database-updater

The database-updater MCP server exposes tools for updating databases from CSV or Excel files and for creating notes to document those updates. The primary tool, update_database, accepts a file path to a CSV or Excel file, a target database type (such as PostgreSQL, MySQL, MongoDB, or SQLite), a connection string for the database, and the target table name. It then updates the specified table with data from the file, applying the appropriate type mappings and supporting multiple database dialects. The create_note tool lets you store and manage notes related to database updates, enabling you to document changes, rationale, and any issues observed during the update process. The server is designed to be used via MCP clients that can invoke these tools with the appropriate JSON payloads and to work with Claude Desktop as described in the repository’s installation notes.

Prerequisites:

• Node.js (v14+ recommended) and npm
• Access to the project repository and its source code

Step-by-step installation:

1. Install dependencies

   npm install
   

2. Build the server

   npm run build
   

3. (Optional) Run in watch mode for development with auto-rebuild

   npm run watch
   

4. Verify the build
   • Ensure the built server artifact exists at the path referenced in your MCP config (e.g., build/index.js)
5. Configure MCP integration
   • Ensure your MCP client or Claude Desktop is configured to point to the server via the mcp_config entry and environment as needed

Notes:

• The server supports updating PostgreSQL, MySQL, MongoDB, and SQLite databases from CSV or Excel files (.xlsx, .xls).
• You can customize connection settings and table mappings as part of the update_database payload.

Tips and caveats:

• Debugging MCP servers runs through stdio; if you encounter issues, use the MCP Inspector tooling referenced in the repository to inspect communications.
• When using Excel files, ensure the sheet contains a header row that maps to your database table columns for reliable updates.
• For sensitive connection strings, consider using environment variables or secret storage where supported by your runtime environment.
• If you run into schema mismatches, verify column data types and potential constraints (NOT NULL, unique keys) in the target table.
• The create_note tool is useful for traceability; include timestamps, user identifiers, and change descriptions to maintain a clean update history.