatives to Haltproof
same job, measured the same wayFail-closed quality gate and hash-chained receipt ledger for AI agent workflows.
Machine-payable deterministic identifier checks + signed XDR-1 receipts for agents.
Deterministic temporal and business-date arithmetic for AI agents via MCP.
Deterministic authorization and security guard for AI agent actions with signed receipts.
LingNao: deterministic reasoning for AI agents → verified/refuted/unverifiable. ~3ms, fail-closed.
Signed, hash-chained provenance receipts for AI agent actions.
Runtime verification MCP server: fail-closed checks for agent tool calls, signed evidence receipts.
Gate for coding agents' MCP and built-in tool calls: rules, approvals and hash-chained receipts
Haltproof — questions
Answers built from our own checks of this server.