> For the complete documentation index, see [llms.txt](https://doc.batch.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.batch.com/guides-and-best-practices/batch-ai/how-to-leverage-batch-connectivity-via-mcp.md). # How to leverage Batch connectivity via MCP? MCP (Model Context Protocol) is a commonly used protocol to connect LLMs to solutions. It lets you connect an assistant, such as Claude or ChatGPT, to your Batch Dashboard. ### What you can ask your assistant to do An MCP wraps whatever part of the Batch API you choose to expose. Most teams start with reporting and data lookups, then add campaign management on top. Depending on how yours is set up, that can include: * Getting the list of your orchestrations (campaigns, automations, triggers, in-app messages), filtered by status, channel, or type. * Getting the performance of an orchestration — sent, delivered, open, click, conversion, revenue — over a given period. * Looking up your segments, audiences, or catalogs. * Requesting an export of profile attributes, events, or reachability data. * Creating, updating, or deleting a campaign. It's up to you which endpoints you expose — the assistant can only do what your MCP setup allows it to do, nothing more. ### Best practices to keep in mind Here are a few best practices: * Keeping campaign creation and edits limited to drafts, so a human still opens the campaign on the dashboard to check and launch it. * Deleting a campaign, on the other hand, takes effect immediately and can't be undone, so it deserves the same care as on the dashboard. * The same permissions and rate limits as the Batch API still apply. ### How to set it up? It is fairly easy for a technical persona to embed APIs of a solution into an MCP. A lot of Batch customers moved toward this usage. It can be setup locally on Batch user's desktops or server side. {% hint style="info" %} Batch team can support you in this effort to create an MCP leveraging Batch. It is available on request for certain customer tiers. Reach out to your Customer Success Manager to learn more {% endhint %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://doc.batch.com/guides-and-best-practices/batch-ai/how-to-leverage-batch-connectivity-via-mcp.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.