MCP server
Google Drive MCP server
Google's own Drive MCP server lets AI search, read and create files in Google Drive, with your Google Workspace sign-in.
- Official server
- Files and storage
At a glance
- Maintained by
- Google (Google Workspace)
- Tools exposed
- 8 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
For many companies, Google Drive is where documents live: proposals, contracts, policies, spreadsheets and presentations. Google now hosts its own Drive MCP server, which lets an assistant search files, read their content, check metadata and permissions, list recent files and create or copy files, using your Google Workspace account.
That means a question like "find the latest signed contract with this supplier and summarize the payment terms" can be answered without anyone digging through folders.
At review time, the server is part of Google's Workspace developer preview program, which requires membership. The old MCP reference server for Google Drive was archived in May 2025. Because the server uses your own sign-in, the assistant sees what you can see, so be careful with accounts that have access to sensitive shared drives.
For company-wide knowledge assistants, we often combine live Drive search with an indexed knowledge base, so answers are fast and respect each person's file permissions.
Use cases
Best business use cases
Find documents
Summarize files
Start from templates
Check sharing
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Mostly read (search, read, metadata, permissions); write limited to creating and copying files.
-
search_filesFind files in Drive that match search criteria.
-
read_file_contentRead the content of a file.
-
download_file_contentDownload the contents of a file.
-
get_file_metadataGet details about a specific file.
-
get_file_permissionsGet the sharing and access settings of a file.
-
list_recent_filesList recently opened or changed files.
-
create_fileCreate a new file in Drive.
-
copy_fileMake a copy of an existing file.
Workflows
Example workflows
Answer a contract question
-
1
Ask about a supplier's payment terms.
-
2
The assistant searches Drive for the contract.
-
3
It reads the latest version.
-
4
It quotes the payment clause.
-
5
It links to the file for checking.
Prepare a client folder
-
1
Ask for a new client pack.
-
2
The assistant copies the template files.
-
3
It names them with the client name.
-
4
It lists what still needs filling in.
-
5
A person completes and shares them.
Prompts
Example prompts
“Find the latest signed contract with Acme Supplies and summarize the payment terms.”
“List files I edited this week in the Sales folder.”
“Copy our proposal template and name it for the Harbor Group project.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Code: terminal
claude mcp add --transport http --client-id YOUR_CLIENT_ID --client-secret --callback-port 8080 google-drive https://drivemcp.googleapis.com/mcp/v1- Hosted server: https://drivemcp.googleapis.com/mcp/v1.
- Needs: OAuth 2.0 with your own Google Cloud project. Enable drive.googleapis.com and drivemcp.googleapis.com, set up the consent screen with scopes drive.readonly and drive.file, and create a Web application OAuth client (redirect https://claude.ai/api/mcp/auth_callback for Claude apps). Requires Developer Preview Program membership..
- Claude Desktop: Settings > Connectors > Add custom connector. Name: Google Drive. Remote MCP server URL: https://drivemcp.googleapis.com/mcp/v1. Paste the OAuth Client ID and Client Secret under Advanced settings.
Security
Security considerations
-
Limit folders
Connect an account or service user that sees only the folders a task needs.
-
Start with reading
Begin with search and read access. Add write actions one at a time.
-
Sensitive files
Shared drives may hold HR or financial files. Use accounts without access to them where possible.
-
Keep a record
Log which files the assistant opens and changes.
Related servers
Servers that pair well with it
Gmail
Google's own Gmail MCP server lets AI search and read threads, manage labels and create drafts. It has no send tool.
Google Sheets
Google's own Sheets MCP server lets AI read and update cell values and formulas, change spreadsheet structure and insert rows or columns.
Google Calendar
Google's own Calendar MCP server lets AI list calendars and events, create, update and delete events, respond to invites and suggest times.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- RAG knowledge assistants Assistants that answer questions from your own documents and show where each answer came from.
- AI Product Development AI agents, knowledge assistants, copilots and document automation built into the way your team already works.
- Customer portals A secure place where your customers upload documents, check status, pay and message your team.
- Internal tools Custom software for your own team: trackers, approval flows and back-office systems that replace spreadsheets.
- Document automation Read invoices, forms, contracts and IDs, pull out the right fields and route them for review.
Solutions
View all solutions- Knowledge assistant (RAG) Ask a question in plain words and get an answer from your own documents, with links to the sources.
- AI document processing Read forms, applications, IDs and statements, extract the fields you need and route each document for the right review.
- Automated quoting Draft accurate quotes and proposals from a request, your price rules and past work, for a person to approve.
- AI-assisted content workflows Briefs, first drafts, edits and repurposing in a workflow where people set the angle and approve every word.
- Invoice processing Read supplier invoices, match them to orders and push approved ones into accounting, with exceptions flagged for review.
- Receipt capture and matching Snap a receipt, and the details are read, categorized and matched to the card transaction and the right project.
Industries
View all industries- Property management Tenant portals, maintenance tracking, owner statements and inbox automation for property managers.
- Construction and facilities Job tracking, maintenance requests, inspections, quotes and proof-of-work photos for builders and facility teams.
- Finance and accounting Client portals, document collection, invoice and receipt processing, and reporting for accounting firms and finance teams.
- Tax and compliance services Client portals, document checklists, case queues and deadline tracking for tax preparers and compliance firms.
- Legal Contract review assistants, knowledge search, intake and document automation for law firms and in-house legal teams.
- Insurance Claims intake, document and photo processing, policy knowledge assistants and customer portals for brokers and insurers.
Case studies
View all case studiesGuides and articles
View all guides and articlesAI models
View all ai models- Claude Sonnet 5 Anthropic's balance of speed and intelligence: a strong everyday model for assistants, document work, tool calling and coding.
- Gemini Embedding 2 Google's current embedding model, multimodal: it embeds text, images, video, audio and PDFs for search and retrieval.
- text-embedding-3-large OpenAI's most capable embedding model for search and retrieval, with 3,072-dimension vectors and support for English and other languages.
- text-embedding-3-small OpenAI's efficient, lowest-cost embedding model, with 1,536-dimension vectors for search, retrieval and similarity at scale.
- Cohere Command A+ Cohere's enterprise flagship for multimodal, multilingual agent tasks, with 48 languages, tool calling, JSON output and open weights under Apache 2.0.
- Cohere Embed v4 Cohere's multimodal embedding model for enterprise search, embedding text, images and mixed documents, with flexible vector sizes and long inputs.
Glossary terms
View all glossary terms- RAG RAG, or retrieval-augmented generation, is a method where an AI system first finds relevant passages in your documents, then answers using only those passages.
- Workflow automation Workflow automation uses software to move work through a series of steps, such as routing, approvals and notifications, based on rules and events.
- Embeddings Embeddings are lists of numbers that represent the meaning of text or images, so software can find items that are similar in meaning.
- Hallucination A hallucination is when an AI model states something false or invented as if it were true, such as a made-up fact, figure or source.
- Semantic search Semantic search finds results by meaning rather than exact words, so a search for "reset my login" can find an article titled "Forgot your password".
- Vector database A vector database stores embeddings, lists of numbers that represent meaning, and quickly finds the ones most similar to a query.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. Google hosts one, available through its Workspace developer preview program at review time.
It was archived in May 2025.
It uses your Google sign-in, so it sees what your account can see.