mcp-kibela
MCP server implementation for Kibela API integration
claude mcp add --transport stdio kiwamizamurai-mcp-kibela-server npx -y @kiwamizamurai/mcp-kibela-server \ --env KIBELA_TEAM="YOUR_TEAM_NAME" \ --env KIBELA_TOKEN="YOUR_TOKEN"
How to use
This MCP server implements Kibela API integration, allowing LLMs to browse and manipulate Kibela content through a set of GraphQL-backed tools. It supports searching notes, retrieving notes and their content, listing groups and folders, managing notes and user interactions (like/unlike), and fetching attachments and recent activity. By wiring this MCP server into your Cursor setup, you can issue structured commands (e.g., kibela_search_notes, kibela_get_my_notes, kibela_get_note_content, kibela_get_groups, kibela_get_group_folders, kibela_get_group_notes, kibela_get_folder_notes, kibela_get_users, kibela_like_note, kibela_unlike_note, kibela_get_recently_viewed_notes, kibela_get_note_from_path) and receive rich note data suitable for downstream reasoning and response generation.
How to install
Prerequisites:
- Node.js and npm installed on your machine.
- Access to the internet to fetch the MCP server package from npm.
Installation steps:
- Install dependencies and run via npx (as recommended in the README):
# Run the MCP server directly without local install
npx -y @kiwamizamurai/mcp-kibela-server
- Alternatively, install the package locally and run the server script if you prefer a local copy (adjust paths as needed):
npm install @kiwamizamurai/mcp-kibela-server
node node_modules/@kiwamizamurai/mcp-kibela-server/dist/src/index.js
- Configure environment variables for Kibela access when starting the server (KIBELA_TEAM and KIBELA_TOKEN are required):
export KIBELA_TEAM=YOUR_TEAM_NAME
export KIBELA_TOKEN=YOUR_TOKEN
- If using Docker, build and run the container as shown in the README, ensuring the same environment variables are exposed to the container.
Additional notes
Tips and considerations:
- Ensure your Kibela credentials (TEAM and TOKEN) are kept secure. Do not commit them to version control.
- If you switch between npx and docker deployments, update your mcp.json configuration accordingly to reflect the chosen command and environment.
- When using the docker approach, remember to expose the necessary environment variables (KIBELA_TEAM, KIBELA_TOKEN) to the container and consider using --rm for cleaner runs.
- For local development, you can inspect and test individual Kibela interfaces with the MCP inspector as documented in the README.
- If you encounter rate limits or API changes on Kibela, update the integration code accordingly, since this MCP server relies on Kibela's GraphQL introspection to function.
Related MCP Servers
inspector
Test & Debug MCP servers, ChatGPT apps, and MCP Apps (ext-apps)
mcp-framework
A framework for writing MCP (Model Context Protocol) servers in Typescript
mcp-sequentialthinking-tools
🧠 An adaptation of the MCP Sequential Thinking Server to guide tool usage. This server provides recommendations for which MCP tools would be most effective at each stage.
mcp-graphql
Model Context Protocol server for GraphQL
anytype
An MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.
mcp -typescript
DataForSEO API modelcontextprotocol server