Kibela MCP Server Integration

What does “Kibela” MCP Server do?

The Kibela MCP Server is an implementation of the Model Context Protocol (MCP) designed to integrate with the Kibela API. By acting as a bridge between AI assistants and Kibela, it enables seamless access to external data, content, and services housed within Kibela workspaces. This integration allows AI agents to query, retrieve, and interact with documents and knowledge bases stored in Kibela, enhancing development workflows by automating tasks such as document search, information extraction, and collaboration. The Kibela MCP Server empowers developers and teams to leverage Large Language Models (LLMs) with up-to-date organizational knowledge, enabling efficient codebase exploration, knowledge management, and workflow automation through standardized MCP tools and resources.

List of Prompts

No prompt templates are mentioned or defined in the available documentation or repository files.

List of Resources

No explicit resources are listed in the available documentation or repository files.

List of Tools

No explicit tools are listed in the available documentation or repository files such as server.py (the repo is implemented in TypeScript/Node.js, and there is no direct mapping to a server.py).

Use Cases of this MCP Server

• Knowledge Management Automation: Integrate Kibela’s knowledge base with LLMs to automate the retrieval and summarization of organizational documentation.
• Document Search and Query: Enable AI assistants to find, extract, and surface relevant information from Kibela for users, improving research and onboarding workflows.
• Workflow Automation: Automate repetitive documentation-related tasks, such as updating records or generating reports from Kibela content.
• Collaboration Enhancement: Facilitate AI-powered collaboration by allowing agents to suggest content, tag documents, or notify team members based on Kibela activity.

How to set it up

Windsurf

1. Ensure Node.js is installed on your system.

2. Locate the Windsurf configuration file (typically windsurf.config.json).

3. Add the Kibela MCP Server package:
   @kiwamizamurai/mcp-kibela-server@latest

4. Insert the MCP server configuration under the mcpServers object:

   {
     "mcpServers": {
       "kibela": {
         "command": "npx",
         "args": ["@kiwamizamurai/mcp-kibela-server@latest"]
       }
     }
   }
   

5. Save and restart Windsurf.

6. Verify the server appears in the MCP server list.

Claude

1. Install Node.js if not already present.

2. Find and open Claude’s configuration file.

3. Add Kibela MCP Server as follows:

   {
     "mcpServers": {
       "kibela": {
         "command": "npx",
         "args": ["@kiwamizamurai/mcp-kibela-server@latest"]
       }
     }
   }
   

4. Restart Claude.

5. Confirm the integration by checking available MCP endpoints.

Cursor

1. Install Node.js.

2. Edit cursor.config.json or the relevant MCP config file.

3. Add the following snippet:

   {
     "mcpServers": {
       "kibela": {
         "command": "npx",
         "args": ["@kiwamizamurai/mcp-kibela-server@latest"]
       }
     }
   }
   

4. Save and restart Cursor.

5. Test by initiating a Kibela-related query.

Cline

1. Make sure Node.js is installed.

2. Access the Cline MCP configuration file.

3. Add the Kibela server entry:

   {
     "mcpServers": {
       "kibela": {
         "command": "npx",
         "args": ["@kiwamizamurai/mcp-kibela-server@latest"]
       }
     }
   }
   

4. Save your changes and restart Cline.

5. Check that the Kibela MCP Server is running.

Securing API Keys

To secure your Kibela API keys, use environment variables. Here’s an example configuration:

{
  "mcpServers": {
    "kibela": {
      "command": "npx",
      "args": ["@kiwamizamurai/mcp-kibela-server@latest"],
      "env": {
        "KIBELA_API_KEY": "${KIBELA_API_KEY}"
      },
      "inputs": {
        "workspace": "your_workspace_name"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "kibela": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “kibela” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Between these tables:
The Kibela MCP Server provides basic documentation, a clear license, and setup instructions for major platforms. However, it lacks explicit lists of tools, resources, and prompt templates in the public documentation, which limits its out-of-the-box agentic utility. If these were added, its value would increase. As it stands, it’s suitable for basic Kibela integration but not for advanced or highly configurable MCP workflows.

MCP Score