sprinty
A disciplined-sprint MCP server for AI coding agents, providing structured sprint management with immutable append-only ledger, programmatic close-gates, and live dashboard.
README
sprinty
A disciplined-sprint MCP server for AI coding agents — Claude Code, Codex, and Gemini.
Sprinty gives an agent first-class tools to run a sprint with structure that can't silently rot: structured sprint → subsprint → item objects, an immutable append-only ledger anchored to real git commits, programmatic close-gates that re-run your tests before a sprint can close, a regex search over the record, and a live follow-along dashboard.
The point: the agent doesn't drift, and the record doesn't lie. IDs are minted server-side, items
can't exist without gates, done rejects a commit that doesn't exist, and sprint_close refuses
to close while anything is unresolved or a gate fails.
Install
Sprinty ships as a native plugin for each agent. The MCP server itself runs via npx -y sprinty-mcp
(the npm package is sprinty-mcp; the server, tools, and plugins are all named sprinty).
Claude Code — clients/claude/ is a plugin (.claude-plugin/plugin.json) bundling the MCP
server and skills. Add the MCP directly:
claude mcp add sprinty -- npx -y sprinty-mcp
Codex — clients/codex/ is a plugin (.codex-plugin/plugin.json + .mcp.json + skills),
installed through a marketplace (clients/codex/marketplace.json). Or add the server to
~/.codex/config.toml:
[mcp_servers.sprinty]
command = "npx"
args = ["-y", "sprinty-mcp"]
Gemini CLI — clients/gemini/ is an extension (gemini-extension.json + GEMINI.md + skills):
gemini extensions install ./clients/gemini
The skills are authored once in skills/ and symlinked into each client, so all three share one
body of guidance.
The loop
sprint_new(goal)
-> subsprint_new(description, goals[], gates[])
-> add(subsprint, description, code_locations[], gates[])
-> done(commit_id, gate_results[]) | split(...) | deprecate(reason)
-> sprint_close()
Full tool reference: skills/using-sprinty/SKILL.md.
How to run a sprint: skills/how-to-run-a-sprint/SKILL.md.
Storage
One append-only JSONL ledger file per sprint under .sprinty/ in the repo you're working on, with a
.sprinty/current pointer naming the active sprint (this enforces one-open-sprint unicity).
.sprinty/ is per working tree, so git worktrees run independent sprints. It is local state — keep
it gitignored.
Develop
npm install
npm test # builds, then runs unit + e2e tests
npm run test:coverage
npm run build
License
Apache-2.0 © Elie Bursztein
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.