{"type":"mcp_server","name":"keboola-mcp-server","description":"The Keboola MCP Server repository provides a Model Context Protocol server for interacting with Keboola Connection, enabling users to list and access data from the Keboola Storage API.","category":"Developer Tools","language":"Python","stars":84,"forks":3,"owner":"keboola","github_url":"https://github.com/keboola/keboola-mcp-server","homepage":null,"setup":"## Setup\n\n**Installation via Smithery:**\n\n```bash\nnpx -y @smithery/cli install keboola-mcp-server --client claude\n```\n\n**Manual Installation:**\n\n1.  Clone the repository: `git clone https://github.com/keboola/keboola-mcp-server.git`\n2.  Change directory: `cd keboola-mcp-server`\n3.  Create a virtual environment: `python3 -m venv .venv`\n4.  Activate the virtual environment: `source .venv/bin/activate`\n5.  Install the package in development mode: `pip3 install -e .`\n6.  Install development dependencies (optional): `pip3 install -e \".[dev]\"`\n\n**Claude Desktop Setup:**\n\n1.  Create or edit the Claude Desktop configuration file:\n    *   macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`\n    *   Windows: `%APPDATA%\\Claude\\claude_desktop_config.json`\n2.  Add the configuration to `claude_desktop_config.json` (adjust paths and credentials):\n\n```json\n{\n  \"mcpServers\": {\n    \"keboola\": {\n      \"command\": \"/path/to/keboola-mcp-server/.venv/bin/python\",\n      \"args\": [\n        \"-m\",\n        \"keboola_mcp_server\",\n        \"--api-url\",\n        \"https://connection.YOUR_REGION.keboola.com\"\n      ],\n      \"env\": {\n        \"KBC_STORAGE_TOKEN\": \"your-keboola-storage-token\",\n        \"PYTHONPATH\": \"/path/to/keboola-mcp-server/src\",\n        \"KBC_SNOWFLAKE_ACCOUNT\": \"your-snowflake-account\",\n        \"KBC_SNOWFLAKE_USER\": \"your-snowflake-user\",\n        \"KBC_SNOWFLAKE_PASSWORD\": \"your-snowflake-password\",\n        \"KBC_SNOWFLAKE_WAREHOUSE\": \"your-snowflake-warehouse\",\n        \"KBC_SNOWFLAKE_DATABASE\": \"your-snowflake-database\",\n        \"KBC_SNOWFLAKE_SCHEMA\": \"your-snowflake-schema\",\n        \"KBC_SNOWFLAKE_ROLE\": \"your-snowflake-role\"\n      }\n    }\n  }\n}\n```\n\n3.  Replace placeholders with actual values.\n4.  Quit and restart Claude Desktop.\n5.  Verify the server is connected by looking for the hammer icon.\n\n**Cursor AI Setup:**\n\n1.  Create or edit the Cursor AI configuration file: `~/.cursor/mcp.json`\n2.  Add one of the following configurations based on your preferred transport method:\n\n    *   **Option 1: Using Server-Sent Events (SSE)**\n\n```json\n{\n  \"mcpServers\": {\n    \"keboola\": {\n      \"url\": \"http://localhost:8000/sse?storage_token=YOUR_STORAGE_TOKEN&snowflake_account=YOUR_ACCOUNT&snowflake_user=YOUR_USER&snowflake_password=YOUR_PASSWORD&snowflake_database=YOUR_DATABASE&snowflake_schema=YOUR_SCHEMA&snowflake_warehouse=YOUR_WAREHOUSE\"\n    }\n  }\n}\n```\n\n    *   **Option 2: Using Standard I/O (stdio)**\n\n```json\n{\n  \"mcpServers\": {\n    \"keboola\": {\n      \"command\": \"/path/to/keboola-mcp-server/venv/bin/python\",\n      \"args\": [\n        \"-m\",\n        \"keboola_mcp_server\",\n        \"--transport\",\n        \"stdio\",\n         \"--api-url\",\n         \"https://connection.YOUR_REGION.keboola.com\"\n      ],\n      \"env\": {\n        \"KBC_STORAGE_TOKEN\": \"your-keboola-storage-token\",\n        \"KBC_SNOWFLAKE_ACCOUNT\": \"your-snowflake-account\",\n        \"KBC_SNOWFLAKE_USER\": \"your-snowflake-user\",\n        \"KBC_SNOWFLAKE_PASSWORD\": \"your-snowflake-password\",\n        \"KBC_SNOWFLAKE_DATABASE\": \"your-snowflake-database\",\n        \"KBC_SNOWFLAKE_SCHEMA\": \"your-snowflake-schema\",\n        \"KBC_SNOWFLAKE_WAREHOUSE\": \"your-snowflake-warehouse\"\n      }\n    }\n  }\n}\n```\n\n3.  Replace placeholders with actual values.\n4.  Restart Cursor AI.\n5.  If using SSE, start the MCP server.\n","tools":"## Available Tools\n\n1.  List buckets and tables (allows browsing data storage).\n2.  Get bucket and table information (provides metadata about data structures).\n3.  Preview table data (allows viewing sample data).\n4.  Export table data to CSV (enables data extraction).\n5.  List components and configurations (provides information about Keboola components).","faq":null,"created_at":"2025-01-12T20:01:21+00:00","updated_at":"2025-03-28T08:15:39+00:00","source_url":"https://model-context-protocol.com/servers/keboola-model-context-protocol-server-connection","related_articles":[]}