Using the Drivetrain MCP Server
Using the Drivetrain MCP Server
The Drivetrain MCP server allows you to connect Drivetrain to MCP-compatible clients such as ChatGPT and Claude.
Once connected, Drivetrain metrics are exposed as callable tools, allowing MCP-compatible clients to retrieve metric values across time, dimensions, and versions.
This provides a new way to work with your Drivetrain metrics: in addition to the application interface, you can now access the same trusted metrics through natural-language prompts in an external client.
What is an MCP server?
An MCP (Model Context Protocol) server is a service that exposes tools - functions that an AI client can call to fetch or process information. When connected, the client determines which tool is relevant to a prompt, calls it, and returns the result in a structured format.
For Drivetrain, this means:
Metrics, dimensions, and versions are available as callable tools.
Clients such as Claude Desktop can fetch Drivetrain metrics, perform derived calculations, and present results as text or charts.
Metrics can be combined with outputs from other MCP servers to power cross-source analysis.
Scope of the Drivetrain MCP Server
The Drivetrain MCP server provides access to:
Metric values
Across time
Filtered by dimensions
Scoped by versions
Including derived metric calculations
It does not provide access to:
Raw datasets
Board editing
Model editing
Schema changes
Dataset-level querying
Example workflow
Once connected, you can use natural-language queries to work with Drivetrain metrics. For example:
Prompt: What’s my Revenue per FTE?
Here’s what happens in the background:
The system first checks whether a “Revenue per FTE” metric exists in Drivetrain.
If it exists, the metric is fetched directly.
If not, the system fetches the Revenue and FTE metrics separately and computes the derived value (Revenue ÷ FTE).
Actual values for the requested time period are then retrieved and displayed—for example, Revenue per FTE across 2025, showing month-to-month trends.
This workflow can be extended to cover deeper analysis:
Benchmarking: You can also prompt:
How does this compare to industry benchmarks for companies of my revenue range?The system automatically searches and consolidates up-to-date benchmark datasets.
Results are filtered to match your company size and revenue tier.
The output is a structured comparison table—for instance, showing that $168K revenue per FTE is above the private SaaS median of $129K but below the $200K–$230K range for larger SaaS companies.
Strategic recommendations: You can follow up with the prompt:
How can I improve my revenue per FTE?Best practices and strategies are curated from trusted sources and contextualized with your metrics.
Recommendations may include quick wins (e.g., pricing optimization, automation, expanding revenue from existing customers) and longer-term initiatives (e.g., employee development, performance management, strategic hiring).
A roadmap is outlined with progressive targets and timelines.
Extending with other MCP servers: By connecting additional servers, you can automate downstream workflows. For example
Use a Gmail MCP server to draft and send an update email to your leadership team.
Use a Notion MCP server to automatically update a shared page with benchmark comparisons and strategies.
In this way, a simple question evolves into a complete workflow—from retrieving Drivetrain metrics, to comparing them with external benchmarks, to generating strategic recommendations and sharing them with stakeholders.
Why use the MCP server?
The Drivetrain MCP server allows you to:
Query metric values using natural-language prompts
Retrieve metrics across time, dimensions, and versions
Compute derived metrics
Use Drivetrain metrics inside external AI-driven workflows
In the next section, you’ll learn how to connect common MCP clients—such as ChatGPT and Claude—to the Drivetrain MCP server.
Last updated
Was this helpful?