Skip to content
English
moinAI
  • There are no suggestions because the search field is empty.

moinAI MCP server: Connecting the knowledge base to external AI tools

moinAI MCP Server as an interface for the efficient use and management of corporate knowledge in third-party systems

The Model Context Protocol (MCP) is a universal interface for connecting AI models to external data sources. The moinAI MCP Server seamlessly links the moinAI knowledge base with external AI applications. This enables the knowledge base to be used and managed directly within other AI environments, thereby eliminating the need for custom interface programming.

  1. Functionality

  2. Application scenarios

  3. Commands and tools

  4. Set up the moinAI MCP server

  5. Best practices

 

1. Functionality

The moinAI MCP Server acts as a bridge between the moinAI platform and external AI infrastructures. This integration enables knowledge content to be retrieved and managed automatically. This facilitates the dynamic integration of corporate knowledge into external workflows, as well as the efficient automation of content maintenance.

Benefits of using the MCP Server

  • Centralised knowledge management: External AI applications always access the latest version of the moinAI knowledge database, ensuring the consistency of information.

  • Efficient control: Content can be created, updated or deleted directly from the external working environment without having to switch between different tools.

  • Workflow automation: Thanks to standardised access, knowledge queries can be integrated directly into automated processes.

 

2. Application scenarios

Using these tools enables the efficient management and utilisation of knowledge across system boundaries:

  • Centralised knowledge management (queryKnowledgebase): When working on complex tasks in an external AI environment, this tool serves to integrate the moinAI knowledge base as a verified data source (‘single source of truth’).

  • Automated knowledge expansion (createArticle): New insights or generated texts can be saved directly as drafts in the moinAI knowledge database without manual effort, which speeds up the editorial process.

  • Efficient quality assurance (retrieveArticles & updateArticle): By retrieving groups of articles, content can be systematically checked. Corrections or adjustments to terminology can be made directly via the interface for multiple articles simultaneously.

  • Lifecycle management (deleteArticle): Outdated information or time-limited campaign content can be automatically removed to keep the knowledge base up to date.

Deletions via the deleteArticle tool are permanent. No additional security prompt is issued within the hub, as the command is authorised directly via the interface. Working with interfaces therefore requires particular care when handling access credentials and data integrity.

Bildschirmfoto 2026-05-07 um 16.25.38

 

3. Commands and Tools

Prerequisites

  • An installed version of Node.js on the local system

  • A compatible MCP host (e.g. Claude Desktop, Cursor or your own LLM environment)

Various actions can be executed directly via prompt or through automated commands via the interface.

Tool Description
queryKnowledgebase Searches the moinAI knowledge base for relevant content.
createArticle Creates a new article directly in the moinAI knowledge base.
retrieveArticles Retrieves existing articles based on filter criteria.
updateArticle Updates existing content within the knowledge base.
deleteArticle Permanently removes articles from the moinAI environment.

 

4. Set up the moinAI MCP server

The connection is established via the moinAI Hub and by configuring the relevant MCP host.

  1. Access the API key in the Hub under Bot Settings → API Settings. Clicking the Generate API Key button creates a new key, which should be copied. If necessary, or if misuse is suspected, a new key can be generated using the Regenerate API Key button. API keys are permanently deleted via the bin icon.


  2. Within the settings of the external AI application, the moinAI MCP Server is added using the npx command. The API key copied earlier must be set as an environment variable (MOIN_AI_API_KEY).
    Important: A current version of Node.js must be installed on the target system.

  3. Once the configuration has been saved, access to the knowledge base within the external application is active.

Detailed technical specifications and examples of integration into various environments are available in the official documentation on GitHub.

The API key grants extensive access to the knowledge base. It must never be shared publicly (e.g. in public repositories). If misuse is suspected, the key should be immediately and irrevocably deleted in the Hub under Bot Settings → API Settings and regenerated. Upon deletion, all services using this key will immediately cease to function.

 

5. Best practices

To ensure the highest possible quality and security when using the moinAI MCP Server, we recommend adhering to the following guidelines.

  • Unique article titles: When automatically generating articles using createArticle, care should be taken to ensure titles are concise and unique. This makes it easier for both human editors and the AI to locate articles later on.

  • Regular audits: Using retrieveArticles in combination with external scripts enables regular checks of the knowledge base for outdated terms or expired offers.

  • Use test environments: Before applying automated deletion or update processes to the entire knowledge base, the functionality should be verified using individual test articles.