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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。