Skip to main content

PowerMetrics MCP Server – AI tool integration (Beta)

Updated

Trustworthy AI requires trustworthy data. Unfortunately, the answers from general-purpose AI assistants often miss the mark, guessing at the math and inventing definitions.

The PowerMetrics MCP server acts as a secure, real-time bridge that closes the gap between conjecture and certainty. With direct access to your metric catalog, and all the business context and relationships behind it, integrating our MCP server with your chosen AI tool ensures reliable answers, grounded in the trusted data within your account.

This article includes:

From simple questions to intelligent workflows

Conversational Analysis. Ask your AI: "Based on our current growth trajectory, what is our projected year-end revenue?" It draws on your full metric history and understands the seasonal patterns and relationships already modelled in PowerMetrics.

Proactive Data Hygiene. Use AI to keep your catalog clean. Tell your assistant: "Find all metrics related to the Toronto pilot and tag them as #Regional-Beta." The AI navigates your catalog's relationships to find the right assets and handles the entire tagging operation automatically.

Always-On Executive Summaries. Connect PowerMetrics to automation tools like n8n or Zapier and create a workflow where your AI checks the metrics every morning and compiles a leadership summary — one that’s 100% grounded in your actual data, with no manual pulling or copy-pasting.

How the PowerMetrics MCP server – AI tool integration works

The PowerMetrics MCP server is built on the open MCP specification and communicates with AI agents using secure HTTP streams. It integrates with the PowerMetrics API, knowledge graph, our knowledge base articles, and tag management system to analyze your data and return answers in natural language.

Our MCP server enables AI agents to interact with your data via:

  • Metric queries (for numerical performance data). AI agents query the metrics in your account, making everything you track in PowerMetrics directly accessible by your chosen AI tool.
  • Knowledge graph queries (for semantic relationships, definitions, and metadata). The knowledge graph exposes the relationships between assets in your account. This enables your integrated AI tool to get accurate answers for questions like: “What data feeds are powering this metric?”, “What operands are included in this calculated metric?”, “Which metrics live in which dashboards?”, and “Who has access to this metric?”.
  • PowerMetrics Knowledge Base articles as a source of detailed, verified information and procedures.
  • Our tag management system for automatic application and removal of asset tags. Learn more about asset tags.

Security and reliability

The PowerMetrics MCP server is designed to keep your data safe and trustworthy.

  • Governed access: Your integrated AI tool respects the access settings as configured in your PowerMetrics account, ensuring everyone sees only what they’re supposed to see.
  • Trusted data: By exposing relationships between assets in your account, the knowledge graph gives your AI tool an in-depth, holistic understanding of your data that naturally results in more reliable, relevant answers.

Using the PowerMetrics MCP server with your AI

You can instruct your AI tool to always refer to the PowerMetrics MCP server by setting up rules/system prompts using this instruction: "When answering questions about data, always use the powermetrics mcp server".

Or, you can refer to the PowerMetrics server on a per-prompt basis only, by including "use powermetrics" or "using powermetrics" in individual prompts. For example:

  • What's trending in my data today, use powermetrics.
  • Using powermetrics, can you tell me why there's a spike in my revenue today?

Connecting the PowerMetrics MCP server to your AI

Here at Klipfolio, we’ve connected our MCP server to Claude (Web and Desktop), Chat GPT, Cursor, Gemini and Gemini CLI, n8n, and Zapier. But, you’re not restricted to these products.

You can connect our MCP server to any AI tool that supports:

  • OAuth authentication
  • Streamable HTTP - use this endpoint: https://mcp.klipfolio.com/api/v1/stream

Please refer to your AI tool’s documentation for instructions on adding an MCP server connection.

Tips and best practices

Start with smaller queries: Start by asking the AI to use list_metrics or get_knowledge_graph_schema to understand what's available before running a heavy execute_metrics_query.

Use the examples query for help in formatting requests: If the AI is struggling with query syntax, explicitly tell it: "Use the get_metrics_query_examples tool to see how to format this request."

Create tags before assigning them: When tagging metrics, dashboards, or data feeds, remember that assign_tags requires an existing tag ID. If the tag doesn't exist yet, call create_tag first, then pass the returned tagId to assign_tags.

Enforce governance: The permission_query_metric_check tool is automatically invoked by most well-behaved agents, but you can explicitly call for it in your system prompt to enforce data governance.

The core toolset

The PowerMetrics MCP server core toolset includes API queries/methods for the following areas:

Metric & Data Exploration

  • execute_metrics_query — The primary tool for retrieving numerical data. It handles aggregations, time-series comparisons, and filtering.
  • get_metrics_query_examples — Returns templates and successful query patterns to help the AI format complex requests.
  • list_metrics — Lists all available metrics in your PowerMetrics account. Use this as a first step before running heavier queries.
  • permission_query_metric_check — A safety tool used by the AI to verify if the current user identity has the required permissions to access specific data.

Knowledge Graph & Semantic Metadata

  • execute_knowledge_graph_query — Queries the "brain" of your PowerMetrics account. It enables the AI to understand how metrics relate to each other (e.g., "Which metrics are affected if Churn increases?").
  • get_knowledge_graph_schema — Provides the structural map of your metrics, dimensions, and entities so the AI knows what questions are possible.

Knowledge Base Documentation

  • retrieve_product_docs — Retrieve information from documentation in the PowerMetrics Knowledge Base. Useful for getting accurate source content for detailed analysis.
  • search_product_docs — Search articles in the PowerMetrics Knowledge Base and return AI-generated answers with source references. Use this to answer questions about PowerMetrics features, configuration, and usage.

Tag & Identity Management

  • get_user_identity — Confirms the authenticated user's details to ensure personal and workspace-level data isolation.
  • create_tag / edit_tag / delete_tag — Enables the AI to organize your metric catalog by managing the taxonomy.
  • assign_tags / unassign_tags — Used to dynamically categorize metrics, dashboards, and data feeds (e.g., "Tag all metrics related to 'Q3 Marketing Campaign' with #Q3-Mktg"). Note: assign_tags requires an existing tagId — use create_tag first if the tag doesn't yet exist.

System prompt suggestions

To help ensure quality interactions and output, we’ve created a set of recommended system prompts for you. Download our recommended system prompts here.

Related articles