gsheetmcp
Reads data from public Google Sheets without authentication, supporting filtering and retrieval of tabular data.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@gsheetmcp Sheet https://docs.google.com/spreadsheets/d/1zwblTR5DWzgOiVxsDYJJkP5Gcmi4OGiCtldI0nyxZGo/edit"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
gsheetmcp — Public Google Sheet MCP server
Generic MCP server for reading public Google Sheet data via the gviz endpoint — no API key, OAuth, or service account required.
Running
Default mode is stdio (for Claude Desktop / MCP Hub via uvx):
uvx gsheetmcpOr run locally (from source):
cd sheet-mcp-server
uv run server.pySSE mode
Set env MCP_TRANSPORT=sse for HTTP SSE transport:
MCP_TRANSPORT=sse uv run server.pyServer exposes SSE endpoint /sse + /messages on 0.0.0.0:8000. Configurable via:
Env | Default | Description |
|
|
|
|
| Host (SSE mode) |
|
| Port (SSE mode) |
Related MCP server: mcp-gsheet
Tool: get_sheet_data
Input
Param | Type | Required | Description |
|
| yes | Full Google Sheet URL (with or without |
|
| no | Column name to filter on (requires |
|
| no | Filter value ( |
Output
{
"sheet_id": "1p67eA4NGs389n-fuqHOmULhE5sfgRtFAulCHR8xcfGE",
"tab_gid": "1253624571",
"total_matched": 15,
"filtered": true,
"columns": ["Mã căn", "Tầng", "Diện tích", "Giá"],
"items": [
{ "Mã căn": "A-1201", "Tầng": "12", "Diện tích": "85", "Giá": "2.5 tỷ" }
]
}Error responses
Case | Response |
Invalid URL format |
|
Sheet not public |
|
| Returns full data + |
Empty tab |
|
Timeout / network error |
|
Examples
Sheet 1: FAQ (2 columns: Title, Description)
URL: https://docs.google.com/spreadsheets/d/1zwblTR5DWzgOiVxsDYJJkP5Gcmi4OGiCtldI0nyxZGo/edit?gid=0
Request:
{
"sheet_url": "https://docs.google.com/spreadsheets/d/1zwblTR5DWzgOiVxsDYJJkP5Gcmi4OGiCtldI0nyxZGo/edit?gid=0",
"filter_column": "Title",
"filter_value": "UI"
}Response:
{
"sheet_id": "1zwblTR5DWzgOiVxsDYJJkP5Gcmi4OGiCtldI0nyxZGo",
"tab_gid": "0",
"total_matched": 3,
"filtered": true,
"columns": ["Title", "Description"],
"items": [
{
"Title": "What's the difference between UI Kits and libraries",
"Description": "UI Kits are copy-and-pastable components..."
}
]
}Sheet 2: Inventory (completely different structure)
With a different sheet structure, columns and items adapt automatically — no column names leak between sheets.
Test cases
Public sheet + valid filter →
filtered: true, correct subsetPublic sheet, no filter →
filtered: false, all rowsBad
filter_column→ full data +warning: filter_column_not_foundPrivate sheet →
error: sheet_not_publicInvalid URL →
error: invalid_sheet_urlTwo sheets with different structures → columns/items adapt independently
MCP client config
stdio (recommended — default)
{
"mcpServers": {
"gsheetmcp": {
"command": "uvx",
"args": ["git+https://github.com/kientv/gsheetmcp.git"]
}
}
}Or with a local clone:
{
"mcpServers": {
"gsheetmcp": {
"command": "uv",
"args": ["run", "--directory", "/path/to/gsheetmcp", "server.py"]
}
}
}SSE (remote server)
When the server runs in SSE mode, configure the client with the endpoint URL:
{
"mcpServers": {
"gsheetmcp": {
"transport": "sse",
"url": "http://host:8000/sse"
}
}
}Limitations
gviz is an internal Google Sheets endpoint, not an official REST API — no SLA.
Works only with public sheets (Anyone with the link can view).
Each call reads 1 tab specified by
gid.No write, delete, or data modification support.
Large sheets may timeout (default 30s).
Available Tools
1 toolget_sheet_dataD
Inputs: sheet_url (required), filter_value, filter_column.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no ambiguity. The single tool is distinctly the only option.
The single tool uses clear snake_case naming, consistent with itself.
A single tool for a Google Sheets integration is far too few; typical operations require multiple tools (e.g., create, update, delete).
The server is severely incomplete, offering only a read operation (get_sheet_data) with no ability to modify or manage sheets.
Maintenance
Related MCP Connectors
Streamable HTTP MCP server for Google Calendar and Sheets with OAuth login.
Hosted Google Sheets MCP server, with each action switched on or off per account.
Hosted MCP server for GA4, Google Ads and Search Console. Google OAuth, nothing to install.
MCP server for Google search results via SERP API
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceMCP server for Google Sheets - read, write, and query spreadsheet data.643 npm2MIT
- AlicenseAqualityDmaintenanceMCP server for interacting with Google Sheets, providing tools to list sheets, read data from cell ranges, and write data to cell ranges.33MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for Google Sheets operations, enabling spreadsheet management including reading, writing, appending, creating, and searching sheets via natural language.MIT
- AlicenseNot gradedqualityCmaintenanceMCP server to read, write, create, and format Google Sheets via OAuth2 authentication, providing tools for spreadsheet management.540 npmMIT