A gateway for MCP servers with Repello ARGUS integration
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"repello-mcp-gateway","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Repello MCP Gateway with ARGUS Integration The Repello MCP Gateway is an advanced intermediary solution for Model Context Protocol (MCP) servers, architected to integrate directly with **Repello's ARGUS API**. It centralizes your AI infrastructure and secures it by analyzing every request and response. The Gateway acts as an intermediary between your development environment (like Cursor or Claude Desktop) and other MCP servers. It: 1. Reads server configurations from an `mcp.json` file. 2. Manages the lifecycle of these configured MCP servers. 3. Intercepts all tool calls and responses. 4. Sends the content of each request and response to the **Repello ARGUS API** for real-time analysis. 5. Provides a unified interface for discovering and interacting with all proxied MCPs. ## Installation ### Python (recommended) Install the repello-mcp-gateway package: ```bash pip install repello-mcp-gateway ``` ## How It Works The Gateway requires credentials for the Repello ARGUS API to function. You must provide a **Tracking ID** and an **API Key** via command-line arguments at startup. When a tool is called (e.g., from an editor like Cursor), the Gateway intercepts the call. Before forwarding it to the downstream MCP server (like a filesystem server), it sends the request payload to `https://argusapi.repello.ai/analyze-prompt`. If the API approves the request, it's sent to the tool. When the tool returns a result, the Gateway intercepts the response. It sends this response to `https://argusapi.repello.ai/analyze-response`. If the API approves, the final result is sent back to the client application. If the ARGUS API detects a threat in either the request or response, it will return an error, and the Gateway will block the action, raising an `AnalysisError`. ## Usage You must start the gateway with your `mcp.json` path, a valid tracking ID, and an API key. ```bash repello-mcp-gateway --mcp-json-path ~/.cursor/mcp.json --tracking-id <your-tracking-id> --api…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.