MCP server

docs-builder includes an MCP (Model Context Protocol) server that allows AI assistants to interact with the documentation tooling directly.

The MCP server is deployed as an HTTP service and exposes all tools through a single endpoint.

Available tools

Tool	Description
`ResolveCrossLink`	Resolves a cross-link (like `docs-content://get-started/intro.md`) to its target URL and returns available anchors.
`ListRepositories`	Lists all repositories available in the cross-link index with their metadata.
`GetRepositoryLinks`	Gets all pages and their anchors published by a specific repository.
`FindCrossLinks`	Finds all cross-links between repositories. Can filter by source or target repository.
`ValidateCrossLinks`	Validates cross-links to a repository and reports any broken links.

These tools help authors create and evaluate documentation using the Elastic Docs content types.

Tool	Description
`ListContentTypes`	Lists all Elastic Docs content types with descriptions and guidance on when to use each.
`GenerateTemplate`	Generates a ready-to-use template for a specific content type (overview, how-to, tutorial, troubleshooting, or changelog). Optionally pre-fills title, description, and product.
`GetContentTypeGuidelines`	Returns detailed authoring and evaluation guidelines for a content type, including required elements, best practices, and anti-patterns.

Tool	Description
`SemanticSearch`	Performs semantic search across all Elastic documentation. Returns relevant documents with summaries, scores, and navigation context.
`FindRelatedDocs`	Finds documents related to a given topic or document. Useful for discovering related content and building context.

Tool	Description
`GetDocumentByUrl`	Gets a specific documentation page by its URL. Returns full document content including AI summaries and metadata.
`AnalyzeDocumentStructure`	Analyzes the structure of a documentation page. Returns heading count, links, parents, and AI enrichment status.

Tool	Description
`CheckCoherence`	Checks documentation coherence for a given topic by finding all related documents and analyzing their coverage.
`FindInconsistencies`	Finds potential inconsistencies in documentation by comparing documents about the same topic.

To use the docs-builder MCP server, add it to your IDE's MCP configuration.

Cursor

Create or edit .cursor/mcp.json in your workspace:

		{
  "mcpServers": {
    "elastic-docs": {
      "url": "https://www.elastic.co/docs/_mcp/"
    }
  }
}
		
	

Then restart Cursor or reload the window. The tools will be available in Agent mode.

Visual Studio Code

Create or edit .vscode/mcp.json in your workspace:

		{
  "servers": {
    "elastic-docs": {
      "type": "http",
      "url": "https://www.elastic.co/docs/_mcp/"
    }
  }
}
		
	

Requires GitHub Copilot with MCP support enabled.

You can test the MCP server using the MCP Inspector:

npx @modelcontextprotocol/inspector --url https://www.elastic.co/docs/_mcp/

This opens a web UI where you can browse all available tools and invoke them manually.