MCP Model Context Protocol

Your Engineering Data,
Any AI Client

Introducing the Keypup MCP Server

Plug Keypup's engineering analytics directly into Claude, Cursor, Kiro, ChatGPT Desktop, or any MCP-compatible AI assistant. Ask questions in plain language, and let the AI build and run the queries for you—no code, no SQL, no complexity.

Claude Desktop + Keypup MCP
User
AI
AI

I'll query your Keypup data to get the monthly merged PR count. Let me fetch that for you.

query_dataset
list_dataset_fields
Month Merged PRs
2026-06 47
2026-05 52
2026-04 61
2026-03 58
Works with
Claude Desktop
Cursor
Kiro
ChatGPT Desktop
Any MCP Client

What the MCP Server Can Do

A focused toolkit that lets AI explore and query your engineering data

Discover Companies

List the companies (teams) you belong to and access your organizational data

Explore Datasets

Browse available datasets: issues & PRs, commits, comments, reviews, activity events

Discover Operators

List available functions and operators for building metrics, dimensions, and filters

Run Queries

Execute aggregated queries with metrics, dimensions, filters, sorting, and pagination

1

You Ask

"Show me bug resolution time by team"

2

AI Orchestrates

Lists companies, picks dataset, looks up fields

3

AI Builds & Runs

Constructs query, executes, and formats results

4

You Get Insights

Clear summary with actionable data

The Kinds of Questions You Can Ask

Real-world queries that the MCP server handles seamlessly

Delivery & Throughput

  • "How many pull requests did we merge each month over the last 6 months?"
  • "What's our weekly issue closing rate this quarter?"
  • "How many commits were made per author last month?"

Cycle Time & Performance

  • "What's the average time between PR creation and merge over the last 12 weeks?"
  • "Show me the review turnaround time trend for the last 3 months."
  • "Which repositories have the slowest cycle time?"

Quality & Process

  • "How many bugs were raised vs. closed each week this quarter?"
  • "What proportion of our pull requests resolve at least one issue?"
  • "How many PRs were merged without a review?"

Workload & Collaboration

  • "Who are our most active reviewers this month?"
  • "How is work distributed across the team right now?"
  • "How many comments do our pull requests receive on average?"

Open-Ended Exploration

  • "Summarize our engineering activity over the last month."
  • "Compare open vs. closed issues over time."
  • "What labels are most common on our issues?"
AI

Refine iteratively: Once you have results, you can ask follow-ups like "now break that down by repository" or "restrict it to the backend team."

Quick Setup in Minutes

Get started with Keypup MCP server in three simple steps

1

Generate API Token

Create a secure API token with the right permissions:

  1. Go to Settings → Account → API Token tab
  2. Click "Create token" and set a descriptive name (e.g., "MCP - Claude Desktop")
  3. Set an expiration date (strongly recommended for security)
  4. Select scopes: Reports read + Companies read
  5. Copy the token immediately (shown only once)
Follow the principle of least privilege: only grant the scopes you need
2

Configure MCP Client

Add Keypup to your MCP client configuration (e.g., Claude Desktop, Cursor):

mcp.json
{
  "mcpServers": {
    "keypup": {
      "url": "https://hq.keypup.io/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN_HERE"
      }
    }
  }
}

Important: Replace YOUR_API_TOKEN_HERE with your actual token. Keep the Bearer prefix.

3

Start Asking Questions

Restart your MCP client and verify the Keypup tools are available:

"List my Keypup companies"
"Show me PRs merged this week"
"What are the available datasets?"

You're all set! The AI will automatically orchestrate the right tools to answer your questions.

Need Help?

Check out the complete documentation or contact our support team.

Built with Security First

  • Read-only access: MCP tools never modify your data
  • Token-based auth: Scoped permissions following least privilege principle
  • Data isolation: Queries are automatically scoped to your companies
  • Expiring tokens: Set time-limited access with periodic rotation

Treat your API token like a password. Store it securely in your local MCP client configuration and never commit it to version control.

Minutes to Setup

Generate a token, add config, start querying. No complex installation required.

Zero Learning Curve

Ask in plain English—no SQL, no GraphQL, no query language to learn.

Universal Compatibility

Works with Claude, Cursor, Kiro, ChatGPT Desktop, and any MCP-compatible client.

AI-Powered Intelligence

The AI automatically orchestrates tools, builds queries, and summarizes results.

Ready to Query Your Data with AI?

Set up the Keypup MCP server in minutes and start exploring your engineering analytics conversationally.