Uses Google Cloud Platform for API authentication and authorization, supporting both OAuth 2.0 and API key authentication methods for accessing Google Sheets.
Enables discovery and listing of Google Spreadsheets stored in Google Drive through Drive API metadata access.
Provides tools for reading and interacting with Google Sheets data, including listing spreadsheets, searching by name, reading sheet data from specific ranges, retrieving metadata, listing sheets/tabs, and searching content within sheets.
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., "@Google Sheets MCP Server show me the sales data from Q3 in the quarterly report spreadsheet"
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.
A Model Context Protocol (MCP) server that provides tools for reading and interacting with Google Sheets data. This server enables AI assistants like Claude Desktop to seamlessly access, search, and analyze Google Spreadsheets.
Built with uv for fast and reliable dependency management.
📋 List Spreadsheets: Discover all accessible Google Spreadsheets
🔍 Search by Name: Find spreadsheets by name (exact or partial match)
📊 Read Sheet Data: Extract data from specific ranges or entire sheets
📝 Sheet Metadata: Get detailed information about spreadsheet structure
📑 List Sheets/Tabs: View all sheets within a spreadsheet
🔎 Search Content: Find specific data within sheets
🎯 Range Data: Get formatted data from specific cell ranges
🔐 Dual Authentication: Supports both OAuth 2.0 (private sheets) and API key (public sheets)
Related MCP server: Google Sheets MCP Server
Python 3.8+
uv package manager
Google Cloud Project with Sheets API enabled
Claude Desktop or other MCP-compatible client
This project uses uv for fast and reliable dependency management:
# Install dependencies using uv
uv sync
# Or if you don't have uv installed yet:
pip install uv
uv syncNote: All dependencies are managed through pyproject.toml and uv.lock files.
Create Google Cloud Project:
Go to Google Cloud Console
Create a new project or select existing one
Enable Google Sheets API and Google Drive API
Create OAuth 2.0 Credentials:
Go to "Credentials" → "Create Credentials" → "OAuth 2.0 Client ID"
Choose "Desktop application"
Download the credentials.json file
Place it in the project root directory
Generate Authentication Token:
# Run the token generation script using uv
uv run token_gen.pyA browser window will open for Google authentication
Grant necessary permissions
This will create token.json file for future use
Environment Setup (Optional):
# Create .env file if you want to use API key fallback
echo "SHEET_API_KEY=your_api_key_here" > .envCreate API Key:
Go to Google Cloud Console
Enable Google Sheets API
Go to "Credentials" → "Create Credentials" → "API Key"
Copy the API key
Environment Configuration:
# Create .env file
echo "SHEET_API_KEY=your_api_key_here" > .envNote: API key authentication only works with publicly shared spreadsheets.
Important: You must generate the authentication token before adding the MCP server to Claude Desktop.
Generate Token First:
uv run token_gen.pyComplete the OAuth flow in your browser.
Then Run Server:
uv run main.pyOnly after completing token generation, add to your Claude Desktop configuration:
{
"mcpServers": {
"sheet-mcp-server": {
"command": "uv",
"args": [
"--directory",
"C:\\path\\to\\your\\SheetMCP",
"run",
"main.py"
]
}
}
}Replace C:\\path\\to\\your\\SheetMCP with your actual project directory path.
Lists all Google Spreadsheets accessible to the authenticated user.
{
"name": "list_spreadsheets",
"arguments": {
"limit": 20,
"order_by": "modifiedTime desc"
}
}Find spreadsheets by name with exact or partial matching.
{
"name": "search_spreadsheets_by_name",
"arguments": {
"name": "Sales Report",
"exact_match": false
}
}Extract data from a specific range or entire sheet.
{
"name": "read_sheet_data",
"arguments": {
"spreadsheet_id": "1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms",
"range": "Sheet1!A1:C10"
}
}Retrieve detailed information about a spreadsheet.
{
"name": "get_sheet_metadata",
"arguments": {
"spreadsheet_id": "1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms"
}
}Get all sheet/tab names within a spreadsheet.
{
"name": "list_sheets",
"arguments": {
"spreadsheet_id": "1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms"
}
}Find specific content within a sheet.
{
"name": "search_sheet_data",
"arguments": {
"spreadsheet_id": "1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms",
"search_term": "Revenue",
"sheet_name": "Q4 Data"
}
}Extract data with specific formatting options.
{
"name": "get_range_data",
"arguments": {
"spreadsheet_id": "1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms",
"range": "Sheet1!A1:E20",
"value_render_option": "FORMATTED_VALUE"
}
}The server uses these Google API scopes:
https://www.googleapis.com/auth/spreadsheets.readonly - Read spreadsheet content
https://www.googleapis.com/auth/drive.metadata.readonly - List and discover spreadsheets
SheetMCP/
├── main.py # Main MCP server implementation
├── token_gen.py # OAuth token generation script
├── pyproject.toml # Project configuration and dependencies
├── uv.lock # Locked dependency versions
├── requirements.txt # Legacy pip requirements (optional)
├── .env # Your environment variables (optional)
├── credentials.json # OAuth credentials (download from Google)
├── token.json # Generated OAuth tokens (created by token_gen.py)
└── README.md # This fileCreate a .env file with:
# For API key authentication (public sheets only) - Optional fallback
SHEET_API_KEY=your_api_key_here
# Server Configuration
SERVER_NAME=google-sheets-mcp-server
SERVER_VERSION=1.0.0
LOG_LEVEL=INFONote: The .env file is optional. OAuth authentication via token_gen.py is the primary method.
OAuth Browser Doesn't Open:
Check firewall settings
Ensure Python has internet access
Try running authentication manually first
Permission Denied Errors:
Verify spreadsheet is accessible with your Google account
Check if spreadsheet is shared appropriately
Ensure correct API scopes are enabled
API Key Limitations:
API keys only work with public spreadsheets
Use OAuth 2.0 for private spreadsheets
Verify spreadsheet sharing settings
Token Expiration:
Delete token.json to force re-authentication
Run uv run token_gen.py again to regenerate
Check if refresh token is still valid
uv Installation Issues:
Install uv: curl -LsSf https://astral.sh/uv/install.sh | sh (Unix) or powershell -c "irm https://astral.sh/uv/install.ps1 | iex" (Windows)
Or use pip: pip install uv
Verify installation: uv --version
Recommended workflow to avoid OAuth interruption during use:
# Step 1: Install dependencies
uv sync
# Step 2: Generate authentication token first
uv run token_gen.py
# Step 3: Then start the MCP server or add to Claude Desktop
uv run main.pyThis ensures authentication is completed before Claude Desktop tries to use the server.
User: "List my Google Spreadsheets"
Claude: Uses list_spreadsheets tool to show available spreadsheets
User: "Find spreadsheets with 'Budget' in the name"
Claude: Uses search_spreadsheets_by_name tool with name="Budget"
User: "Read data from the Sales Q4 spreadsheet, range A1:E20"
Claude: Uses search + read_sheet_data tools to find and extract data
User: "What sheets are in this spreadsheet?"
Claude: Uses list_sheets tool to show all tabs/sheetsFork the repository
Create a feature branch
Make your changes
Add tests if applicable
Submit a pull request
This project is licensed under the MIT License - see the LICENSE file for details.
Keep your credentials.json and token.json files secure
Never commit authentication files to version control
Use environment variables for API keys
Regularly review and rotate credentials
Follow the principle of least privilege for API scopes
Get data from a specific range with formatting options
| Name | Required | Description | Default |
|---|---|---|---|
| spreadsheet_id | Yes | The ID of the Google Spreadsheet | |
| range | Yes | The range to read (e.g., 'Sheet1!A1:C10') | |
| value_render_option | No | How to render values | FORMATTED_VALUE |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'formatting options' but does not cover critical aspects such as whether this is a read-only operation, potential rate limits, authentication needs, error handling, or what the output looks like (e.g., data format, pagination). This leaves significant gaps for a tool that interacts with external data.
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?
The description is a single, efficient sentence that front-loads the core purpose ('Get data from a specific range') and adds a relevant detail ('with formatting options'). There is no wasted verbiage, though it could be slightly more structured by explicitly mentioning the tool's scope or limitations.
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?
Given the complexity of interacting with a spreadsheet API, no annotations, and no output schema, the description is insufficient. It lacks details on behavioral traits (e.g., read-only nature, error cases), output format, and how it differs from sibling tools, making it incomplete for safe and effective agent use.
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?
The input schema has 100% description coverage, providing clear details for all three parameters, including enums for 'value_render_option'. The description adds minimal value by hinting at 'formatting options', which aligns with the schema but does not elaborate beyond it. This meets the baseline for high schema coverage.
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?
The description clearly states the action ('Get data') and resource ('from a specific range'), distinguishing it from siblings like 'get_sheet_metadata' or 'list_sheets' that handle metadata or listing. However, it does not explicitly differentiate from 'read_sheet_data' or 'search_sheet_data', which might also involve reading data, making it slightly less specific than a perfect score.
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?
The description provides no guidance on when to use this tool versus alternatives like 'read_sheet_data' or 'search_sheet_data'. It mentions 'formatting options' but does not specify contexts, exclusions, or prerequisites for selection, leaving the agent to infer usage based on parameter names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get metadata about a Google Spreadsheet
| Name | Required | Description | Default |
|---|---|---|---|
| spreadsheet_id | Yes | The ID of the Google Spreadsheet |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states this is a 'Get' operation, implying read-only behavior, but doesn't specify authentication requirements, rate limits, error conditions, or what metadata fields are returned. For a tool with zero annotation coverage, this leaves significant gaps in understanding how it behaves.
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?
The description is a single, efficient sentence that directly states the tool's purpose with zero wasted words. It's appropriately sized for a simple metadata retrieval tool and front-loads the essential information.
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?
For a tool with no annotations and no output schema, the description is insufficient. It doesn't explain what metadata is returned, how to interpret results, or provide context about the Google Spreadsheet ecosystem. Given the complexity of spreadsheet metadata and lack of structured documentation, more guidance is needed.
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?
The input schema has 100% description coverage, clearly documenting the single required 'spreadsheet_id' parameter. The description doesn't add any additional parameter information beyond what's in the schema, but since schema coverage is complete, the baseline score of 3 is appropriate.
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?
The description clearly states the verb ('Get') and resource ('metadata about a Google Spreadsheet'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'list_sheets' or 'read_sheet_data' which might also retrieve spreadsheet information, leaving some ambiguity about what specifically distinguishes this metadata retrieval.
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?
The description provides no guidance on when to use this tool versus alternatives like 'list_sheets' or 'read_sheet_data'. There's no mention of prerequisites, context, or exclusions, leaving the agent to infer usage based on tool names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all sheets/tabs in a Google Spreadsheet
| Name | Required | Description | Default |
|---|---|---|---|
| spreadsheet_id | Yes | The ID of the Google Spreadsheet |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action but doesn't describe what 'list' entails—such as whether it returns metadata, names only, pagination behavior, or error conditions. For a tool with zero annotation coverage, this leaves significant gaps in understanding how it behaves.
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?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's front-loaded and wastes no space, making it easy to parse quickly.
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?
Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., a list of sheet names, objects with metadata), error handling, or behavioral nuances. For a tool with no structured output information, the description should provide more context to be fully helpful.
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?
The schema description coverage is 100%, so the input schema already documents the single parameter 'spreadsheet_id' with its type and description. The description doesn't add any meaning beyond this, such as format examples or constraints, but the schema provides adequate baseline information.
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?
The description clearly states the action ('List all sheets/tabs') and resource ('in a Google Spreadsheet'), making the purpose immediately understandable. However, it doesn't differentiate this tool from its sibling tools like 'get_sheet_metadata' or 'read_sheet_data', which might have overlapping functionality.
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?
The description provides no guidance on when to use this tool versus alternatives like 'get_sheet_metadata' or 'search_sheet_data'. There's no mention of prerequisites, exclusions, or specific contexts where this tool is preferred, leaving the agent to infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read data from a Google Sheet by spreadsheet ID and range
| Name | Required | Description | Default |
|---|---|---|---|
| spreadsheet_id | Yes | The ID of the Google Spreadsheet | |
| range | No | The range to read (e.g., 'Sheet1!A1:C10') | Sheet1 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool reads data but doesn't mention any behavioral traits such as permissions required, rate limits, error handling, or output format. This is a significant gap for a tool that interacts with external resources like Google Sheets.
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?
The description is a single, efficient sentence that directly states the tool's purpose and parameters. It is front-loaded with essential information and contains no redundant or unnecessary details, making it highly concise and well-structured.
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?
Given the complexity of interacting with Google Sheets and the lack of annotations and output schema, the description is incomplete. It doesn't cover behavioral aspects, usage guidelines, or output details, leaving gaps that could hinder an agent's ability to use the tool effectively in context with its siblings.
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?
Schema description coverage is 100%, so the schema already documents both parameters thoroughly. The description adds minimal value beyond restating the parameters (spreadsheet ID and range), without providing additional context like format examples or usage tips. Baseline 3 is appropriate as the schema does the heavy lifting.
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?
The description clearly states the action ('Read data from') and resource ('a Google Sheet'), specifying the required inputs (spreadsheet ID and range). It distinguishes from siblings like 'get_sheet_metadata' by focusing on data extraction, but doesn't explicitly differentiate from 'get_range_data' or 'search_sheet_data', which may have overlapping functionality.
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?
No guidance is provided on when to use this tool versus alternatives like 'get_range_data' or 'search_sheet_data'. The description lacks context about use cases, prerequisites, or exclusions, leaving the agent to infer usage based on tool names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for specific data in a Google Sheet
| Name | Required | Description | Default |
|---|---|---|---|
| spreadsheet_id | Yes | The ID of the Google Spreadsheet | |
| search_term | Yes | The term to search for | |
| sheet_name | No | Name of the specific sheet to search in | Sheet1 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden but only states the basic action without disclosing behavioral traits. It doesn't mention if this is a read-only operation, how results are returned (e.g., matches, positions), or any constraints like rate limits or permissions needed, which are critical for a search tool.
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?
The description is a single, efficient sentence that directly states the tool's purpose without any wasted words. It's appropriately sized and front-loaded, making it easy to grasp quickly.
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?
Given the complexity of a search operation with 3 parameters, no annotations, and no output schema, the description is incomplete. It fails to explain what the search returns (e.g., cell references, values), how matches are handled, or any limitations, leaving significant gaps for an AI agent to understand the tool fully.
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?
The description adds no meaning beyond the input schema, which has 100% coverage with clear descriptions for all parameters. Since the schema fully documents the parameters, the baseline score of 3 is appropriate, as the description doesn't compensate but also doesn't detract.
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?
The description clearly states the action ('Search') and resource ('specific data in a Google Sheet'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_range_data' or 'read_sheet_data', which might also retrieve data, so it's not fully distinctive.
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?
The description provides no guidance on when to use this tool versus alternatives like 'get_range_data' or 'read_sheet_data'. It lacks context on scenarios where searching is preferred over direct retrieval, such as when the exact location of data is unknown, leaving usage unclear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get_range_dataget_sheet_metadatalist_sheetsread_sheet_datasearch_sheet_dataScored across 5 tools
There is significant overlap between get_range_data and read_sheet_data, as both retrieve data from a sheet range, potentially causing confusion. However, get_range_data mentions formatting options while read_sheet_data specifies spreadsheet ID, providing some differentiation. The other tools have clearer distinct purposes (metadata, listing, searching).
All tool names follow a consistent verb_noun pattern with snake_case (e.g., get_range_data, list_sheets, search_sheet_data). The naming is predictable and readable throughout the set, with no deviations in style or convention.
With 5 tools, the count is reasonable for a Google Sheets server, covering core operations like reading, listing, and searching. It is slightly thin for a full-featured Sheets API but adequate for basic interactions, lacking tools for writing or updating data.
The tool set is severely incomplete for a Google Sheets domain, as it only supports read operations (get, list, search) with no create, update, or delete capabilities. This creates significant gaps that will hinder agents from performing common workflows like editing or managing sheets.
Connect AI assistants to Google Sheets through controlled tools for reading and updating rows.
Query your Google Sheets as structured JSON: list sheets and tabs, read schemas, filter rows.
Provides tools for searching Google Workspace documentation and much more.
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
