Getting Started with MCP Server Documentation
Create your first MCP server documentation in NeoArc Studio. Walk through creating a server directory, configuring the server definition with transport and authentication, and adding tool, resource, and prompt definitions.
This guide walks you through creating MCP server documentation from scratch. By the end, you will have a documented MCP server with transport configuration, at least one tool with annotations, and a published reference that your team can browse.
Step 1: Create the MCP Server Directory
MCP servers are stored in the Integration Design section of your workspace, alongside REST APIs, GraphQL APIs, and other integration types.
Step 2: Configure the Server Definition
The server definition captures API-level settings that apply across all tools, resources, and prompts.
Step 3: Add Your First Tool
Tools are the most common MCP primitive. They define actions that the AI assistant can perform.
Step 4: Publish and Review
Once you have configured the server and added at least one tool, you can publish your documentation site to see how it renders.
Next Steps
Now that you have a basic MCP server documented, explore the more advanced guides.
Deep dive into MCP tool definitions: annotation flags, safety matrix, input/output schemas, error scenarios, result content types, related resources, and example patterns. Learn how to document tools that AI assistants can use safely and effectively.
Learn how to document MCP resources: concrete URIs, URI templates with parameters, content types, subscriptions, audience control, and metadata. Understand the difference between tools and resources and when to use each.
Configure MCP server connectivity: stdio for local processes and streamable HTTP for remote services. Set up OAuth 2.1 with PKCE and dynamic registration, API key authentication, bearer tokens, and environment variable credentials.