A thoughtfully engineered local-first gating layer: no LLM on the enforcement path, auditable decisions, break-glass recovery, and honest disclosure of limits. Its value hinges on hook interception — hard enforcement only on PreToolUse-capable agents — and the docs candidly note advisory-mode limits, estimate-based savings, and unshipped roadmap items. Well suited to teams wanting a cross-agent, learning rule store; overkill for simple static denylists.
Strongest · Documentation 14/20 Weakest · Reliability 8/20
Static review · not runListed 2026-09-07
Read the FMRS scoring method →Runtime：Node.js 18+
THUMBGATE_MCP_PROFILE
Optional MCP tool profile override (essential | default | readonly | locked). Omit to keep the factory least-privilege essential profile; only set when expanded tools are intentional.
THUMBGATE_STRICT_ENFORCEMENT
Set to 1 to preserve deny decisions for every matched blocking rule; by default most matched gates warn and log instead of blocking.
Run npx thumbgate init to auto-detect and wire your agent's integration, or run it as a stdio MCP server directly: npx -y thumbgate serve. Optional THUMBGATE_MCP_PROFILE (essential | default | readonly | locked) overrides the tool profile; THUMBGATE_STRICT_ENFORCEMENT=1 enables strict blocking. Do not use npm start for MCP — that launches the HTTP API, not the stdio server.
{"mcpServers":{"thumbgate":{"command":"npx","args":["-y","thumbgate","serve"]}}}
Shown for Claude Code. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"thumbgate": {
"command": "npx",
"args": [
"-y",
"thumbgate",
"serve"
]
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add thumbgate -- npx -y thumbgate serve
Run it in a terminal; replace any <…> placeholders with your own values first.
After configuring the client with {"mcpServers":{"thumbgate":{"command":"npx","args":["-y","thumbgate","serve"]}}}, start the client and confirm the thumbgate server appears with tools such as gate_check and capture_feedback; alternatively run 'npx thumbgate doctor' to health-check the hooks and MCP wiring.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
ThumbGate is a local-first Pre-Action Checks engine that runs as a stdio MCP server and via PreToolUse hooks to evaluate proposed AI agent tool calls before execution. It captures thumbs-up/down feedback as local lessons, promotes repeated failures into prevention rules, and hard-blocks detected secret leaks plus direct self-disable commands (process kill, env bypass) by default. Other high-risk classes (rm -rf, force-push, fetch-and-run) warn and log by default; THUMBGATE_STRICT_ENFORCEMENT=1 preserves deny decisions for every matched blocking rule. Gate decisions are deterministic (literal/AST matching with local bge-small embeddings via LanceDB) — no LLM runs on the enforcement path. Claude Code, Codex, and Gemini CLI get hard interception; Cursor, Cline, OpenCode, and Amp get advisory gate_check only. Free tier: 2 feedback captures/day (10 total), 3 active auto-promoted prevention rules; Pro at $19/mo adds unlimited rules, lesson recall/search, and a personal dashboard. MIT-licensed.
Upstash's official server providing up-to-date third-party library docs for AI coding assistants
AI-powered NPM package analysis MCP server
An independent control layer that gives AI coding agents budgets, brakes, and receipts
GitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language
Source revision e088a6d6df56 Data synced 2026-10-19 Read the FMRS scoring method