mcp-sheet-filler
Provides tools for reading, writing, and managing tabular data in Google Sheets, including creating sheets, defining field schemas, and auto-filling missing fields without overwriting existing data.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
mcp-sheet-filler
MCP server for storing and safely auto-filling tabular data. Provides tools for an AI agent to read objects, identify empty auto-fill fields, collect values, and write them back — without overwriting existing data.

Installation
npm install
npm run buildRelated MCP server: Structured-sh
Configuration
Environment Variables
Variable | Description | Default |
| Key field name for objects |
|
Google Sheets:
Variable | Description | Default |
| Google Sheet ID | — |
| Data sheet name |
|
| Fields schema sheet name |
|
| Service account JSON (string or file path) | — |
Google Sheets Setup
Create a Google Cloud project and enable the Google Sheets API
Create a service account and download the JSON key
Share your Google Sheet with the service account email (with Editor access)
Set
GOOGLE_SERVICE_ACCOUNT_KEYto the JSON content or file path
Sheet structure:
fieldssheet: columnsname,description,auto,instructions,type,exampledatasheet: first row is headers (field names), first column is the object key, each subsequent row is an object
Usage
With Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"sheet-filler": {
"command": "node",
"args": ["/path/to/mcp-sheet-filler/dist/index.js"],
"env": {
"GOOGLE_SHEET_ID": "your-google-sheet-id",
"GOOGLE_SERVICE_ACCOUNT_KEY": "/path/to/service-account.json"
}
}
}
}Development
npm run dev # Run with tsx
npm run build # Build TypeScript
npm start # Run built version
npm test # Run testsData Model
Fields
Schema for object fields, stored in fields table/sheet:
Column | Type | Description |
| string | Unique field name (required) |
| string | Field description |
| boolean | Auto-fill flag |
| string | Instructions for auto-filling |
| string | Data type for validation |
| string | Example value |
Objects
Data objects stored in data table/sheet. Each row is an object, each column is a field. Objects are identified by their key field (OBJECT_KEY_FIELD, default: name).
Supported Types
string(default)numberdate(ISO-8601:YYYY-MM-DD)datetime(ISO-8601)urlemailjsonenum:val1|val2|val3
Empty Value Rules
A value is considered empty if it is: null, undefined, empty string, or whitespace-only.
Values like 0, false, "0" are not empty.
MCP Tools
filler_init
Initialize the current spreadsheet by creating data and fields tabs with header rows. Errors if either tab already exists. No parameters required.
{}Returns { success, fieldsTab, dataTab, keyField }.
filler_list_fields
List all fields or a subset.
{ "names": ["field1", "field2"], "include_instructions": true }filler_add_fields
Add new fields (batch).
{
"fields": [
{
"name": "website",
"description": "Company website",
"auto": true,
"type": "url",
"instructions": "Find the official website"
}
]
}Returns { results: { [name]: { created: true } | { error: "..." } } }.
filler_get_objects_by_name
Get objects by their names (batch).
{ "names": ["Acme Corp", "Globex"] }Returns { objects: [{ found, object?, missing? } | { found: false, name }] }.
filler_add_objects_by_name
Create new objects (batch).
{ "names": ["Acme Corp", "Globex"] }Returns { results: { [name]: { created: true } | { error: "..." } } }.
filler_save_objects_no_overwrite
Save field values for multiple objects without overwriting non-empty fields.
{
"objects": [
{
"name": "Acme Corp",
"values": {
"website": "https://acme.com",
"founded": "1990"
}
}
]
}Returns status for each field per object:
saved— value was savedskipped_already_set— field already has a valuerejected_unknown_field— field not in schemarejected_invalid_type— value failed type validation
filler_get_next_missing_fields_objects
Get objects that have missing auto-fill fields (default limit 1).
{ "limit": 1, "include_field_meta": true, "skip_filled_fields": false }skip_filled_fields— whentrue, omits already-filled field values fromobject.values(returns{}), reducing response size for wide sheets
Returns { found, objects, count, remain } — use this to process objects one by one or in batches.
Workflow Example
Agent calls
filler_list_fieldsto understand the schemaAgent calls
filler_get_next_missing_fields_objectsto get objects with missing fieldsAgent collects values using instructions from field metadata
Agent calls
filler_save_objects_no_overwriteto save values safely
Error Codes
Code | Description |
| Storage backend not configured |
| Field with this name already exists |
| Field not found |
| Object with this name already exists |
| Object not found |
| Invalid argument provided |
| Storage operation failed |
Tested with
ChatGPT app (developer mode)
Claude connector (custom connector)
Cursor
Antigravity
VSCode
ClaudeClaw
telegram-functions-bot
License
ISC
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
An agent-native database over MCP: shared, validated, structured records in every AI chat.
Live data grids for AI agents. Push structured data; humans review, agents read back via MCP.
Teable is an AI spreadsheet for business that combines a familiar spreadsheet interface with a structured database. Its remote MCP server lets AI agents inspect project and table structure, read and update records, and access the Teable API through OAuth with existing project permissions. Website: [teable.ai](https://teable.ai)
Hosted MCP server for AI-driven data ops. Create apps, manage schemas, and CRUD structured data.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceAn MCP server that enables AI agents to read, create, and modify Google Spreadsheets through actions like editing cells and managing sheets. It features a specialized handoff protocol to synchronize tasks and state between different LLMs using a shared spreadsheet log.602 npmMIT

Structured-shofficial
AlicenseNot gradedqualityDmaintenanceMCP server providing managed persistent memory for AI agents. Read and write structured state across sessions, tools, and restarts at 1000+ requests per second, with no infrastructure to self-host or operate.2Apache 2.0- FlicenseNot gradedqualityDmaintenanceMCP server enabling AI agents to read, write, and manage Google Sheets, including sheet manipulation, row/column operations, dropdowns, checkboxes, and conditional formatting.-
- AlicenseNot gradedqualityDmaintenanceMCP server that turns Excel files into queryable databases, enabling AI agents to filter, aggregate, group, sort data and export results as new Excel files.2MIT