Native MCP — drop one config block

Sprint Tickets,
In Claude Desktop.

Connect via MCP at mcp.sprintflint.com. One JSON block, one bearer token, and Claude can list sprints, file tickets, and post comments without leaving the chat.

5-min setup
REST API + /llms.txt
No card to start

Why Claude Desktop + SprintFlint

Built around how your AI actually works.

Other trackers

  • No native MCP — agent has to scrape HTML or call REST manually
  • Auth flows that break the agent loop
  • Schemas not designed for tool-calling
  • Per-seat pricing for the agent's connection

SprintFlint

  • Public /llms.txt — agents discover the API instantly
  • Bearer-token auth, one header, no OAuth dance
  • REST endpoints designed for agent-first workflows
  • £5/user/mo, free tier covers your first 300 tickets
Step 1 — Token

Generate the API token.

# In SprintFlint: Profile → API Token → Generate
# The same token works for REST API and MCP.
Step 2 — Add MCP server

Drop the MCP server into Claude Desktop config.

Open ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or the equivalent on your OS. Add the SprintFlint server block, then restart Claude Desktop.

{
  "mcpServers": {
    "sprintflint": {
      "url": "https://mcp.sprintflint.com",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN"
      }
    }
  }
}
Step 3 — Chat

Ask Claude about your sprint.

"What's the active sprint and what's still open?"
Claude calls list-sprints and list-issues, summarises the state, and offers to file follow-up issues right from the chat.

  • Agent reads sprint backlog
  • Auto-updates status when work begins
  • Posts progress comments as it goes
  • Pairs with Autoplay for full one-click PRs

Claude Already Knows Your Code.

Now it can read your sprint.
300 free tickets. No card. Native MCP.