# MCP Hub & Observability Gateway (`neon_innovation_lab/mcp-hub-gateway`) Actor

Enterprise API Gateway for the Model Context Protocol. Route, authenticate, and log AI tool executions across multiple downstream MCP servers.

- **URL**: https://apify.com/neon\_innovation\_lab/mcp-hub-gateway.md
- **Developed by:** [Neon Innovation Lab](https://apify.com/neon_innovation_lab) (community)
- **Categories:**
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $5.00 / 1,000 tool routing & telemetries

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## 🌐 MCP Hub & Observability Gateway

An Enterprise API Gateway for the **Model Context Protocol (MCP)**.
This Actor acts as a centralized routing and observability layer for your AI agent swarms. Instead of connecting Claude or your AI clients directly to dozens of scattered backend MCP servers, you connect them to this single Hub.
The Hub transparently aggregates all tools, routes execution requests to the correct downstream servers, and logs every single interaction to a PostgreSQL database for full auditability.

### ✨ Core Features

- **Single Unified Endpoint:** Expose a single Apify Standby URL to your AI clients while routing traffic to multiple backend servers simultaneously.
- **Complete Observability:** Every `call_tool` execution is intercepted and logged directly to your Supabase PostgreSQL database.
- **Latency Tracking:** Automatically measures downstream server execution times (`latency_ms`) to detect bottlenecks.
- **Zero-Config SSL:** Native Apify Standby integration provides secure `https://` and `sse://` connections instantly—no domains or Nginx proxies required.

### 🚀 How to Connect (For AI Clients)

To connect Claude Desktop (or any other MCP-compatible client) to the Gateway, add the following to your `claude_desktop_config.json`:

````json
{
  "mcpServers": {
    "mcp-hub-gateway": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/inspector",
        "https://YOUR_ACTOR_NAME.apify.actor/sse?token=YOUR_API_TOKEN"
      ]
    }
  }
}
🛠 Operator Configuration
When running this Actor, the Operator must provide the following inputs:

DOWNSTREAM_URLS: A comma-separated list of the backend MCP Standby URLs you want to aggregate (e.g., https://backend1.apify.actor/sse, https://backend2.apify.actor/sse).
SUPABASE_URL: Your Supabase project URL (http://...:54321).
SUPABASE_SERVICE_ROLE_KEY: Your Supabase JWT Service Key.
📊 Telemetry Data Logged
The Hub automatically writes the following telemetry data to your hub_logs table for every tool execution:

agent_id: The identifier of the calling AI client.
tool_name: The exact tool that was executed.
request_payload: The JSON arguments sent to the tool.
response_payload: The JSON result returned by the downstream server.
latency_ms: Execution time in milliseconds.
status: success or error.
error_message: Full stack trace if the downstream server fails.

# Actor input Schema

## `DOWNSTREAM_URLS` (type: `string`):

Comma-separated list of downstream MCP Standby URLs to route to.
## `SUPABASE_URL` (type: `string`):

Your Supabase project URL for logging.
## `SUPABASE_SERVICE_ROLE_KEY` (type: `string`):

Your Supabase JWT service role key.

## Actor input object example

```json
{}
````

# Actor output Schema

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("neon_innovation_lab/mcp-hub-gateway").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("neon_innovation_lab/mcp-hub-gateway").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call neon_innovation_lab/mcp-hub-gateway --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,neon_innovation_lab/mcp-hub-gateway"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/TCPifcBeT4mYUDkCp/builds/4W4NwWqHOk3QckPTs/openapi.json