convez.ai
MCP ServerProdutividadeIntermediário
Sprintra-io

Sprintra MCP Server

Sprintra-io/sprintra-mcp

Memória persistente para agentes de IA em coding — sprints, decisões e KB via MCP

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que fornece memória persistente para agentes de IA codificarem com contexto de projeto, sprints e decisões arquiteturais. Integra-se com Claude Code, Cursor e outras ferramentas compatíveis com MCP, evitando reexplicações e mantendo histórico entre sessões.

Instalação

$npx convez-ai Sprintra-io/sprintra-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
3
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 5 meses
Versão
v1.6.2
Issues abertas
1
Contribuidores
2

Casos de uso

  • Manter contexto de projeto entre múltiplas sessões de IA
  • Coordenar trabalho de agentes de IA em sprints e features
  • Armazenar decisões arquiteturais e conhecimento técnico acessível a IA

Veredito

Solução pragmática que resolve um problema real: agentes de IA perdem contexto entre sessões. Implementação limpa (42KB, zero dependências nativas) com múltiplas opções de deployment (cloud ou self-hosted). Bem integrada ao ecossistema MCP e adequada para times que usam agentes de código com frequência.

README

A tradução para o português deste README ainda está na fila.


What is Sprintra?

Sprintra gives your AI coding agent persistent memory — features, architecture decisions, sprint progress, and project context that survive session resets, token limits, and IDE switches.

The problem: Every AI coding session starts from scratch. Your agent doesn't know what you decided last week, what sprint you're in, or what your teammate built yesterday.

The solution: Sprintra's MCP server connects to Claude Code, Cursor, Windsurf, and any MCP-compatible tool. Your agent reads and writes project context automatically — no copy-paste, no re-explaining.

Quick Start

Option 1: Sprintra Cloud (Recommended)

# Install the CLI (42KB, zero native dependencies)
npm install -g @sprintra/cli

# Authenticate
sprintra login

# Auto-configure your AI tool
sprintra connect

Option 2: Self-Hosted

# Scaffold a complete local project with server + dashboard
npx create-sprintra my-project

# Start the server
cd my-project
npm start

# Server + dashboard at http://127.0.0.1:4000

MCP Configuration

Claude Code

{
  "mcpServers": {
    "sprintra": {
      "command": "npx",
      "args": ["@sprintra/cli", "mcp"]
    }
  }
}

Or run: sprintra connect --tool claude-code

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "sprintra": {
      "command": "npx",
      "args": ["@sprintra/cli", "mcp"]
    }
  }
}

Or run: sprintra connect --tool cursor

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):

{
  "mcpServers": {
    "sprintra": {
      "command": "npx",
      "args": ["@sprintra/cli", "mcp"]
    }
  }
}

Windsurf

Run: sprintra connect --tool windsurf

HTTP Transport (Remote)

For remote MCP connections (Claude.ai, mobile):

URL: https://api.sprintra.io/api/mcp
Auth: Bearer <your-token>
Transport: HTTP + SSE

17 MCP Tools

Sprintra uses a consolidated tool pattern (inspired by GitHub's MCP server). Each tool accepts a method parameter to select the operation.

Project Management

ToolMethodsDescription
projectslist, create, update, resolve, get_contextManage projects with tech stack, status, and full context snapshots
featureslist, get_bundle, create, update, save_context, get_contextEpic-level work items with acceptance criteria and AI guidance
storieslist, create, update, batch_updateTasks under features — story, task, bug, chore types
sprintslist, get_current, create, update, assignTime-boxed iterations with progress tracking
releaseslist, create, update, generate_notesRelease milestones with auto-generated release notes

Knowledge & Decisions

ToolMethodsDescription
decisionslist, add, supersede, get_conflicts, resolve_conflictArchitecture Decision Records (ADRs) with AI conflict detection
documentslist, get, create, update, get_versions, restore_version, add_link, get_graphKnowledge base with versioning, templates, and cross-references
noteslist, addQuick capture — ideas, research findings, meeting notes
sessionslist, start, log_message, completeBrainstorming sessions with AI personas

Tracking & Git

ToolMethodsDescription
criteriaadd, remove, update_status, verifyAcceptance criteria management and verification
gitsync, link, unlink, get_status, get_feature_statsGit commit tracking with AI authorship detection
dependenciesadd, remove, get_graphFeature dependency tracking with cycle detection
work_sessionslist, start, end, get_active, list_activity, list_traces, deltaCoding session tracking with context handoff
commentslist, create, update, deleteThreaded comments on any entity
custom_fieldsmanage, set, getCustom metadata fields

AI Intelligence

ToolMethodsDescription
aiget_next_work, report_progress, get_guidance, generate_briefingAI-powered recommendations, progress tracking, and context recovery
pull_requestslist, get_story_prsGitHub PR tracking and auto-linking

Example Prompts

Once connected, try these in Claude Code or Cursor:

"Create a Sprintra project for this repo"

"Capture a feature: user authentication with OAuth and email/password"

"What should I work on next?"

"Record a decision: we chose PostgreSQL over MongoDB for relational order data"

"Give me a standup report"

"What changed since my last session?"

8 AI Skills (Slash Commands)

Install workflow skills for guided project management:

sprintra skills install --all
SkillTriggerDescription
Capture Feature/capture [idea]Break down an idea into features, stories, and criteria
Record Decision/decide [topic]Create an Architecture Decision Record
Standup Report/standupAuto-generate standup from recent work
Wrap Session/wrapSave context for seamless session resume
Sprint Review/sprint-reviewReview sprint progress with metrics
Brainstorm/brainstorm [topic]AI-powered brainstorming with personas
Implement Feature/implement [id]Start implementation with full context loaded
Sprint Planning/sprint-planPlan sprints with AI recommendations

Dashboard

Sprintra includes a full web dashboard with 20+ views:

  • Kanban Board — drag-and-drop story management
  • Sprint Tracker — progress bars, velocity charts, burndown
  • Roadmap — phase timeline with feature grouping
  • Knowledge Base — Confluence-style docs with versioning
  • Decisions — ADR log with conflict detection
  • Reports — burndown, velocity, DORA metrics
  • Activity Feed — real-time project activity

Cloud: app.sprintra.io Self-hosted: http://127.0.0.1:4000 after npm start

Pricing

PlanPriceIncludes
Solo PilotFree forever2 projects, unlimited stories, all MCP tools, all skills
Team$5/seat/month10 projects, AI features, team collaboration, priority support
EnterpriseCustomOn-premise, dedicated infra, custom SLA

Links

License

The Sprintra MCP server documentation in this repository is MIT licensed. The Sprintra server, dashboard, and CLI are proprietary software — see sprintra.io/pricing for plans.

Ver o original no GitHub

Bom para

Relacionados