# Gemini integration: ask Roadmark from Gemini > Connect Roadmark to Gemini through its MCP server: as a custom app in the Gemini app, or as a custom MCP server your admin adds to Gemini Enterprise. URL: https://roadmark.ai/integrations/googlegemini Language: en Last updated: 2026-10-01 **TL;DR:** Roadmark connects to Gemini through Roadmark's MCP server, in one of two places: the Gemini app, where a person adds it as a custom app, or Gemini Enterprise, where an admin adds it once for the team. Either way, each person signs in with their own Roadmark account and Gemini sees only what they can see. ## What syncs One row for each kind of record: which way it moves, and when. | What | Direction | When | | --- | --- | --- | | Questions and requests from your team | Gemini to Roadmark | Each time someone asks Gemini with Roadmark connected | | Answers about loads, lanes, customers and invoices | Roadmark to Gemini | Per question, only what the person asking can see | | Draft quotes, loads, messages and rate agreements | Gemini to Roadmark | When someone asks and confirms, if your admin allows drafting; they wait in Roadmark for approval | ## Setting up Gemini 1. **Copy Roadmark's connector address:** The address of Roadmark's connector (its MCP server) is in Roadmark's settings. A Roadmark admin also chooses how far assistants may go: read only, read and draft, or act within your rules. 2. **Gemini Enterprise: add it for the team:** On the Business edition, a team admin opens Settings & help > Team > Manage team > Connected apps and clicks Add MCP Server, then enables the connection so the team can see it. On the Standard, Plus, Pay-as-you-go and Frontline editions, an admin adds a Custom MCP Server data store from the Gemini Enterprise page in the Google Cloud console, then turns on the actions the team may use. 3. **Gemini app: add it yourself:** On gemini.google.com, open Settings > Connected Apps (or Personal Intelligence > Connected Apps), and under Custom apps click Add a custom app. Paste the address and follow the on-screen steps. 4. **Sign in and ask:** Each person signs in with their own Roadmark account. In the Gemini app, type @ in a chat and pick Roadmark to make sure Gemini uses it, then ask. ### Before you start - For a team: Gemini Enterprise, and an admin who can add connectors (on the Standard, Plus, Pay-as-you-go and Frontline editions, the Discovery Engine Editor role in Google Cloud, and organization policies that allow the custom MCP data store and Roadmark's domains). - For one person in the Gemini app: a personal Google Account, age 18 or over, in the US, with Keep Activity on. - A Roadmark account for each person who will ask. Gemini connects to outside systems through the Model Context Protocol (MCP), and Roadmark's connector is an [MCP server](https://roadmark.ai/integrations/modelcontextprotocol). What changes is where you add it. Google offers custom MCP servers in two products with different rules: the Gemini app at gemini.google.com, for people on personal Google Accounts, and Gemini Enterprise, for teams. ## Which Gemini to use **Gemini Enterprise, for a team.** An admin adds Roadmark once, and each person signs in. On the Business edition, a team admin adds it under Manage team > Connected apps, as Google describes in [Set up your custom MCP server connection](https://support.google.com/g/answer/17106276?hl=en); Google marks that feature as pre-GA. On the Standard, Plus, Pay-as-you-go and Frontline editions, an admin creates a Custom MCP Server data store in the Google Cloud console, following [Set up your custom MCP server data store](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/custom-mcp-server/set-up-custom-mcp-server). Both ask for the server's address and its OAuth details, and Gemini Enterprise registers as an OAuth client so that each person signs in on their own. Google says the Gemini Enterprise app doesn't use your prompts and outputs to train its models, in its [Gemini Enterprise FAQ](https://cloud.google.com/gemini-enterprise/faq). **The Gemini app, for one person.** Anyone who meets Google's conditions can add Roadmark as a custom app, following [Connect & manage custom apps for Gemini Apps](https://support.google.com/gemini/answer/17209137?hl=en). Google lists them plainly: be 18 or over and in the US, sign in with a personal Google Account (work and school accounts can't add custom apps yet), use it in English, and keep Keep Activity on. That last condition matters for business data: the [Gemini Apps Privacy Hub](https://support.google.com/gemini/answer/13594961?hl=en) says Google uses that activity to improve its services, including training generative AI models, and that human reviewers read a subset of chats. Read it before connecting company freight data. ## What your team can ask Gemini Anything they could find in Roadmark, asked in their own words. See the [AI assistants](https://roadmark.ai/ai-assistants) page for questions by team. For example, with Roadmark's example group, an owner asks Gemini how many loads Keel Transport hauled for Ashgrove Logistics this quarter, and at what rate. Keel Transport joined the group in March and still dispatches on McLeod, with Roadmark running beside it. Gemini reads what Roadmark receives from McLeod, the loads, status, stops and documents, and answers from those records. The owner can see all three companies because their Roadmark access covers the group; a dispatcher at Keel Transport asking the same question would see only Keel Transport's side. ## Two sets of permissions, both enforced **Roadmark's.** The connector runs as the person asking and carries exactly their access. A Roadmark admin sets how far assistants may go, from read only, to read and draft, to acting within the rules your team has set for the agents. Work asked for in Gemini goes through the same agents as work asked for in the app, so a dollar limit on a lane, a customer on credit hold or a carrier blocked by compliance applies the same way. See [AI controls](https://roadmark.ai/ai-control). **Gemini's.** In Gemini Enterprise, Google says a new custom MCP server starts switched off: on the Business edition an admin enables the connection, and on the other editions all of its actions are off until an admin turns on the ones the team may use. By default, Gemini Enterprise also asks the person to confirm each action, unless the tool is marked read only. In the Gemini app, Google requires manual confirmation for any write action, and notes that Gemini can make mistakes. On Roadmark's side, anything a chat prepares waits as a draft for a person, unless your admin has chosen "Act within your rules". Every action taken through Gemini is on the record in Roadmark, with the person, the assistant and the time. ## Using it day to day In the Gemini app, type @ in a chat and pick Roadmark so Gemini uses it for that prompt. Ask in plain words. When a request needs work done, the result lands in Roadmark as a draft, with the reasons, in the same queue your team approves everything else from. To stop using it in the Gemini app, turn Roadmark off or remove it under Settings > Connected Apps; your Roadmark admin can also turn assistants off for a person, a team or a company at any time. The same connector works in Claude and ChatGPT too, and the [Developers](https://roadmark.ai/developers) page describes the MCP server behind it for teams building their own tools. ## Questions about Gemini and Roadmark ### Can I connect Roadmark to Gemini with my work Google account? Not in the Gemini app for now: Google says custom apps there need a personal Google Account, and aren't available with a work or school account. For a team on work accounts, Gemini Enterprise supports custom MCP servers, added once by an admin. ### Is our freight data used to train Gemini? It depends on which Gemini. Google says prompts and outputs in the Gemini Enterprise app aren't used to train Google models. The Gemini app needs Keep Activity on for custom apps, and Google says it uses that activity to improve its services, including training generative AI models, with a subset of chats read by human reviewers. On Roadmark's side, the assistant only receives what a question needs, and only what that person may see. ### Can Gemini change anything in Roadmark without asking? No. In the Gemini app, Google requires manual confirmation for any write action. In Gemini Enterprise, a new custom MCP server starts switched off: on the Business edition an admin enables the connection, and on the other editions an admin turns on each action the team may use. Gemini Enterprise also asks the person to confirm an action before it runs, unless the tool is marked read only. And in Roadmark, anything prepared from a chat waits as a draft for someone to approve, unless your admin has chosen "Act within your rules". ### Does it work on my phone? In the Gemini app, yes: you connect Roadmark on gemini.google.com, and Google says it then works in both the Gemini web app and the Gemini mobile app. ## Related pages - [Connect your AI assistant](https://roadmark.ai/ai-assistants): Use Roadmark from Claude, ChatGPT or Gemini - [Control and safety](https://roadmark.ai/ai-control): Approvals, limits and the record - [Security](https://roadmark.ai/security): Company isolation, access and your data - [Developers](https://roadmark.ai/developers): REST API, webhooks and MCP - [Claude integration: ask Roadmark from Claude](https://roadmark.ai/integrations/claude): Add Roadmark to Claude as a custom connector, then ask about loads, lanes and customers in chat. Each person signs in, and anything drafted waits for approval. - [ChatGPT integration: ask Roadmark from ChatGPT](https://roadmark.ai/integrations/openai): Add Roadmark to ChatGPT as a custom MCP app: a workspace admin publishes it once, then each person signs in and asks about loads, lanes and customers. - [TMS MCP server: connect Roadmark to any AI assistant](https://roadmark.ai/integrations/modelcontextprotocol): Roadmark has an MCP server: a small set of freight tools any MCP client can use, each call running as the person signed in and seeing only their access. Companies, people and shipment figures in product examples are fictional. They illustrate workflows and are not customer testimonials or measured results.