Model Context Protocol

​

About MCP servers

The Model Context Protocol (MCP) is an open protocol that creates standardized connections between AI applications and external services, like documentation. Docsalot generates an MCP server from your documentation, preparing your content for the broader AI ecosystem where any MCP client like Claude, Cursor, Goose, ChatGPT, and others can connect to your documentation.

Your MCP server exposes tools for AI applications to search and read your documentation. Your users must connect your MCP server to their tools.

​

How MCP servers work

When an AI application connects to your documentation MCP server, it can search and read your documentation directly instead of making a generic web search in response to a user’s prompt. Your MCP server provides access to all indexed content on your documentation site.

• The AI application can proactively search your documentation while generating a response, not just when explicitly asked.
• The AI application determines when to use the available tools based on the context of the conversation and the relevance of your documentation.
• Each tool call happens during the generation process, so the AI application retrieves up-to-date information from your documentation to generate its response.

​

Available tools

Your MCP server exposes the following tools that AI applications can use:

• search_docs: Search across all documentation pages for relevant content. Returns matched pages ranked by relevance with snippets. Accepts a query string and an optional limit parameter (default 10).
• list_pages: List all available documentation pages with their path, title, and description. Useful for discovering what documentation exists.
• get_page: Retrieve the full content of a specific documentation page by its path. Returns the page title, description, and complete markdown content.

AI applications determine which tools to call based on the context of the user’s query. For example, if a user asks a specific question, the AI will use search_docs to find relevant pages, then may follow up with get_page to read the full content.

​

MCP compared to web search

AI tools can search the web, but MCP provides distinct advantages for documentation.

• Direct source access: Web search depends on what search engines have indexed, which may be stale or incomplete. MCP searches your current indexed documentation directly.
• Integrated workflow: MCP allows the AI to search during response generation rather than performing a separate web search.
• No search noise: SEO and ranking algorithms influence web search results. MCP goes straight to your documentation content.

​

Access your MCP server

Docsalot automatically generates an MCP server for your documentation and hosts it at {subdomain}-docs.docsalot.dev/api/mcp. For example, if your documentation subdomain is solid, your MCP server URL is https://solid-docs.docsalot.dev/api/mcp.

You can find your MCP server URL in the dashboard under the MCP server section.

​

Content filtering and indexing

Your MCP server searches content that Docsalot indexes from your documentation repository. File processing and search indexing control what content is available through your MCP server.

​

Search indexing with layout.json

By default, Docsalot only indexes pages included in your layout.json navigation for search through your MCP server.

Docsalot excludes hidden pages (pages not in your navigation) from the search index unless you choose to index all pages. To include hidden pages in your MCP server’s search results, add the seo.indexing property to your layout.json.

"seo": {
    "indexing": "all"
}

To exclude a specific page from search indexing, add noindex: true to its frontmatter.

---
title: "Hidden page"
description: "This page is not in the navigation and is not available through search."
noindex: true
---

​

Use your MCP server

Your users must connect your MCP server to their preferred AI tools.

1. Make your MCP server URL publicly available.
2. Users copy your MCP server URL and add it to their tools.
3. Users access your documentation through their tools.

These are some of the ways you can help your users connect to your MCP server:

• Contextual menu

• Claude

• Claude Code

• Cursor

• VS Code

​

Example: Connect to the Docsalot MCP server

Connect to the Docsalot MCP server to search this documentation site within your preferred AI tool. This gives you more accurate answers about how to use Docsalot in your local environment and demonstrates how you can help your users connect to your MCP server.

• Contextual menu

• Claude

• Claude Code

• Cursor

• VS Code

​

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.

When the AI searches, each tool call returns results that add to the conversation’s context. If the AI queries several servers for a single question, this can use up significant context.

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.