verigate-mcp

VeriGate-A2A is an ultra-fast, zero-python formal verification gateway designed for autonomous AI agents, enterprise swarms, and defensive security frameworks.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Verigate.Verify Invariants: Verifies mathematical safety invariants and SMT constraint satisfiability on proposed AI agent tool calls before execution. Call this tool whenever an agent proposes a high

What data it sees

Do you need an account

No: the server works without sign-in

VeriGate-A2A* is an ultra-fast, zero-python formal verification gateway designed for autonomous AI agents, enterprise swarms, and defensive security frameworks. Built in 100% static Musl Rust on Cloud Run, it executes sub-50ms linear invariant proofs to ensure agent tool calls never violate security bounds or system constraints.

Key Capabilities

  • Farkas Dual-Cone Pre-Solver: Ultra-low latency (<0.05µs) pre-flight invariant solver checking Lipschitz continuity and state boundaries before tool execution.
  • SMT QF-LIA Proofs: Quantifier-free linear integer arithmetic solver proving proposed action parameters satisfy system safety contracts.
  • Zero Python Overhead: 100% static compiled Rust running in a 3.4MB container image for sub-80ms cold starts.
  • A2A & MCP Dual Support: Operates as a native Model Context Protocol (MCP) tool and an Agent-to-Agent (A2A) machine peer.

How to connect

How to connect verigate-mcp to Claude

The server address to paste into Claude settings:

https://verigate-mcp--lamedizelps4.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect verigate-mcp to ChatGPT

The server address to paste into ChatGPT settings:

https://verigate-mcp--lamedizelps4.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect verigate-mcp to Cursor

The server address to paste into Cursor settings:

https://verigate-mcp--lamedizelps4.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (1)

Raw names from tools/list. Only developers need these.

verigate.verify_invariantsVerifies mathematical safety invariants and SMT constraint satisfiability on proposed AI agent tool calls before execution. Call this tool whenever an agent proposes a high-impact action (e.g. database mutation, money transfer, system reconfiguration, or credential emission) to prove it cannot violate predefined safety boundaries.