# TMS MCP server: connect Roadmark to any AI assistant > 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. URL: https://roadmark.ai/integrations/modelcontextprotocol Language: en Last updated: 2026-10-01 **TL;DR:** Roadmark ships an MCP server, the same one Claude, ChatGPT and Gemini connect to. It offers a small set of freight tools in plain words, such as finding loads, reading a load, pricing a lane as a draft and finding invoices, and every call runs as the person signed in, so any assistant that supports the Model Context Protocol sees only what that person can see in Roadmark. ## What syncs One row for each kind of record: which way it moves, and when. | What | Direction | When | | --- | --- | --- | | Tool calls from the assistant | MCP to Roadmark | Each time a question needs something from Roadmark | | Loads, stops, quotes, customers and invoices | Roadmark to MCP | Per call, only what the person signed in can see | | Draft quotes, loads, messages and ETA updates | MCP to Roadmark | When someone asks, if your admin allows drafting; they wait in Roadmark for approval | ## Setting up MCP 1. **Copy Roadmark's connector address:** The address of Roadmark's 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. **Add it to your MCP client:** Add it wherever your assistant or tool takes a remote MCP server. Claude calls this a custom connector, ChatGPT a custom app, and Gemini a custom app or a custom MCP server. 3. **Sign in with Roadmark:** Each person signs in once with their own Roadmark account. From then on, the assistant acts as them, with exactly their access. 4. **Ask:** Start with "What needs my attention today?" The assistant picks the Roadmark tools a question needs and shows when it calls them. ### Before you start - An assistant or tool that can connect to a remote MCP server and sign in to it. - A Roadmark account for each person who will ask. The [Model Context Protocol](https://modelcontextprotocol.io/docs/getting-started/intro) (MCP) is an open standard for connecting AI applications to outside systems. A business system runs one MCP server, and any assistant that supports the protocol can use it: Claude, ChatGPT and Gemini all do, and so do tools such as Microsoft [Copilot Studio](https://learn.microsoft.com/en-us/microsoft-copilot-studio/agent-extend-action-mcp) and many developer tools. For Roadmark, that means one connector for every assistant your team uses. Your freight stays in Roadmark, and the assistant asks for what a question needs, as the person asking. ## How MCP works, in plain words There are two sides. The assistant is the MCP _client_. The system that holds the data is the MCP _server_. When the two connect, the server lists the tools it offers, each with a name, a description and the inputs it takes. When someone asks a question, the assistant decides which tools it needs, calls them, and writes its answer from what comes back. Two parts of the standard matter most for freight data: - **Sign-in.** For servers reached over the internet, the MCP [authorization specification](https://modelcontextprotocol.io/specification/latest/basic/authorization) is built on OAuth 2.1. The person signs in with the system that holds the data, and the assistant gets a token for that server, never a password. - **A person in the loop.** The [tools specification](https://modelcontextprotocol.io/specification/latest/server/tools) says there should always be a human able to deny a tool call, and that assistants should ask before sensitive operations and show which tools they're calling. Claude, ChatGPT and Gemini each add their own approval settings on top. ## What Roadmark's MCP server offers A small set of tools, in plain words, not a copy of the whole API. As the [Developers](https://roadmark.ai/developers) page describes them, they let an assistant: - find loads by customer, lane, status or date, the way a dispatcher would ask; - read one load in full: stops, status, rate and documents; - price a lane from contracts and rate history, and leave the result as a draft; - record a new ETA from a check call or a delay, drafted for approval like any other update; - find open, paid or overdue invoices for a customer; - look up a customer's contract, contacts and recent loads. Every call runs as the person signed in. It sees their companies and customers, and nothing else, and the same row-level isolation that separates the group's companies in the database applies whether a question comes from a screen, the API or an assistant. See [Security](https://roadmark.ai/security). ## An example, from question to approval With Roadmark's example group, J. Park asks Claude to price the Lakeshore Grocers RFQ. The assistant calls Roadmark's quoting tool for each lane. The Quoting agent prices Mississauga to Joliet at $4,920.00, in US dollars, from 90 days of lane history, and leaves it, with every other lane that has history, as a draft. Lanes with no history, such as Toronto to Memphis, are left for a person. J. Park reviews the drafts in Roadmark, approves them and sends the quote to Lakeshore Grocers. The quote's history shows all three steps: asked in Claude, drafted by the Quoting agent, approved and sent by J. Park. The same request from ChatGPT or Gemini would produce the same drafts, because the price comes from the same agent, contracts and history, not from the assistant. ## Connecting a client Every MCP client names the setting differently, and each vendor decides which plans can use it: - [Claude](https://roadmark.ai/integrations/claude): a custom connector, on Free, Pro, Max, Team and Enterprise plans. - [ChatGPT](https://roadmark.ai/integrations/openai): a custom app, created and published by a workspace admin on Business, Enterprise and Edu. - [Gemini](https://roadmark.ai/integrations/googlegemini): a custom app in the Gemini app on a personal Google Account, or a custom MCP server in Gemini Enterprise. Any other client that can reach a remote MCP server and sign in to it can connect the same way, with the address from Roadmark's settings. Developers building their own agent can use the same server, with the same sign-in and the same limits, or the full Roadmark API and webhooks, starting from a sandbox with the Ashgrove example group already loaded. ## Questions about MCP and Roadmark ### What is an MCP server? The Model Context Protocol (MCP) is an open standard for connecting AI applications to outside systems. An MCP server is the side a business system runs: it tells an assistant which tools it offers, and answers when the assistant calls one. Roadmark's MCP server is how Claude, ChatGPT and Gemini reach your freight in Roadmark. ### Does Roadmark have an MCP server? Yes. It's the same one Claude, ChatGPT and Gemini use: a small set of plain-word tools, such as finding loads, reading one load in full, pricing a lane as a draft and finding open or overdue invoices. Every call runs as the person signed in, seeing only their companies and customers. ### Is the MCP server the whole Roadmark API? No. It's a small set of tools written for an assistant to use, not a copy of the whole API. Developers who need every record, and webhooks, use the Roadmark API, with the same sign-in and the same limits. ### Which assistants can connect to it? Claude, ChatGPT and Gemini, and also agents built in Microsoft Copilot Studio and any other assistant that supports MCP. Each one's own rules decide where you add it and which plans can; the Claude, ChatGPT and Gemini pages here cover those. ### Can an assistant act in Roadmark without anyone approving it? Only within limits your team set. A Roadmark admin chooses read only, read and draft, or act within your rules. At the first two, anything an assistant prepares waits in Roadmark for a person. At the third, it may send only what your Roadmark agents may already send on their own for that lane or customer. ## Related pages - [Developers](https://roadmark.ai/developers): REST API, webhooks and MCP - [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 - [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. - [Gemini integration: ask Roadmark from Gemini](https://roadmark.ai/integrations/googlegemini): 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. Companies, people and shipment figures in product examples are fictional. They illustrate workflows and are not customer testimonials or measured results.