Skip to content
MCP server

Data-grounded sprint retro

Data-grounded sprint retrospectives from your Jira, GitHub, and Slack activity.

Runs locallyStatus and history
Install
Pricing
Open source
Runs
Locally
Version
0.1.0
Listing updated
5 days ago

About Data-grounded sprint retro

Data-grounded sprint retro is an open-source MCP server. It runs locally on your machine and is started by your AI client.

Install

Run in a terminal

claude mcp add retro-mcp --env JIRA_API_TOKEN='<JIRA_API_TOKEN>' --env GITHUB_TOKEN='<GITHUB_TOKEN>' --env SLACK_TOKEN='<SLACK_TOKEN>' -- npx -y retro-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "retro-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "retro-mcp"
      ],
      "env": {
        "JIRA_API_TOKEN": "<JIRA_API_TOKEN>",
        "GITHUB_TOKEN": "<GITHUB_TOKEN>",
        "SLACK_TOKEN": "<SLACK_TOKEN>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "retro-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "retro-mcp"
      ],
      "env": {
        "JIRA_API_TOKEN": "<JIRA_API_TOKEN>",
        "GITHUB_TOKEN": "<GITHUB_TOKEN>",
        "SLACK_TOKEN": "<SLACK_TOKEN>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "retro-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "retro-mcp"
      ],
      "env": {
        "JIRA_API_TOKEN": "<JIRA_API_TOKEN>",
        "GITHUB_TOKEN": "<GITHUB_TOKEN>",
        "SLACK_TOKEN": "<SLACK_TOKEN>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "retro-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "retro-mcp"
      ],
      "env": {
        "JIRA_API_TOKEN": "<JIRA_API_TOKEN>",
        "GITHUB_TOKEN": "<GITHUB_TOKEN>",
        "SLACK_TOKEN": "<SLACK_TOKEN>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "retro-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "retro-mcp"
      ],
      "env": {
        "JIRA_API_TOKEN": "<JIRA_API_TOKEN>",
        "GITHUB_TOKEN": "<GITHUB_TOKEN>",
        "SLACK_TOKEN": "<SLACK_TOKEN>"
      }
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Configuration

  • JIRA_BASE_URLYour Jira Cloud site, e.g. https://your-company.atlassian.net. Required for a live retro.
  • JIRA_EMAILAtlassian account email the API token belongs to.
  • JIRA_API_TOKENJira API token from id.atlassian.com. Read-only use.
  • JIRA_BOARD_IDOptional board id to pin when the account has several boards.
  • GITHUB_TOKENOptional GitHub read-only token for PR review latency and reverts.
  • GITHUB_REPOSOptional comma-separated owner/name repos to scope PR analysis.
  • SLACK_TOKENOptional Slack read token to scan sprint channels for blocker and incident language.
  • SLACK_CHANNELSOptional comma-separated Slack channel ids to scan for the sprint window.
  • RETRO_DEMO_MODESet to true to force the synthetic demo sprint even when credentials are present.

Pricing

Open source

Data-grounded sprint retro FAQ

Is Data-grounded sprint retro free?

Yes. Data-grounded sprint retro is open source, so you can use and self-host it for free.

How do I add Data-grounded sprint retro to Claude Code?

Run this command in your terminal: claude mcp add retro-mcp --env JIRA_API_TOKEN='<JIRA_API_TOKEN>' --env GITHUB_TOKEN='<GITHUB_TOKEN>' --env SLACK_TOKEN='<SLACK_TOKEN>' -- npx -y retro-mcp

Where this comes from

  • Description: from the official MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers