> For the complete documentation index, see [llms.txt](https://integrations.drivetrain.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://integrations.drivetrain.ai/extending-drivetrain/using-the-drivetrain-mcp-server/available-tools.md). # Available MCP tools See every tool the Drivetrain MCP server exposes, and what each one does. Browse every tool an MCP client can call once it's connected to Drivetrain The Drivetrain MCP server exposes 22 tools. Each tool is a specific, named action a connected client is allowed to take — such as looking up a metric or saving a board. Tools split into two groups: * **Read tools** only look up data. Calling one has no effect on your account, and you can call it as many times as you like. * **Write tools** change something in your account. Most save the change as a draft that you review before it takes effect. A few terms used on this page: * **Board** — a report or dashboard made up of charts. * **Dataset** — a table pulled into Drivetrain from a connected source, such as Snowflake or Salesforce. * **Transformation** — a step applied on top of a dataset, such as adding a column, renaming a column, or looking up a value from another table. * **Version** — a named copy of the plan, such as Actual or Budget. * **Scenario** — a what-if variant of the plan, such as Base Case or Optimistic. * **List** — a table you maintain by hand inside Drivetrain, such as a headcount roster. * **The model** — the structure of your plan: the metrics, formulas, and folders themselves, as opposed to the numbers those formulas produce. #### Read tools Drivetrain exposes 18 read tools. **Finding and fetching metrics** | Tool | What it does | | ------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `search_metrics` | Searches your metrics by meaning rather than exact spelling, so a search for "sales performance" finds the relevant metrics. Each result includes what the metric measures and which dimensions it can be sliced by. | | `describe_metrics` | Returns a metric's full details — what it measures, its type, and its available dimensions — for metrics whose exact names are already known. | | `query_metrics` | Fetches the numbers behind one or several metrics across a chosen date range. This is the tool behind a prompt like "show me revenue by quarter." | | `list_versions` | Lists the versions that exist in your account, such as Actual and Budget. | | `list_scenarios` | Lists the scenarios that exist in your account, such as Base Case and Optimistic. | **Understanding how data can be sliced** | Tool | What it does | | ---------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `list_dimensions` | Lists every dimension in your account, and how those dimensions relate to one another. | | `get_dimension_values` | Lists every value a single named dimension can hold, such as all department names or all region codes. | | `resolve_dimensions` | Identifies which dimension a value belongs to. If a prompt mentions "Marketing" without saying what kind of thing it is, this tool works out that Marketing is a department. | **Answering product questions** | Tool | What it does | | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `search_docs` | Searches Drivetrain's own product documentation to answer a how-to or concept question, such as how scenario planning works. Reserved for help questions — it isn't used while a board or model is being built or edited. | **Reading boards** | Tool | What it does | | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------- | | `get_board` | Fetches an existing board in full, including its charts, layout, and settings. The assistant reads a board this way before making any change to it. | **Reading the model** | Tool | What it does | | ------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `get_model_dtml` | Reads one section of your model's structure: the metrics, the folder tree, the templates, or the scenarios. Each call returns a single section. | | `validate_formula` | Checks whether a planning formula is written correctly before it's saved. The check covers syntax — function names, brackets, date handling — not whether the metrics named inside it exist. | **Reading lists** | Tool | What it does | | --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `get_lists` | Shows which lists exist in your account, with the name and ID of each one. | | `get_list_data` | Opens one list and returns everything inside it: column order, the formulas behind any calculated columns, and every row with those formulas already worked out. | **Reading connected data** | Tool | What it does | | ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- | | `list_datasets` | Lists every connected data source in your account, such as Snowflake or Salesforce, along with the tables available in each. | | `list_dataset_columns` | Shows the columns in one connected table and the kind of data each column holds — text, number, or date. | | `get_dataset_column_values` | Lists the distinct values found in one column of a connected table, so exact spelling and capitalization can be confirmed before filtering on it. | | `get_dataset_current_transformations` | Shows the transformation steps already applied to one connected table, in the order they run. | #### Write tools Drivetrain exposes 4 write tools. Each one changes something in your account, and each saves the change as a draft that you review before it takes effect. | Tool | What it does | Who confirms it | | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------ | | `create_board` | Builds a new board. It's checked for structural mistakes, saved as a draft, then opened in the editor for review. | You click **Save** in the editor. | | `update_board` | Changes an existing board — adding or removing charts, adjusting layout, or renaming it. The original board is left untouched; the changes are written into a draft copy. | You click **Save** in the editor. | | `add_dataset_transformations` | Adds new transformation steps on top of the steps a connected table already has. When the request is in plain English, the SQL behind each new step is generated automatically. | You open the draft and save or discard it. | | `update_dataset_transformations` | Replaces transformation steps a connected table already has, swapping a chosen step for a new version of it. | You open the draft and save or discard it. | --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://integrations.drivetrain.ai/extending-drivetrain/using-the-drivetrain-mcp-server/available-tools.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.