Neon Zero-Trust Gateway

io.github.AnsariiPublished by GitHub account Ansariiv1.0.1Updated Oct 24, 2026

Zero-Trust MCP gateway securing internal database tools behind an API key firewall.

VerifiedSSEWeb executableDatabasesKnowledge & MemorySecurity & Monitoring

Overview

AI-generated overview

A hosted zero-trust MCP gateway that lets an assistant run read-only SQL against internal Postgres databases and search internal Notion knowledge bases.

What you can do
Run remote SQL queries against internal Postgres databases, forced into read-only transaction blocks so tables cannot be dropped or data deleted. Search internal Notion wikis and documents. Route all MCP traffic through a hosted Python gateway with audit logging and routing.
When to use it
When you want an AI assistant to query an internal Postgres database or search internal Notion documentation without handing over root database credentials, and you are willing to buy a hosted API key.
Requirements
A remote SSE endpoint; no local package is declared. A purchased API key sent as an Authorization Bearer header, configured in the client (the README shows an npx client-cli invocation). Network access to the hosted gateway.
Before you install
Access is paid: an API key must be purchased before use. The key is a secret sent in the Authorization header and should not be shared. All queries and searches pass through a third-party hosted gateway, which logs traffic. Read-only enforcement is claimed by the provider and should be verified before trusting it with sensitive data.

Installation

In SourceWeft

  1. Open Neon Zero-Trust Gateway in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via SSE. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.Ansarii%2Fzero-trust-gateway/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "neon-zero-trust-gateway": {
      "type": "sse",
      "url": "https://api.neoninnovationlab.com/sse"
    }
  }
}

README

Neon Enterprise MCP Gateway

The Zero-Trust Firewall for Claude & AI Agents

Neon Gateway allows you to securely connect your Claude Desktop or custom AI agents to internal Enterprise databases (Postgres) and Knowledge Bases (Notion) without exposing root credentials or risking data destruction.

Features

  • Zero-Trust Postgres: Execute remote SQL queries forced into READ-ONLY transaction blocks. Agents cannot drop tables or delete data.
  • Notion Enterprise Search: Let Claude search your internal wikis and documents securely.
  • Audit Logging & Routing: All MCP traffic is routed through a secure Python Gateway.

Get Access

This is a hosted, premium MCP Gateway for Enterprise and Agency teams.

  1. Purchase an API Key here: https://neoninnovationlab.com/mcp
  2. You will receive an mcp_live_... key instantly via email.
  3. Configure your Claude Desktop using the instructions below.

Claude Desktop Configuration

Add the following to your claude_desktop_config.json:

json
{  "mcpServers": {    "neon-enterprise-gateway": {      "command": "npx",      "args": [        "-y",        "@modelcontextprotocol/client-cli",        "sse",        "--header",        "Authorization: Bearer YOUR_API_KEY_HERE",        "https://api.neoninnovationlab.com/sse"      ]    }  }}

Source: README.md at commit 493ec36

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declaredRequired10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.