ThumbGate runs on your own machine — the client starts it, so there is no endpoint to ping. 724 installs a week from npm. Last commit 17 Sep 2026.
Pre-action gates that block AI agents from repeating known mistakes.
We read the source, 23 h ago · rules 3dff92dd89df
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
fs.writeFileSync(outputPath, result.jsonl);
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.
postinstall: node bin/postinstall.js || true
const child = spawn(process.execPath, [serverPath], {
const refFile = path.join(gitDir, 'refs', 'heads', branch);
target.innerHTML = gates.map(function (g) {
for (const fileName of fs.readdirSync(directory)) {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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 thumbgate -- npx -y thumbgate
{
"mcpServers": {
"thumbgate": {
"args": [
"-y",
"thumbgate"
],
"command": "npx"
}
}
}
[mcp_servers.thumbgate]
command = "npx"
args = ["-y", "thumbgate"]
{
"mcpServers": {
"thumbgate": {
"args": [
"-y",
"thumbgate"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"thumbgate": {
"args": [
"-y",
"thumbgate"
],
"command": "npx"
}
}
}
Pre-action gates that block AI agents from repeating known mistakes.
Local mandate gate and proof trail for AI agents that take consequential actions.
50 AI prompts for real estate listing agents — CMA, MLS, buyer presentations
Blockchain SSN for AI agents. MCP gateway that blocks at the point of action, tamper evident audit.
MCP enforcement layer that intercepts AI agent actions and blocks rule violations before execution.
RLHF feedback loop for AI agents. Capture signals, promote memories, block mistakes, export DPO.
Decision tracking with prediction validation and outcome gates for AI agents
Create and manage Form.io forms, resources, actions, roles, and projects from your AI agent.
Answers built from our own checks of this server.