Skip to main content
Glama
delorenj

Wise Mise MCP

by delorenj
README.md
# 🎯 Wise Mise MCP

> **The intelligent MCP server that transforms mise task management with AI-powered analysis and domain expertise**

[![PyPI version](https://badge.fury.io/py/wise-mise-mcp.svg)](https://badge.fury.io/py/wise-mise-mcp)
[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
[![Documentation](https://img.shields.io/badge/docs-readthedocs-blue.svg)](https://wise-mise-mcp.readthedocs.io)
[![Deploy to Smithery](https://smithery.ai/badge)](https://smithery.ai/server/wise-mise-mcp)

**Stop wrestling with mise configuration.** Wise Mise MCP brings enterprise-grade intelligence to your [mise](https://mise.jdx.dev/) workflow, automatically analyzing your project structure and creating perfectly organized, maintainable task architectures that scale with your development needs.

## Why Wise Mise MCP?

**🧠 Intelligent Task Analysis**

- Automatically analyzes your project structure to extract meaningful tasks
- Understands 10+ technology domains (build, test, lint, deploy, CI/CD, etc.)
- Suggests optimal task organization and dependency patterns

**πŸ—οΈ Architecture-Aware**

- Follows mise best practices with hierarchical task organization
- Supports complex dependency graphs with source/output tracking
- Optimizes for incremental builds and performance

**πŸ”§ Developer Experience**

- Integrates seamlessly with any MCP-compatible client
- Provides detailed explanations and recommendations
- Reduces cognitive load of task management

## Quick Start

### Using UVX (Recommended)

```bash
# Just run this to start Wise Mise MCP with UVX
uvx wise-mise-mcp

# Or install globally
uv tool install wise-mise-mcp
```

### Traditional pip

```bash
pip install wise-mise-mcp
```

### Add to Your MCP Client

Add to your MCP client configuration (e.g., Claude Desktop):

```json
{
  "mcpServers": {
    "wise-mise-mcp": {
      "command": "uvx",
      "args": ["wise_mise_mcp"]
    }
  }
}
```

### Deploy with Smithery (One-Click Deployment)

[![Deploy to Smithery](https://smithery.ai/badge)](https://smithery.ai/server/wise-mise-mcp)

Deploy Wise Mise MCP instantly to Smithery's cloud infrastructure with one click. Smithery provides managed MCP server hosting with built-in monitoring, scaling, and zero-configuration deployment.

**Quick Smithery Deployment:**
1. Click the "Deploy to Smithery" badge above
2. Connect your GitHub account (if needed)
3. Your MCP server will be automatically deployed and configured
4. Use the provided endpoint in your MCP client configuration

**Benefits of Smithery Deployment:**
- βœ… Zero server management overhead
- βœ… Automatic scaling and load balancing  
- βœ… Built-in monitoring and health checks
- βœ… Global CDN for low-latency access
- βœ… Automatic SSL/TLS encryption
- βœ… Integration with popular MCP clients

## What Makes It "Wise"?

Wise Mise MCP goes beyond simple task creation. It brings intelligence to your mise configuration:

### πŸ” Project Analysis

```python
# Analyzes your entire project structure
analyze_project_for_tasks("/path/to/project")
# Returns strategically organized tasks based on your tech stack
```

### πŸ•ΈοΈ Dependency Mapping

```python
# Traces complex task relationships
trace_task_chain("/path/to/project", "build:prod")
# Visualizes the complete execution flow
```

### ⚑ Smart Task Creation

```python
# Intelligently places tasks in the right domain
create_task(
    project_path="/path/to/project",
    task_description="Run TypeScript type checking",
    # Automatically suggests: lint:types with proper dependencies
)
```

## Core Features

### 🎯 **Domain Experts**

- **Build**: Frontend/Backend build systems, bundlers, compilers
- **Test**: Unit, integration, e2e testing strategies
- **Lint**: Code quality, formatting, static analysis
- **Deploy**: CI/CD, containerization, release management
- **Database**: Migrations, seeding, schema management
- **Development**: Local dev servers, hot reloading, debugging

### πŸ“Š **Intelligent Analysis**

- **Complexity Assessment**: Automatically categorizes tasks as Simple, Moderate, or Complex
- **Dependency Detection**: Identifies natural task relationships
- **Source/Output Tracking**: Optimizes incremental builds
- **Redundancy Elimination**: Finds and removes duplicate tasks

### πŸ”§ **MCP Tools**

| Tool                         | Purpose                                        |
| ---------------------------- | ---------------------------------------------- |
| `analyze_project_for_tasks`  | Extract strategic tasks from project structure |
| `trace_task_chain`           | Map task dependencies and execution flow       |
| `create_task`                | Add new tasks with intelligent placement       |
| `prune_tasks`                | Remove outdated or redundant tasks             |
| `validate_task_architecture` | Ensure configuration follows best practices    |
| `get_task_recommendations`   | Get suggestions for optimization               |

## Example Workflows

### Analyzing a New Project

```bash
# Let Wise Mise MCP analyze your project
> analyze_project_for_tasks("./my-app")

βœ… Detected: Next.js + TypeScript + Prisma
πŸ“‹ Suggested Tasks:
  β”œβ”€β”€ build:dev (next dev)
  β”œβ”€β”€ build:prod (next build)
  β”œβ”€β”€ test:unit (jest)
  β”œβ”€β”€ test:e2e (playwright)
  β”œβ”€β”€ lint:code (eslint)
  β”œβ”€β”€ lint:types (tsc --noEmit)
  β”œβ”€β”€ db:migrate (prisma migrate)
  └── deploy:vercel (vercel deploy)
```

### Understanding Task Dependencies

```bash
# Trace the execution flow
> trace_task_chain("./my-app", "deploy:prod")

πŸ•ΈοΈ Task Chain for deploy:prod:
  1. lint:types (TypeScript check)
  2. test:unit (Unit tests)
  3. build:prod (Production build)
  4. deploy:prod (Deploy to production)

πŸ’‘ Recommendation: Add test:e2e before deploy:prod
```

### Smart Task Creation

```bash
# Describe what you want, get intelligent suggestions
> create_task(
    project_path="./my-app",
    task_description="Generate API documentation from OpenAPI spec"
  )

🧠 Analysis: Documentation generation task
πŸ“ Suggested Placement: docs:api
πŸ”— Dependencies: build:prod (for spec generation)
πŸ“ Suggested Implementation:
  [tasks.docs.api]
  run = "swagger-codegen generate -i ./openapi.json -l html2 -o ./docs/api"
  sources = ["src/api/**/*.ts", "openapi.json"]
  outputs = ["docs/api/**/*"]
```

## Architecture Philosophy

Wise Mise MCP follows a **Domain-Driven Design** approach to task organization:

### πŸ›οΈ **Hierarchical Structure**

- **Level 1**: Domain (build, test, lint, etc.)
- **Level 2**: Environment/Type (dev, prod, unit, e2e)
- **Level 3**: Specific Implementation (server, client, api)

### πŸ”„ **Dependency Patterns**

- **Sequential**: `lint β†’ test β†’ build β†’ deploy`
- **Parallel**: `test:unit` + `test:e2e` β†’ `deploy`
- **Conditional**: `deploy:staging` β†’ `test:smoke` β†’ `deploy:prod`

### ⚑ **Performance Optimization**

- **Source Tracking**: Only rebuild when sources change
- **Output Caching**: Reuse previous build artifacts
- **Incremental Builds**: Support for modern build tools

## Technology Support

Wise Mise MCP includes expert knowledge for:

**Frontend**: React, Vue, Angular, Svelte, Next.js, Nuxt, Vite, Webpack
**Backend**: Node.js, Python, Go, Rust, Java, .NET, PHP
**Databases**: PostgreSQL, MySQL, MongoDB, Redis, Prisma, TypeORM
**Testing**: Jest, Vitest, Cypress, Playwright, PyTest, Go Test
**CI/CD**: GitHub Actions, GitLab CI, CircleCI, Jenkins
**Deployment**: Docker, Kubernetes, Vercel, Netlify, AWS, GCP

## Contributing

We welcome contributions! See our [Contributing Guide](CONTRIBUTING.md) for details.

### Quick Start for Contributors

```bash
# Clone and setup with UV
git clone https://github.com/delorenj/wise-mise-mcp
cd wise-mise-mcp
uv sync

# Run tests
uv run pytest

# Format code
uv run black .
uv run ruff check --fix .
```

## License

MIT License - see [LICENSE](LICENSE) for details.

## Support

- **Documentation**: [Full API Documentation](https://wise-mise-mcp.readthedocs.io/)
- **Issues**: [GitHub Issues](https://github.com/delorenj/wise-mise-mcp/issues)
- **Discussions**: [GitHub Discussions](https://github.com/delorenj/wise-mise-mcp/discussions)

---

_Built with ❀️ by [Jarad DeLorenzo](https://github.com/delorenj) and the open source community_

TDQS

A3.7/5.0

Scored across 10 tools

Disambiguation4/5

Tools generally have distinct purposes, but 'get_task_recommendations' and 'mise_task_expert_guidance' both offer advice, and 'trace_task_chain' overlaps slightly with 'task_chain_analyst'. Descriptions help differentiate them.

Naming Consistency4/5

Most tools use a consistent verb_noun pattern (e.g., create_task, prune_tasks), but 'task_chain_analyst' and 'mise_task_expert_guidance' break the pattern with noun-first or lengthy names.

Tool Count5/5

10 tools cover the domain well without being excessive. Each tool has a clear role in task management, from creation to analysis to cleanup.

Completeness4/5

The set includes creation, removal, pruning, validation, tracing, and guidance. However, an explicit tool for listing all tasks or updating existing tasks is missing, which is a minor gap.

Maintenance

ActivityInactive
ResponsivenessNo issues