Google-Drive-MCP-Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLIENT_ID | Yes | OAuth client ID from Google Cloud credentials | |
| CLIENT_SECRET | Yes | OAuth client secret from Google Cloud credentials | |
| GDRIVE_CREDS_DIR | Yes | Directory path where credential files are stored | |
| PDF_SIZE_LIMIT_MB | No | PDF file size limit in MB (default: 20, max: 100) | 20 |
| GDRIVE_ROOT_FOLDER_ID | Yes | Root folder ID to restrict access |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| gdrive_searchB | Search for files in Google Drive |
| gdrive_read_fileA | Read file contents from Google Drive. Supports text extraction from PDFs and structured data from Excel files (.xlsx). Automatically converts Google Docs/Sheets to readable formats. For very large files (>20MB) or partial reading, use gdrive_read_large_file instead. |
| gsheets_update_cellA | Update a cell value in a Google Spreadsheet |
| gsheets_readA | Read data from Google Sheets (native Google Sheets only, not Excel/CSV files uploaded to Drive). For Excel files (.xlsx), use gdrive_read_file instead. Supports flexible range selection and formatting options. |
| gdrive_folder_structureA | Display the entire folder structure of Google Drive in a tree format |
| gdrive_read_large_fileA | Read large files (>20MB) from Google Drive with streaming support, or read specific byte ranges from any file. Use this for partial file reading or when gdrive_read_file fails due to size limits. Not suitable for Google Docs/Sheets or files requiring text extraction. |
| gdrive_analyze_imageB | Analyze image files from Google Drive with metadata and preview generation |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Most tools are distinct, but gdrive_read_file and gdrive_read_large_file overlap significantly as both read file contents, differentiated only by size thresholds. Additionally, gsheets_read and gdrive_read_file both handle Google Sheets, which could cause an agent to misselect. Descriptions help, but boundaries are not crisp.
The naming pattern is mostly consistent: resources (gdrive/gsheets) prefixed to verb_noun (e.g., gdrive_search, gsheets_read). However, gdrive_folder_structure is a noun phrase instead of a verb-based name, and gsheets_read lacks the explicit '_file' or '_sheet' suffix seen elsewhere, causing minor deviations.
With 7 tools, the count is well-scoped for a Google Drive server covering search, read, and spreadsheet operations. It is within the ideal 3-15 range and each tool addresses a plausible use case without excessive bloat.
The domain appears to be Google Drive file management, but the toolset only supports search, read, folder structure, and a single spreadsheet cell update. Missing critical operations like file upload, delete, update/move, and more advanced spreadsheet writes create significant gaps that would force agents to hit dead ends.