@IgorGanapolsky
Basic information
Agent governance for ThumbGate: 👍/👎 become Pre-Action Checks that flag repeat mistakes and hard-block the risky ones before code or systems change.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"thumbgate": {
"command": "npx",
"args": [
"thumbgate",
"init",
"#",
"auto-detects",
"your",
"agent,",
"wires",
"hooks,",
"30",
"seconds"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
ThumbGate is a local-first firewall for AI coding agents that runs in the PreToolUse hook. It hard-blocks catastrophic tool calls by default (secret exfiltration, destructive deletes, supply-chain attacks) and warns‑and‑logs all other risk classes, with optional strict enforcement. It works across Claude Code, Cursor, Codex, Gemini CLI, Amp, Cline, and OpenCode, and requires no server on the enforcement path.
Run npx thumbgate init to auto-detect your agent and wire the hooks (about 30 seconds). To create a prevention rule, use npx thumbgate capture down "Never run DROP on production tables". Discoverable slash-commands (/thumbgate-guard, /thumbgate-rules, etc.) are installed into the agent’s palette for browsing and invoking enforcement actions.
rm -rf, supply‑chain) by default.THUMBGATE_STRICT_ENFORCEMENT=1.BRAIN.md) gives each agent session persistent institutional memory./thumbgate-guard, /thumbgate-rules, etc.) for discoverable guardrails.rm -rf) and secret leaks without waiting for a review.ThumbGate is a pre‑action enforcement layer, not a post‑hoc dashboard. It blocks or warns before the tool call executes, preventing damage and token waste, while dashboards only report what already happened.
ThumbGate runs locally via `npx` and works with any MCP‑compatible agent. No server is required on the enforcement path. It operates in the PreToolUse hook on the developer’s machine.
All data — feedback, prevention rules, lessons — lives locally in the repository (e.g., `.thumbgate/`). There is no default cloud sync; enterprise plans offer an optional shared hosted lesson DB.
The free tier allows up to 2 feedback captures per day (10 total) and up to 3 active auto‑promoted prevention rules. Pro ($19/mo or $149/yr) removes these limits and adds the dashboard, DPO export, and history‑aware lessons.
Yes. It works across Claude Code, Cursor, Codex, Gemini CLI, Amp, Cline, and OpenCode. Enterprise plans add org‑wide shared lesson databases and enforcement rules.
Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,
Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from
Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Memlord is a remote MCP server available at https://app.memlord.com.
Comments