Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.skale.space/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

The SKALE Documentation MCP server gives AI assistants and agents the ability to search and read SKALE documentation directly. It’s available at: 
https://docs.skale.space/mcp
No installation, npm packages, environment variables, or private keys needed. Just add the URL to any MCP-compatible client.

​
What Is MCP?

The Model Context Protocol (MCP) is an open standard that enables AI models to interact with external tools and data sources. The SKALE Docs MCP server exposes two tools:
  • Search — Search across all SKALE documentation to find relevant pages
  • Query docs filesystem — Read full page content, browse the doc structure, and extract specific sections
AI agents connected to this server can answer questions about SKALE with up-to-date documentation, without relying on training data or web search.

​
Connecting

​
Claude Desktop (claude.ai)

  1. Go to Settings → Connectors
  2. Select Add custom connector
  3. Enter:
    • Name: SKALE Docs
    • URL: https://docs.skale.space/mcp
  4. Select Add

​
Claude Code

claude mcp add --transport http "SKALE Docs" https://docs.skale.space/mcp
Verify the connection: 
claude mcp list

​
Cursor

  1. Open Cursor Settings → MCP (Cmd+Shift+P → “Open MCP settings”)
  2. Add a new MCP server:
{
  "mcpServers": {
    "SKALE Docs": {
      "url": "https://docs.skale.space/mcp"
    }
  }
}

​
VS Code

Create or edit .vscode/mcp.json in your project: 
{
  "servers": {
    "SKALE Docs": {
      "type": "http",
      "url": "https://docs.skale.space/mcp"
    }
  }
}

​
GitHub Copilot

GitHub Copilot can also connect to MCP servers. Add the server in your client settings or Copilot extensions configuration.

​
Other MCP Clients

Any MCP-compatible client can connect by adding a server with url set to https://docs.skale.space/mcp. See the client’s documentation for the exact configuration format.

​
What the MCP Server Provides

The MCP server indexes all public pages listed in the documentation navigation. When an AI agent connects, it can:
  • Answer questions about SKALE concepts, APIs, and SDKs
  • Find relevant cookbook recipes and tutorials
  • Provide accurate code examples from the docs
  • Reference chain information and configuration details

​
MCP Resources: Skill Files

The MCP server also exposes SKALE Skills as MCP resources. Agents connected to the server can discover and access skill files without installing them separately. Skills provide step-by-step instructions for building on SKALE — from setting up a chain to using programmable privacy.