Skip to main content

​
About MCP Servers

The Model Context Protocol (MCP) is an open protocol that creates standardized connections between AI applications and external services, like documentation. Capa’s MCP server enables AI tools to search your documentation directly instead of making generic web searches, providing more accurate and up-to-date information about Capa’s API, features, and integration guides. When an AI tool has your documentation MCP server connected:
  • The AI can proactively search your documentation while generating a response, not just when explicitly asked
  • The AI determines when to use the search tool based on the context of the conversation and the relevance of your documentation
  • Each tool call happens during the generation process, so the AI searches up-to-date information from your documentation

​
Capa’s MCP Server

Capa automatically generates an MCP server for your documentation and hosts it at: MCP Server URL: https://docs.capa.fi/mcp This MCP server provides access to all indexed content on the Capa documentation site, including:
  • API references and endpoints
  • Integration guides and tutorials
  • Webhook documentation
  • Code examples and best practices

​
Connect to Your AI Tool

Your users must connect Capa’s MCP server to their preferred AI tools. Follow the instructions below for your specific tool.

​
Cursor

To connect Capa’s MCP server to Cursor:
  1. Open MCP settings
    1. Use Command + Shift + P (Ctrl + Shift + P on Windows) to open the command palette
    2. Search for “Open MCP settings”
    3. Select Add custom MCP. This opens the mcp.json file
  2. Configure the Capa MCP server In mcp.json, add:
    JSON
    {
  "mcpServers": {
    "Capa": {
      "url": "https://docs.capa.fi/mcp"
    }
  }
}
  3. Test the connection In Cursor’s chat, ask “What tools do you have available?” Cursor should show the Capa MCP server as an available tool.

​
VS Code

To connect Capa’s MCP server to VS Code:
  1. Create the configuration file
    1. Create a .vscode/mcp.json file in your workspace
  2. Configure the Capa MCP server In mcp.json, add:
    JSON
    {
  "servers": {
    "Capa": {
      "type": "http",
      "url": "https://docs.capa.fi/mcp"
    }
  }
}

​
Claude

To use Capa’s MCP server with Claude:
  1. Add the Capa MCP server to Claude
    1. Navigate to the Connectors page in the Claude settings
    2. Select Add custom connector
    3. Add the Capa MCP server:
      • Name: Capa
      • URL: https://docs.capa.fi/mcp
    4. Select Add
  2. Access the MCP server in your chat
    1. When using Claude, select the attachments button (the plus icon)
    2. Select the Capa MCP server
    3. Ask Claude a question about Capa

​
Claude Code

To use Capa’s MCP server with Claude Code, run the following command:
bash
claude mcp add --transport http Capa https://docs.capa.fi/mcp
Test the connection by running:
bash
claude mcp list

​
Using Multiple MCP Servers

Users can connect multiple MCP servers to their AI tools. Connected MCP servers do not consume context until the AI calls a search tool. The AI decides when to search based on query relevance, so it doesn’t search every connected server for every question. Best practices for using multiple MCP servers:
  • Connect only the MCP servers relevant to your current work
  • Be specific in your prompts so the AI searches the most relevant server
  • Disconnect servers you’re not actively using to reduce potential context usage
What’s Next