Claude MarketplacesSubmit
aderix avatar

Vantagate Mcp Server

aderix/vantagate-mcp-server

This adds a human approval layer before your AI agent executes high-risk operations. It exposes two MCP tools: create_vantagate_checkpoint pauses execution and sends a Slack or email notification to a human approver, while check_vantagate_status polls for the decision. The payload is encrypted, purged after approval or rejection, and every decision gets a cryptographic audit trail. Reach for this when your agent is about to delete database records, deploy to production, send bulk emails, or move money. Also ships as an OpenAPI spec if you want to wire it into GPTs, n8n, or LangChain instead of using MCP.

GitHub stars
1
tools
2
auth
Secret needed
transport
STDIO
env var
1
last updated
May 5, 2026
View on GitHub

Tools

2 tools

Public tool metadata for what this MCP can expose to an agent.

create_vantagate_checkpointPauses the agent workflow and routes a human approval request.

Pauses the agent workflow and routes a human approval request.

No parameter schema in public metadata yet.

check_vantagate_statusPolls the decision status of a pending checkpoint.

Polls the decision status of a pending checkpoint.

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Configuration

VANTA_API_KEY*secret

Your VantaGate API Key (Format: vg_123...)

Readme

VantaGate MCP Server & OpenAPI Integration

npm version License: MIT Node.js >= 20

Human-in-the-Loop authorization for AI Agents. VantaGate intercepts high-risk actions, routes them to a human approver via Slack or Email, and returns a cryptographically-signed decision - so your agent resumes or halts with a full audit trail.

What is VantaGate?

AI agents are increasingly capable of executing consequential real-world actions: sending emails to thousands of users, deleting database records, moving money, deploying to production. VantaGate is the trust layer that ensures humans remain in control.

View the full README on GitHub

Details

Repository
github.com/aderix/vantagate-mcp-server
Package
@vantagate/mcp-server
Transport
STDIO
Auth
Required
Registry
MCP registry, active