Product
Core Platform
Analytics Platform AI SDLC Diagnosis AI Agent MCP Server Keypup API
Capabilities
DORA Metrics Issue Cycle Time Team Benchmarking AI Usage Monitoring
Connect
View Integrations →
Solutions
By Source Platforms
GitHub Reporting Azure DevOps Reporting GitLab Reporting Bitbucket Reporting Jira Reporting
By Goals
AI Usage Monitoring Measure AI Impact Achieve Clean & Consistent Data Achieve Operational Excellence Build Your Own Engineering KPIs
Using MCP / AI
With OpenAI With Claude
Resources
Libraries
Dashboard Library Insights Library
Learn
Blog Customer Stories Changelog
Pricing
Get Started - Free
Log In
MCP Model Context Protocol

Analyze, Build and Manage Keypup
From Your AI Assistant

The Keypup MCP Server

Plug Keypup into Claude, ChatGPT, Cursor, Kiro, VS Code, Gemini CLI or any MCP-compatible AI assistant. Ask questions in plain language, let it explain what your insights show, and have it build and edit your dashboards. It acts as you, with your permissions: no code, no SQL, no complexity.

View Documentation Quick Setup
Claude + 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
User
Turn this into a dashboard for the backend team.
AI
create_dashboard
create_widget
add_dashboard_widget

Done: Backend Delivery is in your sidebar, with merged PRs per month, cycle time, review load and open PRs.

Works with
Claude
ChatGPT
Cursor
Kiro
VS Code
Any MCP Client

What the MCP Server Can Do

Everything you do in the Keypup app, from your AI assistant

Analyze Your Data

Explore datasets and their fields, and run queries with metrics, dimensions and filters, including the insight designer's filters such as "is me" or "in the last N weeks"

Explain Your Insights

Get the exact queries behind an insight or a whole dashboard, dashboard filters included, then check the numbers or break them down further

Explore Your Workspace

Search and count your dashboards, insights, projects and members, with the same visibility as in the app

Manage Your Team

Update your team's settings, invite members, change roles, and enable, disable or track projects

Build Dashboards & Insights

Create, edit, copy and share insights and dashboards, start from Keypup's library of ready-made insights, and arrange them on the grid. Every change is checked before it is saved, so a broken insight never reaches your dashboard.

1

You Ask

"Show me bug resolution time by team"

→
2

AI Orchestrates

Finds your team, the right dataset and the insights involved

→
3

AI Builds & Acts

Runs the queries, or builds the dashboard

→
4

You Get Insights

Clear summary with actionable data

MCP server providing a comprehensive audit of pull requests and issues over 6 months
The MCP server can provide comprehensive audits of your engineering data in seconds

The Kinds of Questions You Can Ask

Real-world requests 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?"
  • "What are my open pull requests?"
  • "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?"

Your Dashboards & Insights

  • "Why did cycle time spike on my Delivery dashboard last week?"
  • "Which of our dashboards use the Commits dataset?"
  • "Build me a dashboard tracking PR cycle time and review load for the backend team, and share it with the team."
AI

Refine iteratively: Once you have results, you can ask follow-ups like "now break that down by repository", "restrict it to the backend team" or "add that as an insight on my Delivery dashboard."

Example query showing bug creation and resolution trends over time using the MCP server
Track trends like bug creation vs. resolution with simple questions

Quick Setup in Minutes

Get started with Keypup MCP server in three simple steps

1

Add the Keypup MCP Server

Add Keypup to your AI assistant with the server URL:

Server URL 
https://hq.keypup.io/mcp
2

Sign In and Authorize

Your AI assistant opens a browser window: sign in to Keypup and authorize access. There is no token to copy, store or rotate.

The AI acts as you, with your permissions: it sees and changes only what you can in the app
3

Start Asking

Check that the Keypup tools are available, then ask away:

"Show me PRs merged this week"
"What does the Cycle Time insight on my Delivery dashboard measure?"
"Build me a dashboard tracking our open bugs"

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

Using an API Token Instead

For an MCP client that does not support OAuth, use a Keypup API token:

  1. Go to Settings → Account → API Token tab
  2. Click "Create token", set a descriptive name (e.g., "MCP - Gemini CLI") and an expiration date
  3. Select the mcp:read scope to let the AI read and query your data, and mcp:write to also let it make changes
  4. Copy the token immediately (shown only once) and add it to your client's configuration:
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.

Need Help?

Check out the complete documentation or contact our support team.

Built with Security First

  • Acts as you: The AI sees and changes only what you can in the app, and the app's roles apply
  • You choose read or write: Grant mcp:read alone for analysis, add mcp:write to allow changes
  • Every change is audited: Changes, and refused attempts, are recorded in your team's audit trail
  • No long-lived secret: OAuth access is authorized in your browser, and API tokens can expire

Most AI clients let you approve each tool call. Keep approval on for the tools that change data, especially deletions and member changes. If you use an API token, treat it like a password and never commit it to version control.

Minutes to Setup

Add the server URL, sign in, start asking. 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, ChatGPT, Cursor, Kiro, VS Code, and any MCP-compatible client.

AI-Powered Intelligence

The AI orchestrates the tools, runs the queries, summarizes the results, and builds the dashboards.

Ready to Run Keypup From Your AI Assistant?

Set up the Keypup MCP server in minutes, explore your engineering analytics conversationally, and let your AI assistant build your dashboards.

View Documentation