Sprinty is an MCP server enabling AI agents to run disciplined coding sprints with structured tracking, gating, and a live dashboard. It provides:
Sprint Lifecycle: Start (sprint_new), resume (sprint_resume), detach (sprint_detach), list (sprint_list), close (sprint_close) with gate checks, and archive (sprint_archive) sprints. Specify Git and data directories.
Orientation & Navigation: Get sprint overviews (overview), view the next active work items (next) including blocked and high‑priority items, and search the sprint ledger via regex (search).
Subsprint Management: Create feature‑sized subsprints (subsprint_new) with goals and gates, list them (subsprint_list), and retrieve details (subsprint_get).
Work Item Tracking: Add atomic items (item_add) with title, description, code locations, gates, and dependencies. Retrieve, update metadata (item_update), mark done (item_done) with commit ID and gate evidence, split oversized items into new subsprints (item_split), and deprecate items (item_deprecate).
Notes: Add, list, get, and update notes attached to items (note_add, note_list, note_get, note_update).
Artifacts: Manage file artifacts linked to sprints/items: add, list, get, update path/title/related items (artifact_add, artifact_list, artifact_get, artifact_update).
Changelog & Reporting: Generate SemVer Markdown changelogs with change‑map and coverage tables (changelog).
Dashboard: Retrieve dashboard URL/port (dashboard_info) and restart it (dashboard_restart).
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@sprinty Create a new sprint for implementing user authentication"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Sprinty is an MCP server for running disciplined coding sprints with AI agents. It gives agents server-minted sprint, subsprint, and item IDs; explicit dependencies; gate evidence; Git-backed change maps; SemVer changelogs; and a local dashboard so humans can watch the work while it happens.
Sprinty is published to npm as sprinty-mcp. The npm package is the MCP server. Claude and Codex
plugin installs are distributed from this Git repository through each client's marketplace system.
MCP-only install:
claude mcp add sprinty -- npx -y sprinty-mcpPlugin install, with Sprinty skills plus the MCP server:
claude plugin marketplace add ebursztein/sprinty
claude plugin install sprinty@sprintyThe Claude marketplace manifest is .claude-plugin/marketplace.json; the plugin bundle is
clients/claude/.
MCP-only install:
codex mcp add sprinty -- npx -y sprinty-mcpPlugin install, with Sprinty skills plus the MCP server:
codex plugin marketplace add ebursztein/sprinty
codex plugin add sprinty@sprintyThe Codex marketplace manifest is .agents/plugins/marketplace.json; the plugin bundle is
plugins/sprinty/. Codex does not currently use an OpenAI npm plugin package for this flow.
Use the MCP server directly from npm:
npx -y sprinty-mcpThe repository also includes a Gemini extension in clients/gemini/ for clients that install local
Gemini extensions.
Sprinty ships a portable Agent Plugins package at the repository root
(plugin.json, mcp.json, skills/), so any conformant client can load the skills and the MCP
server without a client-specific bundle. Follow your client's plugin install instructions and point
it at this repository.
Claude Code and Gemini CLI are not Agent Plugins clients today; they use the bundles above.
Configure a stdio MCP server with:
{
"command": "npx",
"args": ["-y", "sprinty-mcp"]
}Related MCP server: ForgeSwarm
Sprinty never guesses the repository from the MCP server process cwd. Start or resume with explicit paths:
sprint_new({ goal, git_dir, data_dir, context_notes? })
sprint_resume({ git_dir, data_dir })Use a worktree-local, gitignored data_dir, usually <git_dir>/.sprinty. When data_dir is
omitted and git_dir is provided, Sprinty uses <git_dir>/.sprinty. sprint_new and
sprint_resume return the dashboard URL. Call info({ git_dir }) first for startup orientation and
compact sprint rows. Use info({ workspace_dirs: [...] }) when you need to inspect multiple Sprinty
data dirs together, then sprint_resume({ git_dir, data_dir }).
Tool | Purpose |
| Startup orientation before binding, including sprint rows, resume/create help, and dashboard state. |
| Start a sprint with explicit |
| Reattach this MCP session to an existing sprint. |
| Clear this MCP process binding and stop the dashboard. |
| Close only after all work is resolved, changelog exists, gates pass, and coverage is supplied. |
| Archive an active sprint with a recovery reason. |
| Compact sprint summary for orientation. |
| Compact active work window with current, next, blocked, relations, notes, and artifacts. |
| Regex search over the immutable sprint ledger. |
| Generate SemVer Markdown and return the path. |
| Create a feature-sized unit of work. |
| List subsprints with compact item counts. |
| Read one subsprint and its item rows. |
| Create one atomic, gated item. |
| Read full item detail. |
| Update item metadata, priority, notes, or dependency edges. |
| Complete an item with a real commit, gate evidence, and changelog entry. |
| Resolve an oversized item by creating a seeded subsprint. |
| Drop an item with an explicit reason, or pass a subsprint id to drop it and its open items. |
| Attach a note to an item. |
| List notes for an item. |
| Read one note. |
| Update one note. |
| Attach a durable file path to the sprint. |
| List active artifacts. |
| Read one artifact record. |
| Update artifact metadata. |
| Report the current dashboard URL and port. |
| Restart the dashboard and return the new URL and port. |
Publishing is gated by tests. The GitHub Release workflow runs npm ci, npm test, and only then
npm publish --access public.
Local checks:
npm test
npm run typecheckApache-2.0
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
The project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ebursztein/sprinty'
If you have feedback or need assistance with the MCP directory API, please join our Discord server