ai-docs-mcp

LaserFocused-ee/ai-docs-mcp

3.2

If you are the rightful owner of ai-docs-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

Knowledge Hub is a Model Context Protocol (MCP) server that provides AI assistants with unified access to organizational knowledge across multiple platforms.

Tools

Functions exposed to the LLM to take actions

legacy-list-docs

List all available documentation files in the system

legacy-read-doc

Read a specific documentation file by category and name

guru-list-cards

List and search Guru cards with optional filters

guru-read-card

Read the full content of a specific Guru card by ID

guru-get-card-attachments

List and optionally download attachments from a Guru card

list-database-pages

Query and search documentation pages in the Notion database. Supports advanced filtering by search terms, categories, tags, status, and flexible sorting. Perfect for AI agents to find relevant documentation based on current context.

create-page-from-markdown

Create a new documentation page in Notion from markdown content or a markdown file. Automatically converts markdown syntax to Notion blocks and sets proper metadata. Choose either markdown content OR filePath, not both.

update-page

Update an existing Notion page's content and/or metadata. Can replace entire page content with new markdown or just update metadata properties. Content updates create a new page and archive the old one to preserve history.

archive-page

Archive (soft delete) a Notion page by moving it to trash. The page will be removed from the database and no longer visible in listings. Use this to remove outdated or incorrect documentation. Cannot be undone via API.

export-page-to-markdown

Export a Notion page to clean markdown format. Converts all Notion blocks back to standard markdown syntax. Uses optimized parallel block fetching for improved performance.

hello

A simple hello world example tool

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources