| Name | automagik-tools JSON |
| Version |
0.7.3
JSON |
| download |
| home_page | None |
| Summary | A monorepo package for MCP tools with dynamic loading capabilities - featuring Evolution API v2 WhatsApp integration |
| upload_time | 2025-07-09 22:45:08 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.12 |
| license | MIT |
| keywords |
mcp
tools
ai
agents
fastmcp
whatsapp
discord
notion
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
<p align="center">
<img src=".github/images/automagik_logo.png" alt="AutoMagik Tools Logo" width="600"/>
</p>
# 🪄 AutoMagik Tools
## MCP Agents That Learn Your APIs Automagikally
Drop any OpenAPI spec → Get an intelligent MCP agent that learns how you work and gets better with every interaction. Export to code when you're ready to customize.
Born from our daily work at [Namastex Labs](https://www.linkedin.com/company/namastexlabs), AutoMagik Tools creates **self-evolving agents** that turn any API into a natural language interface.
## 🧠 Self-Learning MCP Agents
Unlike static tools, AutoMagik agents **remember and adapt**:
```bash
# First time: "How much did I sell last month?"
# Agent learns your sales endpoints, date formats, and preferences
# By the 10th interaction:
# Agent already knows exactly which data you want and how you like it formatted
uvx automagik-tools tool automagik -t sse --port 8000
```
**Three Intelligence Modes:**
- 🔧 **Standard**: Full schema access for precise control
- 📋 **Markdown**: Agent processes noisy JSON into clean, readable output (powered by GPT-4.1-nano)
- 💬 **Genie**: Natural language interface - just describe what you need
*Powered by GPT-4.1 family models for cost-effective agentic behavior and reliable API reasoning.*
## 🚀 From Any API to Smart Agent
Turn any OpenAPI spec into an intelligent agent:
```bash
# Discord API becomes a smart agent
uvx automagik-tools openapi \
https://raw.githubusercontent.com/discord/discord-api-spec/main/specs/openapi.json \
-t sse --port 8001
# Share this agent with your entire team via SSE
# Team members can access the same learning agent at http://localhost:8001
```
**Now you can say:**
- "Show me unread messages from the design team"
- "Schedule a voice call for 3pm in the dev channel"
- "Find all threads where someone mentioned the new feature"
Agent learns your patterns, server preferences, and communication style.
## 🧞 Genie: Universal MCP Orchestrator
**Genie connects any MCP servers and orchestrates them with persistent memory**:
```bash
# Run Genie with memory-based agents
uvx automagik-tools tool genie -t sse --port 8000
```
### Configure Genie with Multiple MCP Servers
Genie can orchestrate any combination of MCP servers. Configure via environment variables:
```bash
# Method 1: JSON configuration for multiple servers
export GENIE_MCP_CONFIGS='{
"agent-memory": {
"url": "http://192.168.112.149:8000/sse",
"transport": "sse"
},
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/allowed/directory"],
"env": {}
},
"github": {
"command": "uvx",
"args": ["mcp-server-git"],
"env": {"GITHUB_TOKEN": "your-token"}
}
}'
# Method 2: AutoMagik-specific shorthand
export GENIE_AUTOMAGIK_API_KEY="your-api-key"
export GENIE_AUTOMAGIK_BASE_URL="http://localhost:8881"
export GENIE_AUTOMAGIK_TIMEOUT="600"
```
### Add Genie to Claude/Cursor (Universal Orchestrator)
[](https://cursor.com/install-mcp?name=discord&config=eyJjb21tYW5kIjoidXZ4IGF1dG9tYWdpay10b29sc0BsYXRlc3Qgc2VydmUgLS1vcGVuYXBpLXVybCBodHRwczovL3Jhdy5naXRodWJ1c2VyY29udGVudC5jb20vZGlzY29yZC9kaXNjb3JkLWFwaS1zcGVjL21haW4vc3BlY3Mvb3BlbmFwaS5qc29uIC0tdHJhbnNwb3J0IHN0ZGlvIiwiZW52Ijp7IkRJU0NPUkRfVE9LRU4iOiJZT1VSX0JPVF9UT0tFTiJ9fQ%3D%3D)
```json
{
"mcpServers": {
"genie": {
"command": "uvx",
"args": [
"automagik-tools@latest",
"serve",
"--tool",
"genie",
"--transport",
"stdio"
],
"env": {
"OPENAI_API_KEY": "your-openai-key",
"GENIE_MCP_CONFIGS": "{\"agent-memory\":{\"url\":\"http://192.168.112.149:8000/sse\",\"transport\":\"sse\"},\"filesystem\":{\"command\":\"npx\",\"args\":[\"-y\",\"@modelcontextprotocol/server-filesystem\",\"/allowed/path\"],\"env\":{}}}"
}
}
}
}
```
**Now in Claude/Cursor, Genie can:**
- "Use the memory agent to remember this conversation"
- "Check the filesystem for project files and analyze them with the memory agent"
- "Coordinate between multiple tools to complete complex tasks"
## 🌟 Featured: AutoMagik Orchestration
Enterprise-grade agent orchestration that speaks human:
```bash
uvx automagik-tools tool automagik --transport sse --port 8000
```
**Real examples from our users:**
- "Monitor inventory across all warehouses and alert me when Corona drops below 10k units"
- "Generate weekly performance reports and send to regional managers"
- "Set up automated quality checks for next month's production runs"
- "Track competitor pricing and notify me of changes above 5%"
💬 Natural Language • 🧠 Memory & Learning • 🔄 Task Orchestration • 🏗️ Framework Agnostic • 👩💻 Export to Code
## 🚀 Quick Start
### Environment Setup
Create a `.env` file with your API keys:
```bash
# .env
OPENAI_API_KEY=sk-your-openai-key-here
AUTOMAGIK_API_KEY=your-automagik-api-key
AUTOMAGIK_BASE_URL=http://localhost:8881
# Enable JSON to Markdown processing (optional)
ENABLE_JSON_PROCESSING=true
JSON_PROCESSOR_MODEL=gpt-4.1-nano
```
### Copy this into Claude/Cursor for instant API orchestration:
[](https://cursor.com/install-mcp?name=automagik&config=eyJjb21tYW5kIjoidXZ4IGF1dG9tYWdpay10b29sc0BsYXRlc3Qgc2VydmUgLS10b29sIGF1dG9tYWdpayAtLXRyYW5zcG9ydCBzdGRpbyIsImVudiI6eyJBVVRPTUFHSUtfQUdFTlRTX0FQSV9LRVkiOiJZT1VSX0FQSV9LRVkiLCJBVVRPTUFHSUtfQUdFTlRTX0JBU0VfVVJMIjoiaHR0cDovL2xvY2FsaG9zdDo4ODgxIiwiQVVUT01BR0lLX0FHRU5UU19PUEVOQVBJX1VSTCI6Imh0dHA6Ly9sb2NhbGhvc3Q6ODg4MS9hcGkvdjEvb3BlbmFwaS5qc29uIn19)
```json
{
"mcpServers": {
"automagik": {
"command": "uvx",
"args": [
"automagik-tools@latest",
"serve",
"--tool",
"automagik",
"--transport",
"stdio"
],
"env": {
"AUTOMAGIK_API_KEY": "YOUR_API_KEY",
"AUTOMAGIK_BASE_URL": "http://localhost:8881",
"OPENAI_API_KEY": "YOUR_OPENAI_API_KEY"
}
}
}
}
```
**Where to add:**
- **Claude Desktop**: Settings → Developer → Edit Config
- **Cursor**: `~/.cursor/mcp.json`
### Test any API instantly:
```bash
# Jira becomes conversational project management
OPENAI_API_KEY=your_key JIRA_API_TOKEN=your_token uvx automagik-tools serve \
--openapi-url https://dac-static.atlassian.com/cloud/jira/platform/swagger-v3.v3.json \
--transport sse --port 8002
# Shopify for e-commerce automation
OPENAI_API_KEY=your_key SHOPIFY_ACCESS_TOKEN=your_token uvx automagik-tools serve \
--openapi-url https://shopify.dev/docs/api/admin-rest/2023-04/openapi.json \
--transport sse --port 8003
# SSE mode allows your team to share the same learning agent
```
## 📋 Real-World Agent Examples
### Genie Orchestrating Multiple Tools
**Personal Automation:**
- "Use memory agent to remember my GitHub preferences, then check my repos and create a weekly summary"
- "Process these expense receipts with the filesystem tool and store insights in memory"
- "Monitor my crypto portfolio with the trading API and remember my risk preferences"
**Team Coordination:**
- "Coordinate between Slack and Linear to set up daily standups for the design team"
- "Use the file system to track project deadlines and notify stakeholders via Discord"
- "Analyze customer feedback from multiple sources and create sentiment reports"
**Business Intelligence:**
- "Compare Q4 sales across all regions using the database and memory tools"
- "Generate inventory reports by coordinating warehouse APIs and document storage"
- "Monitor competitor pricing across platforms and update my preference memory"
The agent **learns your patterns** - after a few interactions, it knows exactly how you like your data formatted, which metrics matter most, and when to proactively alert you.
## 🛠️ Advanced Usage
### Multiple Server Configurations
Configure Genie with different MCP server combinations:
```bash
# Development setup with local tools
export GENIE_MCP_CONFIGS='{
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/home/user/projects"],
"env": {}
},
"git": {
"command": "uvx",
"args": ["mcp-server-git"],
"env": {"GIT_AUTHOR_NAME": "Your Name"}
}
}'
# Production setup with external services
export GENIE_MCP_CONFIGS='{
"automagik": {
"command": "uvx",
"args": ["automagik-tools", "tool", "automagik", "--transport", "stdio"],
"env": {
"AUTOMAGIK_API_KEY": "prod-key",
"AUTOMAGIK_BASE_URL": "https://api.yourcompany.com"
}
},
"slack": {
"command": "docker",
"args": ["run", "-i", "--rm", "-e", "SLACK_BOT_TOKEN", "mcp/slack"],
"env": {"SLACK_BOT_TOKEN": "xoxb-your-token"}
}
}'
```
### Dynamic MCP Server Connection
You can also pass MCP server configurations directly to Genie via the `ask_genie` tool:
```json
{
"tool": "ask_genie",
"arguments": {
"query": "List all my GitHub repositories and remember my coding preferences",
"mcp_servers": {
"github": {
"command": "uvx",
"args": ["mcp-server-git"],
"env": {"GITHUB_TOKEN": "your-token"}
},
"memory": {
"url": "http://localhost:8000/sse",
"transport": "sse"
}
}
}
}
```
## 🎯 Why Intelligent Agents Matter
**The old way:** Hours writing API integrations, maintaining complex schemas, fighting with documentation. When APIs change, everything breaks.
**The AutoMagik way:**
1. **Point** to any OpenAPI spec
2. **Ask** in natural language what you need
3. **Learn** as the agent adapts to your workflow
4. **Export** to code when you need customization
When your needs evolve, your agent **learns and remembers**.
## 🛠️ Built-in Tools
### AutoMagik 🤖
AI orchestration that speaks human:
```bash
# Quick test with SSE
uvx automagik-tools tool automagik --transport sse --port 8000
```
**What you can do:**
- ✨ Use Spark to spawn hives of agents in seconds
- 🔄 Schedule recurring AI tasks and automations
- 💬 Natural language task descriptions
- 🏗️ Works with any AI framework
### Genie 🧞
Universal MCP orchestrator with persistent memory:
```bash
# Run as SSE server for team sharing
uvx automagik-tools tool genie --transport sse --port 8000
```
**Capabilities:**
- 🧠 Persistent memory across all sessions
- 🔗 Connect to unlimited MCP servers
- 💬 Natural language task coordination
- 👥 Shared learning across team members
### AutoMagik Workflows 🚀
Smart Claude workflow orchestration with real-time progress tracking:
```bash
# Execute Claude Code workflows with progress monitoring
uvx automagik-tools tool automagik-workflows --transport stdio
```
**Features:**
- 🚀 **Run Claude Code Workflows**: Execute workflows with progress reporting
- 📊 **Real-time Status**: Track workflow completion with visual progress
- 📋 **List Workflows**: Discover available workflows and recent runs
- 🔄 **Status Monitoring**: Get detailed workflow execution status
### Evolution API (WhatsApp) 📱
Complete WhatsApp automation:
- Send/receive messages
- Media support (images, documents)
- Group management
- Status updates
## 🚀 The Future: Self-Maintaining Tools
Our roadmap includes agents that:
- **Auto-discover** API endpoints without OpenAPI specs
- **Auto-evolution**: Tools that update and adapt when APIs change
- **Self-debug** and report issues back to maintainers
- **Collaborate** with other agents for complex workflows
- **Generate** their own tools from natural language descriptions
**Production Deployments (Coming Soon):**
- 🐳 **Docker**: One-click deployment scripts for containerized agents
- ☁️ **Cloud Ready**: Deploy to AWS, Google Cloud, Azure with pre-built templates
- 🌐 **Team Sharing**: VPS and network deployments for organization-wide agent access
- 📈 **Scalable**: Load balancing and auto-scaling for high-demand agents
*Coming 2025: A hive of AI agents maintaining this entire codebase - reporting bugs, implementing features, and keeping users happy. All open source.*
## 📋 Real-World Examples
### Genie with Memory Agent
```json
{
"mcpServers": {
"genie_with_memory": {
"command": "uvx",
"args": [
"automagik-tools@latest",
"serve",
"--tool",
"genie",
"--transport",
"stdio"
],
"env": {
"OPENAI_API_KEY": "your-openai-key",
"GENIE_MCP_CONFIGS": "{\"agent-memory\":{\"url\":\"http://192.168.112.149:8000/sse\",\"transport\":\"sse\"}}"
}
}
}
}
```
### AutoMagik with Multiple APIs
```bash
# Stripe Payments
uvx automagik-tools serve \
--openapi-url https://raw.githubusercontent.com/stripe/openapi/master/openapi/spec3.json \
--api-key $STRIPE_API_KEY
# GitHub API
uvx automagik-tools serve \
--openapi-url https://raw.githubusercontent.com/github/rest-api-description/main/descriptions/api.github.com/api.github.com.json \
--api-key $GITHUB_TOKEN
# Your Internal API
uvx automagik-tools serve \
--openapi-url https://api.yourcompany.com/openapi.json \
--api-key $YOUR_API_KEY
```
<details>
<summary><b>🛠️ Developer Documentation</b></summary>
## Development Setup
```bash
# Clone the repo
git clone https://github.com/namastexlabs/automagik-tools
cd automagik-tools
# Install with all dev dependencies
make install
# Run tests
make test
# Create a new tool
make new-tool
```
## Creating Tools from OpenAPI
```bash
# Method 1: Dynamic (no files created)
uvx automagik-tools openapi https://api.example.com/openapi.json
# Method 2: Generate persistent tool
uvx automagik-tools create-tool --url https://api.example.com/openapi.json --name my-api
uvx automagik-tools tool my-api
```
## Adding Your Own Tools
1. Create a folder in `automagik_tools/tools/your_tool/`
2. Add `__init__.py` with FastMCP server
3. That's it - auto-discovered!
See our [Tool Creation Guide](docs/TOOL_CREATION_GUIDE.md) for details.
## Available Commands
```bash
# Core commands
automagik-tools list # List all available tools
automagik-tools hub # Serve all tools together
automagik-tools tool <name> # Serve a specific tool
automagik-tools openapi <url> # Serve from OpenAPI spec
automagik-tools mcp-config <tool> # Generate MCP config
automagik-tools info <tool> # Show tool details
automagik-tools version # Show version
# Development commands
make install # Install dev environment
make test # Run all tests
make lint # Check code style
make format # Auto-format code
make build # Build package
make docker-build # Build Docker images
```
</details>
## 🤝 Contributing
We love contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
## 📄 License
MIT License - see [LICENSE](LICENSE)
## 🙏 Credits
Built with ❤️ by [Namastex Labs](https://www.linkedin.com/company/namastexlabs)
Special thanks to:
- [Anthropic](https://anthropic.com) for MCP
- [FastMCP](https://github.com/jlowin/fastmcp) for the awesome framework
- Our amazing community of contributors
---
<p align="center">
<b>Every API becomes a smart agent that learns how you work.</b><br>
<a href="https://github.com/namastexlabs/automagik-tools">Star us on GitHub</a> •
<a href="https://discord.gg/automagik">Join our Discord</a> •
<a href="https://twitter.com/namastexlabs">Follow on Twitter</a>
</p>
Raw data
{
"_id": null,
"home_page": null,
"name": "automagik-tools",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.12",
"maintainer_email": null,
"keywords": "mcp, tools, ai, agents, fastmcp, whatsapp, discord, notion",
"author": null,
"author_email": "Felipe Rosa <felipe@namastex.ai>, Cezar Vasconcelos <cezar@namastex.ai>",
"download_url": "https://files.pythonhosted.org/packages/b3/c1/89b17b86540a6292869a17353d43f76bbc534008b9f90526ae1f46a3b69e/automagik_tools-0.7.3.tar.gz",
"platform": null,
"description": "<p align=\"center\">\n <img src=\".github/images/automagik_logo.png\" alt=\"AutoMagik Tools Logo\" width=\"600\"/>\n</p>\n\n# \ud83e\ude84 AutoMagik Tools\n\n## MCP Agents That Learn Your APIs Automagikally\n\nDrop any OpenAPI spec \u2192 Get an intelligent MCP agent that learns how you work and gets better with every interaction. Export to code when you're ready to customize.\n\nBorn from our daily work at [Namastex Labs](https://www.linkedin.com/company/namastexlabs), AutoMagik Tools creates **self-evolving agents** that turn any API into a natural language interface.\n\n## \ud83e\udde0 Self-Learning MCP Agents\n\nUnlike static tools, AutoMagik agents **remember and adapt**:\n\n```bash\n# First time: \"How much did I sell last month?\"\n# Agent learns your sales endpoints, date formats, and preferences\n\n# By the 10th interaction:\n# Agent already knows exactly which data you want and how you like it formatted\nuvx automagik-tools tool automagik -t sse --port 8000\n```\n\n**Three Intelligence Modes:**\n- \ud83d\udd27 **Standard**: Full schema access for precise control\n- \ud83d\udccb **Markdown**: Agent processes noisy JSON into clean, readable output (powered by GPT-4.1-nano)\n- \ud83d\udcac **Genie**: Natural language interface - just describe what you need\n\n*Powered by GPT-4.1 family models for cost-effective agentic behavior and reliable API reasoning.*\n\n## \ud83d\ude80 From Any API to Smart Agent\n\nTurn any OpenAPI spec into an intelligent agent:\n\n```bash\n# Discord API becomes a smart agent\nuvx automagik-tools openapi \\\n https://raw.githubusercontent.com/discord/discord-api-spec/main/specs/openapi.json \\\n -t sse --port 8001\n\n# Share this agent with your entire team via SSE\n# Team members can access the same learning agent at http://localhost:8001\n```\n\n**Now you can say:**\n- \"Show me unread messages from the design team\"\n- \"Schedule a voice call for 3pm in the dev channel\"\n- \"Find all threads where someone mentioned the new feature\"\n\nAgent learns your patterns, server preferences, and communication style.\n\n## \ud83e\uddde Genie: Universal MCP Orchestrator\n\n**Genie connects any MCP servers and orchestrates them with persistent memory**:\n\n```bash\n# Run Genie with memory-based agents\nuvx automagik-tools tool genie -t sse --port 8000\n```\n\n### Configure Genie with Multiple MCP Servers\n\nGenie can orchestrate any combination of MCP servers. Configure via environment variables:\n\n```bash\n# Method 1: JSON configuration for multiple servers\nexport GENIE_MCP_CONFIGS='{\n \"agent-memory\": {\n \"url\": \"http://192.168.112.149:8000/sse\",\n \"transport\": \"sse\"\n },\n \"filesystem\": {\n \"command\": \"npx\",\n \"args\": [\"-y\", \"@modelcontextprotocol/server-filesystem\", \"/path/to/allowed/directory\"],\n \"env\": {}\n },\n \"github\": {\n \"command\": \"uvx\",\n \"args\": [\"mcp-server-git\"],\n \"env\": {\"GITHUB_TOKEN\": \"your-token\"}\n }\n}'\n\n# Method 2: AutoMagik-specific shorthand\nexport GENIE_AUTOMAGIK_API_KEY=\"your-api-key\"\nexport GENIE_AUTOMAGIK_BASE_URL=\"http://localhost:8881\"\nexport GENIE_AUTOMAGIK_TIMEOUT=\"600\"\n```\n\n### Add Genie to Claude/Cursor (Universal Orchestrator)\n\n[](https://cursor.com/install-mcp?name=discord&config=eyJjb21tYW5kIjoidXZ4IGF1dG9tYWdpay10b29sc0BsYXRlc3Qgc2VydmUgLS1vcGVuYXBpLXVybCBodHRwczovL3Jhdy5naXRodWJ1c2VyY29udGVudC5jb20vZGlzY29yZC9kaXNjb3JkLWFwaS1zcGVjL21haW4vc3BlY3Mvb3BlbmFwaS5qc29uIC0tdHJhbnNwb3J0IHN0ZGlvIiwiZW52Ijp7IkRJU0NPUkRfVE9LRU4iOiJZT1VSX0JPVF9UT0tFTiJ9fQ%3D%3D)\n\n```json\n{\n \"mcpServers\": {\n \"genie\": {\n \"command\": \"uvx\",\n \"args\": [\n \"automagik-tools@latest\",\n \"serve\",\n \"--tool\",\n \"genie\",\n \"--transport\",\n \"stdio\"\n ],\n \"env\": {\n \"OPENAI_API_KEY\": \"your-openai-key\",\n \"GENIE_MCP_CONFIGS\": \"{\\\"agent-memory\\\":{\\\"url\\\":\\\"http://192.168.112.149:8000/sse\\\",\\\"transport\\\":\\\"sse\\\"},\\\"filesystem\\\":{\\\"command\\\":\\\"npx\\\",\\\"args\\\":[\\\"-y\\\",\\\"@modelcontextprotocol/server-filesystem\\\",\\\"/allowed/path\\\"],\\\"env\\\":{}}}\"\n }\n }\n }\n}\n```\n\n**Now in Claude/Cursor, Genie can:**\n- \"Use the memory agent to remember this conversation\"\n- \"Check the filesystem for project files and analyze them with the memory agent\"\n- \"Coordinate between multiple tools to complete complex tasks\"\n\n## \ud83c\udf1f Featured: AutoMagik Orchestration\n\nEnterprise-grade agent orchestration that speaks human:\n\n```bash\nuvx automagik-tools tool automagik --transport sse --port 8000\n```\n\n**Real examples from our users:**\n- \"Monitor inventory across all warehouses and alert me when Corona drops below 10k units\"\n- \"Generate weekly performance reports and send to regional managers\" \n- \"Set up automated quality checks for next month's production runs\"\n- \"Track competitor pricing and notify me of changes above 5%\"\n\n\ud83d\udcac Natural Language \u2022 \ud83e\udde0 Memory & Learning \u2022 \ud83d\udd04 Task Orchestration \u2022 \ud83c\udfd7\ufe0f Framework Agnostic \u2022 \ud83d\udc69\u200d\ud83d\udcbb Export to Code\n\n## \ud83d\ude80 Quick Start\n\n### Environment Setup\n\nCreate a `.env` file with your API keys:\n\n```bash\n# .env\nOPENAI_API_KEY=sk-your-openai-key-here\nAUTOMAGIK_API_KEY=your-automagik-api-key\nAUTOMAGIK_BASE_URL=http://localhost:8881\n\n# Enable JSON to Markdown processing (optional)\nENABLE_JSON_PROCESSING=true\nJSON_PROCESSOR_MODEL=gpt-4.1-nano\n```\n\n### Copy this into Claude/Cursor for instant API orchestration:\n\n\n[](https://cursor.com/install-mcp?name=automagik&config=eyJjb21tYW5kIjoidXZ4IGF1dG9tYWdpay10b29sc0BsYXRlc3Qgc2VydmUgLS10b29sIGF1dG9tYWdpayAtLXRyYW5zcG9ydCBzdGRpbyIsImVudiI6eyJBVVRPTUFHSUtfQUdFTlRTX0FQSV9LRVkiOiJZT1VSX0FQSV9LRVkiLCJBVVRPTUFHSUtfQUdFTlRTX0JBU0VfVVJMIjoiaHR0cDovL2xvY2FsaG9zdDo4ODgxIiwiQVVUT01BR0lLX0FHRU5UU19PUEVOQVBJX1VSTCI6Imh0dHA6Ly9sb2NhbGhvc3Q6ODg4MS9hcGkvdjEvb3BlbmFwaS5qc29uIn19)\n```json\n{\n \"mcpServers\": {\n \"automagik\": {\n \"command\": \"uvx\",\n \"args\": [\n \"automagik-tools@latest\",\n \"serve\",\n \"--tool\",\n \"automagik\",\n \"--transport\",\n \"stdio\"\n ],\n \"env\": {\n \"AUTOMAGIK_API_KEY\": \"YOUR_API_KEY\",\n \"AUTOMAGIK_BASE_URL\": \"http://localhost:8881\",\n \"OPENAI_API_KEY\": \"YOUR_OPENAI_API_KEY\"\n }\n }\n }\n}\n```\n\n**Where to add:**\n- **Claude Desktop**: Settings \u2192 Developer \u2192 Edit Config\n- **Cursor**: `~/.cursor/mcp.json`\n\n### Test any API instantly:\n\n```bash\n# Jira becomes conversational project management\nOPENAI_API_KEY=your_key JIRA_API_TOKEN=your_token uvx automagik-tools serve \\\n --openapi-url https://dac-static.atlassian.com/cloud/jira/platform/swagger-v3.v3.json \\\n --transport sse --port 8002\n\n# Shopify for e-commerce automation \nOPENAI_API_KEY=your_key SHOPIFY_ACCESS_TOKEN=your_token uvx automagik-tools serve \\\n --openapi-url https://shopify.dev/docs/api/admin-rest/2023-04/openapi.json \\\n --transport sse --port 8003\n\n# SSE mode allows your team to share the same learning agent\n```\n\n## \ud83d\udccb Real-World Agent Examples\n\n### Genie Orchestrating Multiple Tools\n\n**Personal Automation:**\n- \"Use memory agent to remember my GitHub preferences, then check my repos and create a weekly summary\"\n- \"Process these expense receipts with the filesystem tool and store insights in memory\"\n- \"Monitor my crypto portfolio with the trading API and remember my risk preferences\"\n\n**Team Coordination:**\n- \"Coordinate between Slack and Linear to set up daily standups for the design team\"\n- \"Use the file system to track project deadlines and notify stakeholders via Discord\" \n- \"Analyze customer feedback from multiple sources and create sentiment reports\"\n\n**Business Intelligence:**\n- \"Compare Q4 sales across all regions using the database and memory tools\"\n- \"Generate inventory reports by coordinating warehouse APIs and document storage\"\n- \"Monitor competitor pricing across platforms and update my preference memory\"\n\nThe agent **learns your patterns** - after a few interactions, it knows exactly how you like your data formatted, which metrics matter most, and when to proactively alert you.\n\n## \ud83d\udee0\ufe0f Advanced Usage\n\n### Multiple Server Configurations\n\nConfigure Genie with different MCP server combinations:\n\n```bash\n# Development setup with local tools\nexport GENIE_MCP_CONFIGS='{\n \"filesystem\": {\n \"command\": \"npx\",\n \"args\": [\"-y\", \"@modelcontextprotocol/server-filesystem\", \"/home/user/projects\"],\n \"env\": {}\n },\n \"git\": {\n \"command\": \"uvx\", \n \"args\": [\"mcp-server-git\"],\n \"env\": {\"GIT_AUTHOR_NAME\": \"Your Name\"}\n }\n}'\n\n# Production setup with external services\nexport GENIE_MCP_CONFIGS='{\n \"automagik\": {\n \"command\": \"uvx\",\n \"args\": [\"automagik-tools\", \"tool\", \"automagik\", \"--transport\", \"stdio\"],\n \"env\": {\n \"AUTOMAGIK_API_KEY\": \"prod-key\",\n \"AUTOMAGIK_BASE_URL\": \"https://api.yourcompany.com\"\n }\n },\n \"slack\": {\n \"command\": \"docker\",\n \"args\": [\"run\", \"-i\", \"--rm\", \"-e\", \"SLACK_BOT_TOKEN\", \"mcp/slack\"],\n \"env\": {\"SLACK_BOT_TOKEN\": \"xoxb-your-token\"}\n }\n}'\n```\n\n### Dynamic MCP Server Connection\n\nYou can also pass MCP server configurations directly to Genie via the `ask_genie` tool:\n\n```json\n{\n \"tool\": \"ask_genie\",\n \"arguments\": {\n \"query\": \"List all my GitHub repositories and remember my coding preferences\",\n \"mcp_servers\": {\n \"github\": {\n \"command\": \"uvx\",\n \"args\": [\"mcp-server-git\"],\n \"env\": {\"GITHUB_TOKEN\": \"your-token\"}\n },\n \"memory\": {\n \"url\": \"http://localhost:8000/sse\",\n \"transport\": \"sse\"\n }\n }\n }\n}\n```\n\n## \ud83c\udfaf Why Intelligent Agents Matter\n\n**The old way:** Hours writing API integrations, maintaining complex schemas, fighting with documentation. When APIs change, everything breaks.\n\n**The AutoMagik way:**\n1. **Point** to any OpenAPI spec\n2. **Ask** in natural language what you need \n3. **Learn** as the agent adapts to your workflow\n4. **Export** to code when you need customization\n\nWhen your needs evolve, your agent **learns and remembers**.\n\n## \ud83d\udee0\ufe0f Built-in Tools\n\n### AutoMagik \ud83e\udd16\nAI orchestration that speaks human:\n\n```bash\n# Quick test with SSE\nuvx automagik-tools tool automagik --transport sse --port 8000\n```\n\n**What you can do:**\n- \u2728 Use Spark to spawn hives of agents in seconds\n- \ud83d\udd04 Schedule recurring AI tasks and automations\n- \ud83d\udcac Natural language task descriptions\n- \ud83c\udfd7\ufe0f Works with any AI framework\n\n### Genie \ud83e\uddde\nUniversal MCP orchestrator with persistent memory:\n\n```bash\n# Run as SSE server for team sharing\nuvx automagik-tools tool genie --transport sse --port 8000\n```\n\n**Capabilities:**\n- \ud83e\udde0 Persistent memory across all sessions\n- \ud83d\udd17 Connect to unlimited MCP servers\n- \ud83d\udcac Natural language task coordination\n- \ud83d\udc65 Shared learning across team members\n\n### AutoMagik Workflows \ud83d\ude80\nSmart Claude workflow orchestration with real-time progress tracking:\n\n```bash\n# Execute Claude Code workflows with progress monitoring\nuvx automagik-tools tool automagik-workflows --transport stdio\n```\n\n**Features:**\n- \ud83d\ude80 **Run Claude Code Workflows**: Execute workflows with progress reporting\n- \ud83d\udcca **Real-time Status**: Track workflow completion with visual progress\n- \ud83d\udccb **List Workflows**: Discover available workflows and recent runs \n- \ud83d\udd04 **Status Monitoring**: Get detailed workflow execution status\n\n### Evolution API (WhatsApp) \ud83d\udcf1\nComplete WhatsApp automation:\n- Send/receive messages\n- Media support (images, documents)\n- Group management\n- Status updates\n\n## \ud83d\ude80 The Future: Self-Maintaining Tools\n\nOur roadmap includes agents that:\n- **Auto-discover** API endpoints without OpenAPI specs\n- **Auto-evolution**: Tools that update and adapt when APIs change\n- **Self-debug** and report issues back to maintainers\n- **Collaborate** with other agents for complex workflows\n- **Generate** their own tools from natural language descriptions\n\n**Production Deployments (Coming Soon):**\n- \ud83d\udc33 **Docker**: One-click deployment scripts for containerized agents\n- \u2601\ufe0f **Cloud Ready**: Deploy to AWS, Google Cloud, Azure with pre-built templates\n- \ud83c\udf10 **Team Sharing**: VPS and network deployments for organization-wide agent access\n- \ud83d\udcc8 **Scalable**: Load balancing and auto-scaling for high-demand agents\n\n*Coming 2025: A hive of AI agents maintaining this entire codebase - reporting bugs, implementing features, and keeping users happy. All open source.*\n\n## \ud83d\udccb Real-World Examples\n\n### Genie with Memory Agent\n```json\n{\n \"mcpServers\": {\n \"genie_with_memory\": {\n \"command\": \"uvx\",\n \"args\": [\n \"automagik-tools@latest\",\n \"serve\",\n \"--tool\",\n \"genie\",\n \"--transport\",\n \"stdio\"\n ],\n \"env\": {\n \"OPENAI_API_KEY\": \"your-openai-key\",\n \"GENIE_MCP_CONFIGS\": \"{\\\"agent-memory\\\":{\\\"url\\\":\\\"http://192.168.112.149:8000/sse\\\",\\\"transport\\\":\\\"sse\\\"}}\"\n }\n }\n }\n}\n```\n\n### AutoMagik with Multiple APIs\n```bash\n# Stripe Payments\nuvx automagik-tools serve \\\n --openapi-url https://raw.githubusercontent.com/stripe/openapi/master/openapi/spec3.json \\\n --api-key $STRIPE_API_KEY\n\n# GitHub API \nuvx automagik-tools serve \\\n --openapi-url https://raw.githubusercontent.com/github/rest-api-description/main/descriptions/api.github.com/api.github.com.json \\\n --api-key $GITHUB_TOKEN\n\n# Your Internal API\nuvx automagik-tools serve \\\n --openapi-url https://api.yourcompany.com/openapi.json \\\n --api-key $YOUR_API_KEY\n```\n\n<details>\n<summary><b>\ud83d\udee0\ufe0f Developer Documentation</b></summary>\n\n## Development Setup\n\n```bash\n# Clone the repo\ngit clone https://github.com/namastexlabs/automagik-tools\ncd automagik-tools\n\n# Install with all dev dependencies\nmake install\n\n# Run tests\nmake test\n\n# Create a new tool\nmake new-tool\n```\n\n## Creating Tools from OpenAPI\n\n```bash\n# Method 1: Dynamic (no files created)\nuvx automagik-tools openapi https://api.example.com/openapi.json\n\n# Method 2: Generate persistent tool\nuvx automagik-tools create-tool --url https://api.example.com/openapi.json --name my-api\nuvx automagik-tools tool my-api\n```\n\n## Adding Your Own Tools\n\n1. Create a folder in `automagik_tools/tools/your_tool/`\n2. Add `__init__.py` with FastMCP server\n3. That's it - auto-discovered!\n\nSee our [Tool Creation Guide](docs/TOOL_CREATION_GUIDE.md) for details.\n\n## Available Commands\n\n```bash\n# Core commands\nautomagik-tools list # List all available tools\nautomagik-tools hub # Serve all tools together\nautomagik-tools tool <name> # Serve a specific tool\nautomagik-tools openapi <url> # Serve from OpenAPI spec\nautomagik-tools mcp-config <tool> # Generate MCP config\nautomagik-tools info <tool> # Show tool details\nautomagik-tools version # Show version\n\n# Development commands \nmake install # Install dev environment\nmake test # Run all tests\nmake lint # Check code style\nmake format # Auto-format code\nmake build # Build package\nmake docker-build # Build Docker images\n```\n\n</details>\n\n## \ud83e\udd1d Contributing\n\nWe love contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.\n\n## \ud83d\udcc4 License\n\nMIT License - see [LICENSE](LICENSE)\n\n## \ud83d\ude4f Credits\n\nBuilt with \u2764\ufe0f by [Namastex Labs](https://www.linkedin.com/company/namastexlabs)\n\nSpecial thanks to:\n- [Anthropic](https://anthropic.com) for MCP\n- [FastMCP](https://github.com/jlowin/fastmcp) for the awesome framework\n- Our amazing community of contributors\n\n---\n\n<p align=\"center\">\n <b>Every API becomes a smart agent that learns how you work.</b><br>\n <a href=\"https://github.com/namastexlabs/automagik-tools\">Star us on GitHub</a> \u2022 \n <a href=\"https://discord.gg/automagik\">Join our Discord</a> \u2022 \n <a href=\"https://twitter.com/namastexlabs\">Follow on Twitter</a>\n</p>\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A monorepo package for MCP tools with dynamic loading capabilities - featuring Evolution API v2 WhatsApp integration",
"version": "0.7.3",
"project_urls": {
"Documentation": "https://github.com/namastexlabs/automagik-tools/README.md",
"Homepage": "https://github.com/namastexlabs/automagik-tools",
"Issues": "https://github.com/namastexlabs/automagik-tools/issues",
"Repository": "https://github.com/namastexlabs/automagik-tools"
},
"split_keywords": [
"mcp",
" tools",
" ai",
" agents",
" fastmcp",
" whatsapp",
" discord",
" notion"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "c54ea86b740c5d74892fbbfdea253349919a1cf4e515a6c2b38e01e00219a19d",
"md5": "fccb7d168de2e43949f83f4a1f258777",
"sha256": "55afbfe5bf5ea7bad1bcd25df4f294b7b9b699fd03134e232ac3003a0cc7e06d"
},
"downloads": -1,
"filename": "automagik_tools-0.7.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "fccb7d168de2e43949f83f4a1f258777",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.12",
"size": 70256,
"upload_time": "2025-07-09T22:45:06",
"upload_time_iso_8601": "2025-07-09T22:45:06.769777Z",
"url": "https://files.pythonhosted.org/packages/c5/4e/a86b740c5d74892fbbfdea253349919a1cf4e515a6c2b38e01e00219a19d/automagik_tools-0.7.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "b3c189b17b86540a6292869a17353d43f76bbc534008b9f90526ae1f46a3b69e",
"md5": "4e8bf96378c69bd1d46102debf856110",
"sha256": "97d49465ca408f43c76efb76c1e3f5e1b6ad9fef236311683497dc0c897abb34"
},
"downloads": -1,
"filename": "automagik_tools-0.7.3.tar.gz",
"has_sig": false,
"md5_digest": "4e8bf96378c69bd1d46102debf856110",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.12",
"size": 77163,
"upload_time": "2025-07-09T22:45:08",
"upload_time_iso_8601": "2025-07-09T22:45:08.489654Z",
"url": "https://files.pythonhosted.org/packages/b3/c1/89b17b86540a6292869a17353d43f76bbc534008b9f90526ae1f46a3b69e/automagik_tools-0.7.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-09 22:45:08",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "namastexlabs",
"github_project": "automagik-tools",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "automagik-tools"
}
