Typed SQLite entity storage with optional asynchronous Google Sheets projection for review and collaboration.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Spreadsheet DB.
Hikoutei provides a typed entity layer over local SQLite and can publish committed changes to Google Sheets asynchronously. Applications define entities with scalar properties such as strings, numbers, booleans, and primary keys, then use a request-local manager to create, update, query, and remove records.
The Spreadsheet DB MCP server uses SQLite as the application authority. Google Sheets is a secondary view for inspection, operational work, and lightweight collaboration. Normal application reads and writes stay local, so they do not wait for network calls to Sheets. The library also checks for unexpected column changes and duplicate headers, and it avoids silently replacing newer spreadsheet edits during conflicts.
A configured database file stores the entity data locally. Changes are committed to SQLite first, then placed into an asynchronous synchronization flow that projects them to Google Sheets. The documented flow includes an outbox, delivery handling, retries, deduplication, and conflict processing.
Edits made by people in the spreadsheet are brought back through polling. Accepted changes enter SQLite; conflicting changes are recorded instead of being silently overwritten. This arrangement keeps the application path independent from Sheets availability while retaining a human-readable operational view.
The design is intended for typed TypeScript applications. It sits above lower-level packages such as google-spreadsheet and @googleapis/sheets, rather than replacing their full spreadsheet APIs.
Install the package with its documented MikroORM dependencies:
Creating the local store does not require Google Cloud configuration. Initialize a database with createTypedSheets, provide a SQLite file path, and register entity definitions. Use a forked entity manager for request-local operations, then persist changes and call flush().
To enable Sheets projection, install the gcloud CLI and run npx hikoutei setup. The interactive command creates a Cloud project, service account, key, and spreadsheet, then writes environment configuration. Synchronization is enabled when HIKOUTEI_SYNC_SPREADSHEET_URL is present; without it, the setup remains local-only. The repository also points to separate guidance for credential pools, quotas, and manual configuration.
The Spreadsheet DB MCP serverβs documented capabilities include:
The Spreadsheet DB MCP server is not a raw Google Sheets wrapper, a replacement for PostgreSQL, or an authoritative spreadsheet database. Direct row and cell manipulation is limited compared with the underlying Google Sheets clients, and full Sheets API access remains the providerβs responsibility.
The supplied material describes a TypeScript library and does not specify an MCP transport, named MCP tools, or compatibility requirements for clients such as Cursor or Claude Desktop. Those details should be verified before treating the project as a conventional MCP server integration.
Factual signals from GitHub, npm, and our automated checks β not a rating.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/spreadsheet-db)<a href="https://allmcps.com/mcp/spreadsheet-db"><img src="https://allmcps.com/api/badge/spreadsheet-db?style=directory" alt="Spreadsheet DB on AllMCPs" /></a>