MewCP Google Drive MCP

by asthetech

Not rated
GitHub

About

Hosted, Stateless & Multitenant Google Drive MCP server enables AI assistants to access, organize, search, and manage files through Google Drive.

Details

Author
asthetech
Categories
Developer Tools, Search, Knowledge Base

Setup

Install MewCP Google Drive MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/asthetech/mewcp-google-drive

Follow the installation instructions in the repository README, then restart your MCP client.

Hosted, Stateless & Multitenant Google Drive MCP server enables AI assistants to access, organize, search, and manage files through Google Drive.

Upload, search, and manage Google Drive files — directly from your AI workflows.

A Model Context Protocol (MCP) server that exposes Google Drive's API for listing, searching, uploading, downloading, sharing, and organizing files and folders.

The Google Drive MCP Server provides full programmatic access to Google Drive through a stateless, multi-tenant interface:

- List, search, upload, and download files using Drive's native query syntax
- Create and organize folders, manage file permissions and sharing
- Read text file content directly without downloading to disk

- Automating file management and document workflows from AI agents
- Building assistants that can read, organize, and share Drive files
- Integrating Google Drive actions into LLM-powered pipelines

Lists files in Google Drive with optional filtering by parent folder, name, or type.

- folder_id (string, optional) — Parent folder ID to filter results by - query (string, optional) — Additional Drive query fragment e.g. name contains 'report' - page_size (integer, optional) — Maximum number of results to return, capped at 1000. Default: 10`
{ "count": 3, "files": [ { "id": "1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs", "name": "report.pdf", "mimeType": "application/pdf", "size": "204800", "createdTime": "2024-01-15T10:00:00.000Z", "modifiedTime": "2024-03-20T14:30:00.000Z", "webViewLink": "https://drive.google.com/file/d/..." } ] }

Returns the full metadata object for a single file or folder.

- file_id (string, required) — Google Drive file ID
{ "id": "1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs", "name": "report.pdf", "mimeType": "application/pdf", "size": "204800", "createdTime": "2024-01-15T10:00:00.000Z", "modifiedTime": "2024-03-20T14:30:00.000Z", "owners": [{ "displayName": "John Doe", "emailAddress": "john@example.com" }], "webViewLink": "https://drive.google.com/file/d/..." }

Downloads a file from Drive and writes it to a specified local path.

- file_id (string, required) — Google Drive file ID - destination_path (string, required) — Local filesystem path to save the file to
{ "message": "File downloaded successfully to: /path/to/file.pdf" }

Uploads a local file to Google Drive with an optional destination name, folder, and MIME type.

- file_path (string, required) — Local filesystem path of the file to upload - name (string, optional) — Destination filename in Drive. Defaults to the local filename - folder_id (string, optional) — Parent folder ID in Drive to upload into - mime_type (string, optional) — MIME type of the file e.g. text/plain, application/pdf
{ "message": "File uploaded successfully", "file": { "id": "1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs", "name": "report.pdf", "webViewLink": "https://drive.google.com/file/d/..." } }

Creates a new folder, optionally nested inside a parent folder.

- name (string, required) — Folder name - parent_folder_id (string, optional) — Parent folder ID to create the folder inside
{ "message": "Folder created successfully", "folder": { "id": "1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs", "name": "Projects", "webViewLink": "https://drive.google.com/drive/folders/..." } }

Permanently deletes a file or folder. This action cannot be undone.

- file_id (string, required) — Google Drive file or folder ID to delete
{ "message": "File/folder with ID 1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs deleted successfully" }

Searches Drive using the full Drive query expression language and returns matching file metadata.

- query (string, required) — Drive query expression e.g. name contains 'report', mimeType='application/pdf' - page_size (integer, optional) — Maximum number of results to return, capped at 1000. Default: 10
{ "count": 2, "files": [ { "id": "1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs", "name": "Q1 Report.pdf", "mimeType": "application/pdf", "webViewLink": "https://drive.google.com/file/d/..." } ] }

Grants a permission on a file, either to a specific user or to anyone with the link.

- file_id (string, required) — Google Drive file ID - email (string, optional) — Recipient email address when sharing with a specific user - role (string, optional) — Permission role. Values: reader, commenter, writer. Default: reader - share_type (string, optional) — Permission type. Values: user, group, domain, anyone. Defaults to user if email is provided, otherwise anyone
{ "message": "File shared successfully", "permission_id": "anyoneWithLink", "webViewLink": "https://drive.google.com/file/d/.../view", "webContentLink": "https://drive.google.com/uc?id=..." }

Reads and returns the decoded text content of a file directly, without saving to disk.

- file_id (string, required) — Google Drive file ID
"The full decoded text content of the file as a string."

- file_id— Unique Google Drive file or folder identifier. Obtain fromlist_files,search_files, or any file response.
-
folder_id— ID of a Drive folder. Uselist_filesorsearch_fileswithmimeType='application/vnd.google-apps.folder'to find folder IDs.
-
page_size— Limits the number of items returned. Always capped at 1000.

name contains 'report' — Files with "report" in name name = 'budget.xlsx' — Exact filename match mimeType = 'application/pdf' — Files of a specific MIME type mimeType = 'application/vnd.google-apps.folder' — Folders only 'folder_id' in parents — Files inside a specific folder modifiedTime > '2024-01-01T00:00:00' — Files modified after a date fullText contains 'quarterly' — Files containing text (Docs/Sheets only)
reader — View only commenter — View and comment writer — View, comment, and edit

- Cause:API key not provided in request headers or incorrect format
- Solution:
- Verify
Authorization: Bearer YOUR_API_KEYandX-Mewcp-Credential-Id: CREDENTIAL-IDheaders are present
- Check API key is active in your MewCP account

- Cause:API calls have exceeded your request limits
- Solution:
- Check credit usage in your Curious Layer dashboard
- Upgrade to a paid plan or add credits for higher limits
- Contact support for credit adjustments

- Cause:No Google Drive credential linked to your account
- Solution:
- Go toCredentialsin your MewCP dashboard
- Connect your Google account via OAuth
- Retry the request with the correct
X-Mewcp-Credential-Idheader

- Cause:JSON payload is invalid or missing required fields
- Solution:
- Validate JSON syntax before sending
- Ensure all required tool parameters are included
- Check parameter types match expected values

- Cause:Incorrect server name in the API endpoint
- Solution:
- Verify endpoint format:
{server-name}/mcp/{tool-name}`
- Use correct server name from documentation
- Check available servers in your Curious Layer account

- Cause:Upstream Google Drive API returned an error
- Solution:
- Check Google service status atGoogle Workspace Status Page
- Verify your credential has the required Drive permissions
- Review the error message for specific details

- Google Drive API Documentation— Official API reference
-
Google Drive API Reference— Complete endpoint reference
-
FastMCP Docs— FastMCP specification
-
FastMCP Credentials— FastMCP Credentials package for credential handling

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Semantic code search for AI agents without indexing your codebase or storing any data. Fast and accurate.

Create and read feature flags, review experiments, generate flag types, search docs, and interact with GrowthBook's feature flagging and experimentation platform.

Word search, crossword, and sudoku generator MCP server with printable PDF worksheets, themed word banks, and verifiable LLM evals. Local-first, from the makers of puzzletide.com.

Official MCP server for Stimulsoft Reports & Dashboards documentation. Semantic search across FAQ, Programming Manual, Server/User Manual, and Server/Cloud API for .NET, WPF, Avalonia, WEB, Blazor, Angular, React, JS, PHP, Java, and Python platforms.

Searching and access your AI coding sessions from Claude Code, Gemini CLI, opencode, and OpenAI Codex.

Search Apple's Developer Documentation with smart search and wildcard support.

MCP server that exposes ast-grep (sg) as two tools for structural code search.

Search everything your terminal ever printed. Local MCP server over per-command recorded output: full-text search, exit codes, diffs, secret redaction. Built and maintained by an AI agent (Soren Achebe).

Let AI agents search, register, and manage domains via API

Search, compare, and get docs for 210+ APIs ranked by CLI and agent relevance

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.