📄️ MCP (Model Context Protocol)
MCP is a set of rules that helps AI models communicate and understand context better when working with different apps, tools, or systems.
📄️ MCP Connectors
MCP connectors are tools to connect to MCP servers. They provide full MCP protocol support including tools, resources, resource templates, and prompts.
📄️ MCP Virtual Server
An MCP Virtual Server is a reusable, persisted definition of an exposed MCP server. Instead of repeating the same settings on every route, you define them once as a virtual server and reference it from the exposition plugins (and from the preset) through server_ref.
📄️ MCP Virtual Server exposition
Otoroshi can expose tool functions and MCP connectors as an MCP server that external MCP clients connect to.
📄️ MCP Registry
Otoroshi can publish your governed MCP virtual servers to the standard MCP registry format, so that registry-aware MCP clients in your organization discover the sanctioned servers automatically — and connect through the gateway (so OAuth and the Zero-Trust controls apply end to end).
🗃️ MCP Connectors examples
15 items
📄️ Tutorial: OAuth-protected MCP server with geocoding tools
In this tutorial, you will build a complete, production-ready MCP server that exposes geocoding tools from the French national geocoding API (Géoplateforme IGN). All the exposition settings live on a reusable MCP Virtual Server, which the route references with serverref. The server is protected with OAuth 2.0 (the built-in enforceoauth option) and exposes the standard .well-known/oauth-protected-resource discovery document via the dedicated McpProtectedResourceMetadata plugin.