Tatara

Vol. 05 / Connect Gemini

Connect Gemini to your company documents

Gemini reads your company documents through Tatara over the Model Context Protocol, and the route depends on which Gemini you mean. Gemini CLI takes the server as one entry in a settings file and is the straightforward path. The Gemini app accepts a custom MCP server too, but through Spark and with real conditions attached.

Start free

500 documents free
No card

The address, whichever client you use: https://www.tatara.app/api/mcp

A chat window plugged by a cable into a stack of documents.

Connecting Gemini

Does Gemini support MCP servers?

Yes, on more than one surface, and they are not equivalent. Gemini CLI has first-class MCP server configuration and connects to Tatara in one config entry. The Gemini app accepts a custom MCP server URL under Spark’s connected apps, gated by Google’s eligibility rules. Gemini Enterprise has its own separate setup on Google Cloud.

How do you connect Gemini to Tatara?

You give the client Tatara’s address and approve the connection once. Tatara serves MCP over streamable HTTP at a single URL, and takes either a browser sign-in or an access token as the credential, so the steps are the same wherever you start.

The full procedure, including issuing and revoking access tokens, lives in the Tatara docs. For Gemini’s own screens, see Google on connecting custom apps to Gemini.

After you connect

What can Gemini do once it is connected?

It gets thirty-one tools against your workspace, in eight groups: finding and reading documents, writing them, organising them into folders, curating the tag and property vocabulary, deleting or restoring things, working in workbooks, mapping related ideas on whiteboards, and building data pages that read their figures from a workbook. The tools describe themselves, so a connected agent discovers what it needs when it needs it.

A document ringed by eight kinds of tool.

Every agent write is governed. A document needs a type, a title, a description and tags steered to your taxonomy, and a write that does not qualify comes back with what is wrong and how to fix it. The agent corrects itself inside its own loop instead of leaving a half-written document for someone to find later. Every save is stamped with the credential behind it, which is why an agent cannot pass itself off as a person.

A page written by an agent, stamped with a tick.

Underneath, a workspace is plain Markdown with YAML frontmatter: one file per concept, with links forming a graph, and nothing you could not open in an editor. You can also install the open source agent skills with npx skills add tatara-app/tatara-skills, which teach Gemini the workflow up front so its first write usually passes.

The same page open as a document and as plain text, beside an open padlock.

What are the limits with Gemini?

MCP support is not the same across assistants, so here is the honest version for this one.

Common questions

Gemini and your company documents

Can Gemini read my company documents?

Yes, over MCP, though which Gemini matters. Gemini CLI connects to Tatara with one entry in its settings file and no eligibility conditions. The Gemini app can connect too, but only through Spark and only if you meet Google’s requirements for it.

Does the Gemini app support custom MCP servers?

Yes, under Spark’s connected apps, with conditions. Google requires Spark access, a personal Google Account rather than a work or school one, and activity history left on, and availability is regional. Gemini CLI has none of those restrictions, which is why it is the route this page leads with.

Do I have to paste a client ID and secret?

No. Tatara’s MCP server supports Dynamic Client Registration, so a client that asks for one can register itself. The advanced credential fields Google and OpenAI show for servers that cannot do this stay empty for Tatara.

What if the client cannot open a browser to sign in?

Use an access token instead. An account owner creates one in Tatara under Settings, Access tokens; the client sends it as a bearer credential on every call. The token is shown exactly once when it is created, and revoking it cuts the agent off on its next request.

Get started

What does it cost to connect Gemini?

Nothing to start. The free plan holds 500 documents and does not ask for a card. Agents connect to it over MCP and can read your workspace and make governed writes to it. Paid plans add headroom, and the pricing page has the current limits.