ThumbGate MCP工具

Install for Your Agent

Works with Claude Code, Cursor, Codex, Gemini CLI, Amp, Cline, OpenCode, and any MCP-compatible agent. Migrating from Roo Code (sunsetting 2026-05-15)? See adapters/cline/INSTALL.md.

Install Codex Plugin

Open the Codex plugin install page or download the standalone bundle from GitHub Releases. The Codex launcher resolves thumbgate@latest when MCP and hooks start, so published npm fixes reach active Codex installs without hand-editing ~/.codex/config.toml.

1. Install page: thumbgate.ai/codex-plugin
2. Direct zip: thumbgate-codex-plugin.zip
3. Follow: plugins/codex-profile/INSTALL.md

Install ChatGPT App / GPT Action

ChatGPT is the advice, checkpointing, and typed-feedback surface; ThumbGate's hard enforcement still runs locally in Codex, Claude Code, Cursor, Gemini CLI, Amp, OpenCode, MCP, or CI after install.

1. App page: thumbgate.ai/chatgpt-app
2. Live GPT: thumbgate.ai/go/gpt
3. GPT Action schema: thumbgate.ai/openapi.yaml
4. Follow: adapters/chatgpt/INSTALL.md

---

Optional Vertex Setup

To wire local ThumbGate scoring to Vertex AI, run:

npx thumbgate setup-vertex

This command does not create or verify a live Dialogflow CX agent. Dialogflow is only relevant when a customer wants ThumbGate guard adapters in front of their own production DFCX agents. On current Google Cloud CLI installs, the old alpha gcloud CX command group is not available; verify Conversational Agents / Dialogflow CX with the Google Cloud console or the official Dialogflow CX REST API (projects.locations.agents) before claiming a live DFCX deployment.

Quick Start

npx thumbgate init                                                         # auto-detects your agent, wires everything
npx thumbgate capture down "Never run DROP on production tables"

That single command creates a prevention rule. Next time any AI agent tries to run DROP on production:

⛔ Check blocked: "Never run DROP on production tables"
   Pattern: DROP.*production
   Verdict: BLOCK

---

Use Cases

🎬 90-second demo

Watch the force-push scenario: agent tries to git push --force, one thumbs-down, next session it's blocked — zero tokens spent on the repeat.

▶ Watch the 90-second demo · Script · ElevenLabs narration: npm run demo:voiceover

---

Enterprise Data Chat and Optional Google Adapters

The Enterprise dashboard chat is local/open-source first: it answers over local ThumbGate data using lesson retrieval, LanceDB-backed vectors, and your configured LLM. Set THUMBGATE_LOCAL_LLM_ENDPOINT to an OpenAI-compatible local endpoint (Ollama, llama.cpp, vLLM, LM Studio, etc.) when you want generated answers without sending dashboard data to Google.

Google Cloud is an optional regulated-enterprise adapter, not a dashboard chatbot requirement. If a buyer already standardizes on Vertex AI or Dialogflow CX, ThumbGate can verify that posture and deploy guard adapters in their tenancy.

CLI Reference

npx thumbgate init                                              # detect agent, wire hooks
npx thumbgate doctor                                            # health check
npx thumbgate capture up|down "<text>"                         # capture a signal as a stored lesson (positional format)
npx thumbgate lessons                                           # see what's been learned
npx thumbgate brain --write                                     # build .thumbgate/BRAIN.md — the agent-readable context brain
npx thumbgate explore    # terminal explorer for lessons, checks, stats
npx thumbgate background-governance  # review background-agent run risk
npx thumbgate model-candidates --workload=dashboard-analysis --provider=openai --json  # evaluate GPT-5.5 routing
npx thumbgate native-messaging-audit  # inspect local browser bridges and extension hosts
npx thumbgate dashboard --open                                  # open local project-scoped dashboard in browser
thumbgate-dashboard                                             # standalone browser dashboard shortcut (run '/project:thumbgate-dashboard' in Claude/Grok)
npx thumbgate check-update                                      # check if a new version is available on npm/GitHub
npx thumbgate self-update                                       # update ThumbGate to the latest version globally
npx thumbgate serve      # start MCP server on stdio
npx thumbgate bench      # run reliability benchmark
npx thumbgate bench --programbench-smoke  # include cleanroom whole-repo proof lane
npx thumbgate break-glass --reason="ThumbGate over-fired"  # short TTL recovery for gate over-fire

Developer Workflows

• Stop force-push to main — Check blocks git push --force on protected branches before it runs
• Prevent repeated migration failures — Each mistake becomes a searchable lesson that fires before the next attempt
• Block unauthorized file edits — Control which files agents can touch with path-based rules
• Memory across sessions — The agent remembers your feedback from yesterday
• Shared team safety — One developer's thumbs-down protects the whole team
• Auto-improving without feedback — Self-improvement mode evaluates outcomes and generates rules automatically

Integrations

• ChatGPT App / GPT Action — First-class ChatGPT distribution page with the live GPT, public OpenAPI Action schema, and local enforcement install path
• Open ThumbGate GPT — ThumbGate GPT: start here. Paste agent actions, get advice + checkpointing. No, users do not have to keep chatting inside the ThumbGate GPT to use ThumbGate — the hard enforcement layer still runs where the work happens.
• Claude Desktop Extension — One-click install for Claude Desktop
• Codex Plugin — Auto-updating standalone bundle and install page for Codex CLI
• VS Code / Open VSX Extension — Marketplace-ready MCP provider and .vscode/mcp.json fallback for VS Code-compatible IDEs
• Antigravity-compatible VSIX — Open VSX/direct VSIX install path while Antigravity-specific marketplace support is still unproven
• JetBrains Plugin Scaffold — IntelliJ/PyCharm Marketplace path for the same thumbgate@latest runtime
• Perplexity Command Center — AI-search visibility + lead discovery
• ThumbGate Bench — Reliability benchmark and ProgramBench-style cleanroom proof lane
• Manus AI Skill — ThumbGate integration for Manus AI agents

---

Layer 4: Multi-Agent Distribution (the actual moat vs hand-rolled hooks)

Claude Code already ships permissions.deny and PreToolUse hooks. Cursor and Codex have their own. So why ThumbGate over a hand-written hook?

Two things hand-written hooks structurally cannot do:

1. Cross-agent propagation. A permissions.deny pattern lives in one agent's config and stays there. ThumbGate's checks distribute across every connected agent over MCP stdio — thumbs-down once in Cursor, the same pattern blocks on Claude Code, Codex, Gemini CLI, Cline, OpenCode, Amp in the next session, no copy-paste between configs.
2. Learning loop. A hand-written hook covers exactly the patterns you wrote. ThumbGate promotes every thumbs-down into a fresh rule, tunes existing rules' confidence weights from outcomes (Thompson Sampling, see Layer 2), and pulls semantically-near patterns into scope via local embeddings. The rule corpus sharpens without an operator hand-writing a regex for every new mistake shape.

Hand-rolled hooks are the right tool for a small, static denylist you maintain by hand. ThumbGate is the right tool when you want corrections from any agent to harden every agent automatically.

Prompt engineering still matters, but it is only the starting point. ThumbGate adds prompt evaluation on top: proof lanes, benchmarks, and self-heal checks tell you whether your prompt and workflow actually held up under execution instead of leaving you to guess from vibes. Run npx thumbgate eval --from-feedback --write-report=.thumbgate/prompt-eval-proof.md to turn real thumbs-up/down feedback into reusable eval cases and a buyer-ready proof report.

Install scope: machine-wide vs per-project

ThumbGate supports two install scopes. Pick once when you install — you can switch later by re-running with the other flag.

Both scopes write mcpServers.thumbgate + the PreToolUse / UserPromptSubmit / PostToolUse / SessionStart hooks; the only difference is where. Machine-wide is the right default for most developers. Switch to --project only when you have a reason to keep lessons from bleeding between repos.

Per-project lesson DBs live under each repo's .claude/memory/feedback/ and must stay gitignored — they're a runtime store, not source. ThumbGate's bundled .gitignore template handles this.

FAQ

Is ThumbGate a model fine-tuning tool? No. ThumbGate does not update model weights. It captures feedback, stores lessons, injects context at runtime, and blocks bad actions before they execute.

How is this different from CLAUDE.md or .cursorrules? Those are suggestions the agent can ignore. ThumbGate checks are enforced — they physically block the action before it runs. They also auto-generate from feedback instead of requiring manual writing.

Does it work with my agent? If it supports MCP or pre-action hooks, yes. Claude Code, Claude Desktop, Cursor, Codex, Gemini CLI, Amp, Cline, OpenCode all work out of the box.

Is it free? The free tier gives you 2 feedback captures/day, 10 total captures, and up to 3 active auto-promoted prevention rules — enough for solo devs to prove a blocked repeat before upgrading. MCP integrations ship free for every agent.

Pro ($19/mo or $149/yr) removes the rule cap and adds history-aware lesson recall, lesson search, and a personal dashboard. Enterprise (custom pricing, scoped after intake) adds a shared hosted lesson DB, org dashboard, and shared enforcement.

---