Google Drive logo

Google Drive

OrganizationPopular
cursor
google-drive

Work with Google Drive through its MCP tools - search, read, create, organize, share, comment, and export files. Use when creating files in specific folders, moving or renaming, converting Markdown/CSV into Docs/Sheets, managing comments, or exporting a rendered PDF.

Overview

Publishercursor
Repositoryplugins
Skill namegoogle-drive
Stars
9.2K
Forks
863
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by cursor on GitHub. Read the source before you install it.

Installation

Install the Google Drive AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/cursor/plugins/tree/main/third_party/google-drive/skills/google-drive
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/cursor/plugins.git /tmp/plugins
mkdir -p .claude/skills
cp -r /tmp/plugins/third_party/google-drive/skills/google-drive .claude/skills/google-drive
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Google Drive in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Google Drive on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Google Drive is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Google Drive files

Ids come from search, never guesses

Every tool takes Drive file ids. Get them from search (or list_folder for a known folder, list_recent_files for "what was I just working on"), or from the id in a URL the user pasted. exact_name beats query for a known filename; add mime_type_filter to cut noise. Never invent an id or reuse one from a stale conversation - re-search first.

Folder targeting

  • create_folder takes parent_folder_id; without it the folder lands in My Drive root. When the user names a destination folder, resolve its id and pass it - a file created in root when a folder was specified is a wrong result even if the content is perfect.
  • create_file also takes parent_folder_id, so create files directly where they belong instead of creating then moving.
  • The Docs/Sheets/Slides providers' own create tools CANNOT target a folder (their APIs have no parent parameter). When placement matters, either create the artifact there with create_file (Markdown to Doc, CSV to Sheet), or create it and then move_or_rename with destination_folder_id.
  • move_or_rename does either or both in one call; renaming does not change the id.
  • update_file is the same rename/move with the hosted Drive tool's argument names (fileId; title renames, parentId moves by replacing the current parent); it exists on both the translator and hosted surfaces, so prefer it in guidance that must work on either.
  • Grant limits: this app's grant is drive.file, so moving into or writing files/folders this app never created (and the user never picked) can 403. That 403 is a permission fact, not a transient error; do not retry it.

Markdown and CSV conversion

create_file with target_mime_type: application/vnd.google-apps.document converts Markdown (headings, lists, tables) into a real Google Doc in one call; ...spreadsheet converts CSV into a Sheet. This is the fastest correct way to produce a formatted Doc: prefer it over create-then-insert when the content is known up front. update_file_content converts in place the same way.

Copying, metadata, and sharing

  • copy_file duplicates a file (optionally into a folder) - the right way to instantiate a template without touching the original.
  • get_file_metadata returns the full record (mime type, parents, size, owners, modified time); use it to confirm a move landed.
  • get_file_permissions lists who has access; share_file grants a role to an email. Share only when the user asked; report the link rather than widening access speculatively.
  • download_file returns the raw bytes base64-encoded for non-Google files (images, PDFs, plain text).

Reading and exporting

  • read_file returns text: Docs as Markdown, Sheets as CSV per tab, Slides as plain text. Use it to verify content after writes.
  • export_file returns rendered bytes base64-encoded: pdf for Docs/Sheets/Slides (Sheets PDF renders every tab, charts included), png/svg for Drawings, plus office formats (docx/xlsx/pptx). Use PDF when the user wants to see the final look; exports cap at 10 MB.
  • For one slide as PNG use the google-slides get_slide_thumbnail tool, not Drive export.

Comments

Comments live on the Drive file, so one tool set covers Docs, Sheets, and Slides alike:

  • list_comments returns each comment's text, quoted document text, resolved state, and replies; it pages, so follow nextPageToken before concluding a thread does not exist.
  • add_comment adds a file-level comment (no text anchor).
  • reply_to_comment replies by comment id, and its action: "resolve" (content optional) is the ONLY way to resolve a thread; editing document text near a comment never resolves it. Leave already-resolved threads alone.

Deleting

trash_file is recoverable (~30 days) and works on files and folders (a trashed folder takes its contents). Permanent deletion is deliberately not available; never promise it.

Verify your work

After creates and moves, confirm placement with list_folder on the destination or get_file_metadata (check parents). After content writes, read_file is the ground truth for text and export_file (pdf) for the rendered result.

Frequently asked questions

What does the Google Drive AI skill do?

Work with Google Drive through its MCP tools - search, read, create, organize, share, comment, and export files. Use when creating files in specific folders, moving or renaming, converting Markdown/CSV into Docs/Sheets, managing comments, or exporting a rendered PDF.

Why use Google Drive on TypingMind?

Because you install it once and use it with any model. Google Drive is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Google Drive in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cursor/plugins/tree/main/third_party/google-drive/skills/google-drive. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Google Drive?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Google Drive?

As many as you like. As long as a model supports skills, you can use Google Drive with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Google Drive AI skill free?

It is published on GitHub by cursor. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇