ThoughtProof runs on your own machine — the client starts it, so there is no endpoint to ping. 61 installs a week from npm. Last commit 4 Nov 2026.
Pre-action gate: verify before pay/trade/write/deploy. execute=true only on ALLOW.
We read the source, 3 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.
proc = subprocess.run(
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 thoughtproof-mcp -- npx -y thoughtproof-mcp
{
"mcpServers": {
"thoughtproof-mcp": {
"command": "npx",
"args": [
"-y",
"thoughtproof-mcp"
]
}
}
}
[mcp_servers.thoughtproof-mcp]
command = "npx"
args = ["-y", "thoughtproof-mcp"]
{
"mcpServers": {
"thoughtproof-mcp": {
"command": "npx",
"args": [
"-y",
"thoughtproof-mcp"
]
}
}
}
{
"servers": {
"thoughtproof-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"thoughtproof-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
DQL_API_KEY (Required for DQL-backed verify_decision calls. Sentinel and RV paths use their respective keys), SENTINEL_API_KEY (Optional; needed when mode=sentinel or auto-route picks Sentinel), THOUGHTPROOF_API_KEY (Optional operator key for verify_claim / verify_trade / Sentinel fallback).
Pre-deploy ship gate AI agents call before shipping. Also audits the agent's own MCP config.
The API-change deploy gate for AI coding agents. Read-only breaking-change detection.
MCP server for the Google Apps Script API: projects, code, versions, deployments and executions.
Inspect n8n, Dify, Trigger.dev and Activepieces automation exports before deployment.
Deployment truth verification for AI agents. Verifies the live site matches the build.
Checks TypeORM migrations for data loss, table locks, and deploy problems before they run.
Execution graph of AWS: verified contracts, least-privilege IAM policies, pre-flight authorization.
Solana pre-trade safety for AI agents: cabal, bundle, dump, deployer & honeypot in one verdict.
Answers built from our own checks of this server.