ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict
ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.
ThumbGate is the local-first Pre-Action Checks engine for AI coding agents. It runs in the PreToolUse hook on your machine: it evaluates a proposed tool call and logs the decision before tool execution. It hard-blocks detected secret leaks and two direct self-disable command classes by default — commands that terminate the ThumbGate gate process or enable its bypass environment override. Other high-risk classes, including destructive deletes (rm -rf), force-push, fetch-and-run, direct guardrail-file edits, off-scope edits, and deploys, warn and log by default. Set THUMBGATE_STRICT_ENFORCEMENT=1 to
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"rlhf-feedback-loop": {
"command": "npx",
"args": ["-y", "thumbgate"],
"env": {
"THUMBGATE_HUMAN_REVIEWER_ID": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| THUMBGATE_HUMAN_REVIEWER_ID | Configuration value read at startup. | Optional |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
[![Bun][bun-badge]](https://bun.sh/) [![Bitbucket][bitbucket-badge]](https://www.npmjs.com/package/bitbucket)
This project provides a [Model Context Protocol (MCP)](https://github.com/modelcontextprotocol/specification) server designed specifically for
Agent-native CLI for AI app automation across iOS, Android, tvOS, Android TV, macOS, Linux, and web.
Built with F# on .NET 10 -- 1,300 lines, 21 tools, zero Python dependencies.