holdgate-proxy
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
HoldGate
Human approval for AI agent actions — self-hosted.
An agent wants to wire $12,000, delete a table, or send a customer email. HoldGate holds the call, pushes it to a person's phone, and runs it only if they say yes.
[ AI agent ]
↓ calls a tool
[ holdgate-proxy ] ── holds it ──→ [ backend ] ── push ──→ [ a person's phone ]
↓ only once approved ↓
[ the real tool runs ] ←───────────── approve / deny ───────────┘MIT licensed, no hosted service, no account. You run all of it.
Two ways to use it
As an MCP proxy — no code changes. Wrap any stdio MCP server in your client config and every tool call it exposes becomes gated:
"stripe": {
"command": "holdgate-proxy",
"args": ["--key", "hg_live_…", "--upstream", "npx -y @stripe/mcp --api-key=sk_live_…"]
}Nothing changes in anyone's repository. Remove the wrapper and the gate is gone.
As an SDK — for code an agent never touches. A server-side function calling Stripe directly never goes near MCP, so it needs a line:
const receipt = await holdGate.gatekeeper(
"refundCustomer",
[customerId, amountUsd],
refundCustomer,
);gatekeeper blocks, then calls your function only if a human approved. The
arguments are frozen server-side when the ticket opens, so an agent cannot get a
tap on $10 and then run $999,999.
Related MCP server: agent-firewall
What's in here
Package | |
holdgate-proxy | stdio MCP proxy. The main event. Published to npm. |
holdgate-sdk |
|
holdgate-backend | Next.js API + Postgres schema and migrations |
holdgate-dashboard | Next.js admin UI — rules, keys, audit log |
holdgate-mobile | Expo app — where approvals are answered |
Rules live in the backend: ALWAYS_ASK, AUTO_APPROVE, or THRESHOLD (ask only
above a number). A tool with no rule asks — the default is fail-closed, so a
newly wrapped tool is never silently permitted. If the backend is unreachable the
proxy refuses rather than allows.
Honest comparison
Several projects do this, and some will suit you better:
Anthropic's Remote Control, inside the Claude iOS and Android apps, is free, built in, and needs no setup. If you only use Claude Code, start there.
Pushary, ClawMetry, Agent Approve, Forge Remote — hosted, polished phone approval, nothing to run.
HumanLayer — approvals into Slack and email, where teams already decide.
HoldGate's reason to exist is that you host it. Your Postgres, your audit trail, no third party holding a log of what your agents tried to do. If that doesn't matter to you, one of the above is less work.
Running it yourself
Needs a Supabase project (or any Postgres) and an Expo account for push.
cd holdgate-backend
cp .env.example .env.local # SUPABASE_URL, keys
supabase db push # migrations 0001–0007
yarn install && yarn devThen the dashboard for rules and API keys, and the mobile app for whoever approves. Each directory has its own README.
Status
Working and tested end to end: an MCP tool call held, pushed to a physical phone, approved, and forwarded to the real server — plus the refusal paths (denied, expired, backend unreachable), each verified to leave the tool unrun.
Rough edges worth knowing: only stdio MCP servers are proxied (not HTTP/SSE), and the config lives in a file the developer controls, so this is a guardrail, not a sandbox — anyone who can edit the MCP config can remove the wrapper. The way to make it enforceable is to let the proxy hold the upstream's credentials, so bypassing it loses access to the tools rather than just skipping approval.
License
MIT.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Guard wraps stdio MCP servers: risky calls wait for a person; no answer, no run. Remote: cooperative
Set up human approval for your AI agents' tool calls.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Let AI agents ask a real person for a decision on their phone and wait for the answer.
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides a human-approval tool for MCP-compatible agents, pausing execution until a human approves or edits the action, with every decision logged.210 npm2MIT
- AlicenseNot gradedqualityBmaintenanceSits in front of any MCP server to enforce allow/ask/block policies on tool calls, paths, shell commands, and network domains, with local approval prompts and an audit log.MIT
- AlicenseNot gradedqualityCmaintenanceProvides an MCP stdio interface for AI agents to propose tool calls that are validated against task policy, held for human approval when required, executed in a sandboxed Linux environment, and recorded in an audit log.MIT
- AlicenseAqualityBmaintenanceExperimental Python MCP server exposing traceguard_shield_exec to evaluate proposed tool calls through an authorization hook. Returns approval or rejection messages over stdio; it does not execute the requested tools.1MIT