gsheetmcp
Reads data from public Google Sheets without authentication, supporting filtering and retrieval of tabular data.
Click on "Install 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., "@gsheetmcpSheet 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
| Name | Required | Description | Default |
|---|---|---|---|
| sheet_url | Yes | ||
| filter_value | No | ||
| filter_column | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
v0.1.0- First observed
get_sheet_data
TDQS
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
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Streamable HTTP MCP server for Google Calendar and Sheets with OAuth login.
MCP server for Google search results via SERP API
MCP server for querying and analyzing data from ad platforms, analytics tools, and spreadsheets
Query, join, profile, clean and convert CSV/JSON/Parquet with server-side DuckDB over MCP.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceMCP server for Google Sheets - read, write, and query spreadsheet data.1782MIT
- 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 gradedqualityBmaintenanceMCP 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.606MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/kientv/gsheetmcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server