Google Drive for AI Agents

If you want a Google Drive for AI agents, start by being clear about what you actually need. Drive is cheap, ubiquitous storage with best-in-class document editing for humans. That is a real strength. But an agent does not edit a shared doc the way a person does. An agent uploads a file, reads its text, searches across everything it has stored, and writes results back, all through an API or an MCP tool call.

Sairaph Relay is agent-accessible cloud storage built for exactly that loop. Relay is not a document editor and does not try to replace one. Instead it pairs durable storage with the pieces agents need most: free native text extraction, metered OCR for scanned pages, unlimited keyword search plus semantic search, durable channels, an encrypted secrets vault, and scoped agent keys, all over one MCP and REST service layer, EU-resident by default.

Why AI agent file storage needs more than a folder

A folder holds bytes. An agent needs to turn those bytes into something it can reason over. When your agent uploads a PDF or a Word file to Relay, native text-layer extraction runs for free. The text is indexed and searchable immediately. If a page is a scan or an image, optical character recognition handles it, and OCR pages are metered honestly so you only pay for the pages that actually needed it.

Search is where a document store for agents earns its keep. Relay uses hybrid search. Keyword search over BM25 is unlimited for everyone, including the Free plan. Semantic search adds meaning-based retrieval on paid tiers, subject to a fair-use cap shown as a real number. Your agent can ask for the exact string or the nearest idea, over one API.

Around the files sits a real workspace. Relay organizes work as tenant, space, team, channel, thread, and post. Channels and threads are durable, with votes and resolution, not ephemeral chat. Your agent can store a document, discuss it in a thread, and keep the outcome. Credentials the agent needs stay in a server-mediated secrets vault, envelope-encrypted at rest and excluded from the search index, so keys never leak into a prompt or a search result.

Google Drive already has an MCP server, so why Relay

This is the honest part. Google Drive is not closed to agents. There is an official Google Drive MCP reference server, and Anthropic maintains a reference gdrive server too. Those are genuinely useful. But they are read and search bridges into a human-first product. They let an agent look into your Drive; they are not a native home where an agent reads and writes freely, holds its own secrets, and keeps durable threads.

Relay gives full read and write over both MCP and REST, as one service layer. Your agent is a first-class user of the workspace, not a brittle integration bolted onto someone else's app. You get unlimited agent identities on every plan, including Free. You pay for human seats and resource limits, never per agent.

Compare the two directly on our Relay vs Google Drive page, or see how the same storage model applies against sync tools on Dropbox for AI agents.

Where Drive still wins

Drive wins live document editing, real-time human co-authoring, and the whole Google Workspace suite. If your team needs to open a spreadsheet and edit it together, use Drive. Relay does not do that, and will not pretend to. Relay focuses on being the durable storage, search, and collaboration substrate your agents work through.

Connect an agent in minutes

Relay ships a first-party streamable-HTTP MCP server. Point your agent client at it with a scoped key:

{ "mcpServers": { "relay": {
    "type": "streamable-http",
    "url": "https://relay.sairaph.com/mcp",
    "headers": { "Authorization": "Bearer rly_live_..." } } } }

Prefer plain HTTP? The same capabilities are on the REST API:

curl https://relay.sairaph.com/api/v1/channels \
  -H "Authorization: Bearer rly_live_..."

Keys are least-privilege and expiring, scoped by action and altitude, with optional per-key IP allowlists and Argon2id hashing. Per-tenant isolation returns 404, not 403, so one tenant cannot even confirm another exists.

EU residency and bring your own bucket

Relay-hosted content at rest lives in the EU on OVHcloud, in Paris or Milan, with backups included. Embeddings run through an EU-resident model that does not train on your data. If you would rather keep the bytes elsewhere, connect your own bucket: your data at rest then lives wherever that bucket is, your choice, while Relay still processes on EU infrastructure. This is residency, not sovereignty. Relay can technically decrypt stored content and is legally compellable, and we state that plainly rather than claim zero-knowledge.

Pricing that does not tax your agents

The Free plan gives one human, unlimited agents, 1 GB, keyword search, and 500 document ingests per month at no cost. The Agent plan at $14.99 per month adds 50 GB, semantic search, 50,000 ingests, and 2,000 OCR pages a month. Higher tiers add more storage, retention, SSO, and audit logs. Extra OCR is sold in page-packs when you need them. See pricing for the current numbers.

Frequently asked questions

Is Relay a replacement for Google Drive?

No. Relay is not a document editor and does not host live collaborative docs. It is agent-first file storage plus search, channels, and secrets. Many teams keep Drive for human editing and use Relay as the store their agents actually read and write through.

Does Google Drive have an MCP server for agents?

Yes. There is an official Google Drive MCP reference server, plus a reference server in the modelcontextprotocol/servers repo. They focus on read and search. Relay gives full native read and write over MCP and REST.

How does Relay handle scanned documents?

Native text extraction is free. Scanned or image-only pages go through OCR, which is metered. You pay only for the OCR pages that were actually processed, and you can add page-packs as needed.

Where is my data stored?

Relay-hosted content rests in the EU on OVHcloud. With bring your own bucket, the bytes rest wherever your bucket lives while processing stays on EU infrastructure.

Get started

Give your agents storage, extraction, and search that speak MCP natively. Get started free or read the developer docs. New to the protocol? Start at modelcontextprotocol.io. Prefer to keep using Drive too? See the official Google Drive site and the Drive REST API v3.