# Traia IATP
[](https://badge.fury.io/py/traia-iatp)
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/MIT)
**Traia IATP** is an Inter-Agent Transfer Protocol (IATP) package that enables AI agents to utilize other AI agents as tools via the A2A (Agent-to-Agent) protocol. This implementation allows CrewAI agents to act as both IATP servers (utility agents) and clients.
## Features
- 🤖 **Utility Agent Creation**: Convert MCP servers into IATP-compatible utility agents
- 🔌 **IATP Client Tools**: Enable CrewAI crews to use utility agents as tools via IATP protocol
- 🌐 **Protocol Support**: HTTP/2 with SSE streaming and optional gRPC for high-performance scenarios
- 📊 **Registry Management**: MongoDB-based registry for discovering utility agents
- 🐳 **Docker Support**: Complete containerization for deployment
- 🐳 **Local Docker Deployment**: Complete containerization for local deployment
## Installation
### From PyPI (Recommended)
```bash
pip install traia-iatp
```
### From Source
```bash
git clone https://github.com/Traia-IO/IATP.git
cd IATP
pip install -e .
```
### Development Installation
```bash
# Install with all dependencies for development
pip install -e ".[dev]"
```
## Quick Start
### 1. Creating a Utility Agency (IATP Server)
```python
import asyncio
from traia_iatp import MCPServer, MCPServerType, IATPServerAgentGenerator
async def create_utility_agency():
# Define an MCP server
mcp_server = MCPServer(
name="example-mcp-server",
url="http://example-mcp-server:8080",
server_type=MCPServerType.STREAMABLE_HTTP,
description="Example MCP server that provides utility functions"
)
# Generate and deploy utility agency
generator = IATPServerAgentGenerator()
agency = await generator.create_from_mcp(mcp_server)
# Deploy locally with Docker
await generator.deploy_local(agency)
```
### 2. Using Utility Agencies in CrewAI (IATP Client)
```python
from crewai import Agent, Task, Crew
from traia_iatp import find_utility_agent
from traia_iatp.client import A2AToolkit
# Find available utility agents by agent_id
agent = find_utility_agent(agent_id="finbert-mcp-traia-utility-agent")
if agent:
# Get the IATP endpoint
endpoint = agent.base_url
if agent.endpoints and 'iatp_endpoint' in agent.endpoints:
endpoint = agent.endpoints['iatp_endpoint']
# Create tool from agent endpoint
finbert_tool = A2AToolkit.create_tool_from_endpoint(
endpoint=endpoint,
name=agent.name,
description=agent.description,
timeout=300,
retry_attempts=1,
supports_streaming=False,
iatp_endpoint=endpoint
)
# Use in CrewAI agent
sentiment_analyst = Agent(
role="Financial Sentiment Analyst",
goal="Analyze sentiment of financial texts using FinBERT models",
backstory="Expert financial sentiment analyst with deep knowledge of market psychology",
tools=[finbert_tool],
verbose=True,
allow_delegation=False
)
# Create task
task = Task(
description="Analyze the sentiment of: 'Apple Inc. reported record quarterly earnings'",
expected_output="Sentiment classification with confidence score and investment implications",
agent=sentiment_analyst
)
# Run crew
crew = Crew(agents=[sentiment_analyst], tasks=[task])
result = crew.kickoff()
```
#### Alternative: Batch Tool Creation
For creating multiple tools at once, you can use the convenience function:
```python
from traia_iatp.client import create_utility_agency_tools
# Search and create tools in batch
tools = create_utility_agency_tools(
query="sentiment analysis",
tags=["finbert", "nlp"],
capabilities=["sentiment_analysis"]
)
# Use all found tools in an agent
agent = Agent(
role="Multi-Tool Analyst",
tools=tools,
goal="Analyze using multiple available utility agents"
)
```
### 3. CLI Usage
The package includes a powerful CLI for managing utility agencies:
```bash
# First, register an MCP server in the registry
traia-iatp register-mcp \
--name "Trading MCP" \
--url "http://localhost:8000/mcp" \
--description "Trading MCP server" \
--capability "trading" \
--capability "crypto"
# Create a utility agency from registered MCP server
traia-iatp create-agency \
--name "My Trading Agent" \
--description "Advanced trading utility agent" \
--mcp-name "Trading MCP" \
--deploy
# List available utility agencies
traia-iatp list-agencies
# Search for agencies by capability
traia-iatp search-agencies --query "trading crypto"
# Deploy from a generated agency directory
traia-iatp deploy ./utility_agencies/my-trading-agent --port 8001
# Find available tools for CrewAI
traia-iatp find-tools --tag "trading" --capability "crypto"
# List registered MCP servers
traia-iatp list-mcp-servers
# Show example CrewAI integration code
traia-iatp example-crew
```
## Architecture
### IATP Operation Modes
The IATP protocol supports two distinct operation modes:
#### 1. Synchronous JSON-RPC Mode
For simple request-response patterns:
- Client sends: `message/send` request via JSON-RPC
- Server processes the request using CrewAI agents
- Server returns: A single `Message` result
#### 2. Streaming SSE Mode
For real-time data and long-running operations:
- Client sends: `message/send` request via JSON-RPC
- Server returns: Stream of events via Server-Sent Events (SSE)
- Supports progress updates, partial results, and completion notifications
### Component Overview
```
┌─────────────────────┐ ┌─────────────────────┐ ┌─────────────────────┐
│ CrewAI Agent │───▶│ IATP Client │───▶│ Utility Agency │
│ (A2A Client) │ │ (HTTP/2 + gRPC) │ │ (A2A Server) │
└─────────────────────┘ └─────────────────────┘ └─────────────────────┘
│
▼
┌─────────────────────┐
│ MCP Server │
│ (Tools Provider) │
└─────────────────────┘
```
## Key Components
### Server Components (`traia_iatp.server`)
- **Template Generation**: Jinja2 templates for creating utility agents
- **HTTP/2 + SSE Support**: Modern protocol support with streaming
- **gRPC Integration**: Optional high-performance protocol support
- **Docker Containerization**: Complete deployment packaging
### Client Components (`traia_iatp.client`)
- **CrewAI Integration**: Native tools for CrewAI agents
- **HTTP/2 Client**: Persistent connections with multiplexing
- **SSE Streaming**: Real-time data consumption
- **Connection Management**: Pooling and retry logic
### Registry Components (`traia_iatp.registry`)
- **MongoDB Integration**: Persistent storage and search
- **Vector Search**: Embedding-based capability discovery
- **Atlas Search**: Full-text search capabilities
- **Agent Discovery**: Find agents by capability, tags, or description
## Environment Variables
```bash
# MongoDB Configuration (choose one method)
MONGODB_CONNECTION_STRING="mongodb+srv://..."
# OR
MONGODB_USER="username"
MONGODB_PASSWORD="password"
# OR X.509 Certificate
MONGODB_X509_CERT_FILE="/path/to/cert.pem"
# Optional: Custom MongoDB cluster
MONGODB_CLUSTER_URI="custom-cluster.mongodb.net"
MONGODB_DATABASE_NAME="custom_db"
# OpenAI for embeddings (optional)
OPENAI_API_KEY="your-openai-key"
# MCP Server Authentication (as needed)
MCP_API_KEY="your-mcp-api-key"
```
## Examples
### Advanced IATP Integration
```python
from traia_iatp import find_utility_agent
from traia_iatp.client import A2AToolkit
# Find multiple utility agents
trading_agent = find_utility_agent(agent_id="trading-mcp-agent")
sentiment_agent = find_utility_agent(agent_id="finbert-mcp-agent")
tools = []
for agent in [trading_agent, sentiment_agent]:
if agent:
# Get endpoint and create tool
endpoint = agent.endpoints.get('iatp_endpoint', agent.base_url)
tool = A2AToolkit.create_tool_from_endpoint(
endpoint=endpoint,
name=agent.name,
description=agent.description,
iatp_endpoint=endpoint
)
tools.append(tool)
# Use multiple IATP tools in one agent
multi_tool_agent = Agent(
role="Multi-Domain Analyst",
goal="Analyze markets using multiple specialized AI agents",
tools=tools,
backstory="Expert analyst with access to specialized AI agents for trading and sentiment analysis"
)
```
### Local Docker Deployment
```python
from traia_iatp.utils.docker_utils import LocalDockerRunner
from pathlib import Path
# Deploy a generated agency locally (not yet configured properly)
runner = LocalDockerRunner()
deployment_info = await runner.run_agent_docker(
agent_path=Path("./utility_agencies/my-trading-agent"),
port=8000,
detached=True
)
if deployment_info["success"]:
print(f"Agency deployed at: {deployment_info['iatp_endpoint']}")
print(f"Container: {deployment_info['container_name']}")
print(f"Stop with: {deployment_info['stop_command']}")
```
## Development
### Setting Up Development Environment
```bash
# Clone the repository
git clone https://github.com/Traia-IO/IATP.git
cd IATP
# Create virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install in development mode with dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Run linting
black .
flake8 .
mypy .
```
### Running Tests
```bash
# Run all tests
pytest
# Run specific test file
pytest tests/test_client.py
# Run with coverage
pytest --cov=traia_iatp --cov-report=html
```
## Contributing
We welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.
This is a private code base hence only members of Dcentralab can contribute
1. Fork the repository
2. Create a feature branch (`git checkout -b feature/amazing-feature`)
3. Commit your changes (`git commit -m 'Add amazing feature'`)
4. Push to the branch (`git push origin feature/amazing-feature`)
5. Open a Pull Request
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
## Support
- 📖 **Documentation**: [https://pypi.org/project/traia-iatp](https://pypi.org/project/traia-iatp)
- 🐛 **Bug Reports**: [GitHub Issues](https://github.com/Traia-IO/IATP/issues)
- 💬 **Community**: [Visit our website](https://traia.io)
- 📧 **Email**: support@traia.io
## Related Projects
- [A2A Protocol](https://github.com/google-a2a/A2A) - Agent-to-Agent communication protocol
- [CrewAI](https://github.com/joaomdmoura/crewAI) - Framework for orchestrating role-playing AI agents
- [FastMCP](https://github.com/modelcontextprotocol/fastmcp) - Fast implementation of Model Context Protocol
---
**Made with ❤️ by the Traia Team**
Raw data
{
"_id": null,
"home_page": null,
"name": "traia-iatp",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.12.8",
"maintainer_email": null,
"keywords": "crewai, iatp, agent-to-agent, a2a, mcp, web3, cryptocurrency, tools",
"author": null,
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/db/14/1b29e11d0848a00f027bfa9ff1efd20fd69d710839801e8564189283c9b3/traia_iatp-0.1.4.tar.gz",
"platform": null,
"description": "# Traia IATP\n\n[](https://badge.fury.io/py/traia-iatp)\n[](https://www.python.org/downloads/)\n[](https://opensource.org/licenses/MIT)\n\n**Traia IATP** is an Inter-Agent Transfer Protocol (IATP) package that enables AI agents to utilize other AI agents as tools via the A2A (Agent-to-Agent) protocol. This implementation allows CrewAI agents to act as both IATP servers (utility agents) and clients.\n\n## Features\n\n- \ud83e\udd16 **Utility Agent Creation**: Convert MCP servers into IATP-compatible utility agents\n- \ud83d\udd0c **IATP Client Tools**: Enable CrewAI crews to use utility agents as tools via IATP protocol\n- \ud83c\udf10 **Protocol Support**: HTTP/2 with SSE streaming and optional gRPC for high-performance scenarios\n- \ud83d\udcca **Registry Management**: MongoDB-based registry for discovering utility agents\n- \ud83d\udc33 **Docker Support**: Complete containerization for deployment\n- \ud83d\udc33 **Local Docker Deployment**: Complete containerization for local deployment\n\n## Installation\n\n### From PyPI (Recommended)\n\n```bash\npip install traia-iatp\n```\n\n### From Source\n\n```bash\ngit clone https://github.com/Traia-IO/IATP.git\ncd IATP\npip install -e .\n```\n\n### Development Installation\n\n```bash\n# Install with all dependencies for development\npip install -e \".[dev]\"\n```\n\n## Quick Start\n\n### 1. Creating a Utility Agency (IATP Server)\n\n```python\nimport asyncio\nfrom traia_iatp import MCPServer, MCPServerType, IATPServerAgentGenerator\n\nasync def create_utility_agency():\n # Define an MCP server\n mcp_server = MCPServer(\n name=\"example-mcp-server\",\n url=\"http://example-mcp-server:8080\",\n server_type=MCPServerType.STREAMABLE_HTTP,\n description=\"Example MCP server that provides utility functions\"\n )\n \n # Generate and deploy utility agency\n generator = IATPServerAgentGenerator()\n agency = await generator.create_from_mcp(mcp_server)\n \n # Deploy locally with Docker\n await generator.deploy_local(agency)\n```\n\n### 2. Using Utility Agencies in CrewAI (IATP Client)\n\n```python\nfrom crewai import Agent, Task, Crew\nfrom traia_iatp import find_utility_agent\nfrom traia_iatp.client import A2AToolkit\n\n# Find available utility agents by agent_id\nagent = find_utility_agent(agent_id=\"finbert-mcp-traia-utility-agent\")\n\nif agent:\n # Get the IATP endpoint\n endpoint = agent.base_url\n if agent.endpoints and 'iatp_endpoint' in agent.endpoints:\n endpoint = agent.endpoints['iatp_endpoint']\n \n # Create tool from agent endpoint\n finbert_tool = A2AToolkit.create_tool_from_endpoint(\n endpoint=endpoint,\n name=agent.name,\n description=agent.description,\n timeout=300,\n retry_attempts=1,\n supports_streaming=False,\n iatp_endpoint=endpoint\n )\n \n # Use in CrewAI agent\n sentiment_analyst = Agent(\n role=\"Financial Sentiment Analyst\",\n goal=\"Analyze sentiment of financial texts using FinBERT models\",\n backstory=\"Expert financial sentiment analyst with deep knowledge of market psychology\",\n tools=[finbert_tool],\n verbose=True,\n allow_delegation=False\n )\n \n # Create task\n task = Task(\n description=\"Analyze the sentiment of: 'Apple Inc. reported record quarterly earnings'\",\n expected_output=\"Sentiment classification with confidence score and investment implications\",\n agent=sentiment_analyst\n )\n \n # Run crew\n crew = Crew(agents=[sentiment_analyst], tasks=[task])\n result = crew.kickoff()\n```\n\n#### Alternative: Batch Tool Creation\n\nFor creating multiple tools at once, you can use the convenience function:\n\n```python\nfrom traia_iatp.client import create_utility_agency_tools\n\n# Search and create tools in batch\ntools = create_utility_agency_tools(\n query=\"sentiment analysis\",\n tags=[\"finbert\", \"nlp\"],\n capabilities=[\"sentiment_analysis\"]\n)\n\n# Use all found tools in an agent\nagent = Agent(\n role=\"Multi-Tool Analyst\",\n tools=tools,\n goal=\"Analyze using multiple available utility agents\"\n)\n```\n\n### 3. CLI Usage\n\nThe package includes a powerful CLI for managing utility agencies:\n\n```bash\n# First, register an MCP server in the registry\ntraia-iatp register-mcp \\\n --name \"Trading MCP\" \\\n --url \"http://localhost:8000/mcp\" \\\n --description \"Trading MCP server\" \\\n --capability \"trading\" \\\n --capability \"crypto\"\n\n# Create a utility agency from registered MCP server\ntraia-iatp create-agency \\\n --name \"My Trading Agent\" \\\n --description \"Advanced trading utility agent\" \\\n --mcp-name \"Trading MCP\" \\\n --deploy\n\n# List available utility agencies\ntraia-iatp list-agencies\n\n# Search for agencies by capability\ntraia-iatp search-agencies --query \"trading crypto\"\n\n# Deploy from a generated agency directory\ntraia-iatp deploy ./utility_agencies/my-trading-agent --port 8001\n\n# Find available tools for CrewAI\ntraia-iatp find-tools --tag \"trading\" --capability \"crypto\"\n\n# List registered MCP servers\ntraia-iatp list-mcp-servers\n\n# Show example CrewAI integration code\ntraia-iatp example-crew\n```\n\n## Architecture\n\n### IATP Operation Modes\n\nThe IATP protocol supports two distinct operation modes:\n\n#### 1. Synchronous JSON-RPC Mode\nFor simple request-response patterns:\n- Client sends: `message/send` request via JSON-RPC\n- Server processes the request using CrewAI agents \n- Server returns: A single `Message` result\n\n#### 2. Streaming SSE Mode\nFor real-time data and long-running operations:\n- Client sends: `message/send` request via JSON-RPC\n- Server returns: Stream of events via Server-Sent Events (SSE)\n- Supports progress updates, partial results, and completion notifications\n\n### Component Overview\n\n```\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510 \u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510 \u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 CrewAI Agent \u2502\u2500\u2500\u2500\u25b6\u2502 IATP Client \u2502\u2500\u2500\u2500\u25b6\u2502 Utility Agency \u2502\n\u2502 (A2A Client) \u2502 \u2502 (HTTP/2 + gRPC) \u2502 \u2502 (A2A Server) \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518 \u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518 \u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n \u2502\n \u25bc\n \u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n \u2502 MCP Server \u2502\n \u2502 (Tools Provider) \u2502\n \u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n```\n\n## Key Components\n\n### Server Components (`traia_iatp.server`)\n- **Template Generation**: Jinja2 templates for creating utility agents\n- **HTTP/2 + SSE Support**: Modern protocol support with streaming\n- **gRPC Integration**: Optional high-performance protocol support\n- **Docker Containerization**: Complete deployment packaging\n\n### Client Components (`traia_iatp.client`)\n- **CrewAI Integration**: Native tools for CrewAI agents\n- **HTTP/2 Client**: Persistent connections with multiplexing\n- **SSE Streaming**: Real-time data consumption\n- **Connection Management**: Pooling and retry logic\n\n### Registry Components (`traia_iatp.registry`)\n- **MongoDB Integration**: Persistent storage and search\n- **Vector Search**: Embedding-based capability discovery\n- **Atlas Search**: Full-text search capabilities\n- **Agent Discovery**: Find agents by capability, tags, or description\n\n## Environment Variables\n\n```bash\n# MongoDB Configuration (choose one method)\nMONGODB_CONNECTION_STRING=\"mongodb+srv://...\"\n# OR\nMONGODB_USER=\"username\"\nMONGODB_PASSWORD=\"password\"\n# OR X.509 Certificate\nMONGODB_X509_CERT_FILE=\"/path/to/cert.pem\"\n\n# Optional: Custom MongoDB cluster\nMONGODB_CLUSTER_URI=\"custom-cluster.mongodb.net\"\nMONGODB_DATABASE_NAME=\"custom_db\"\n\n# OpenAI for embeddings (optional)\nOPENAI_API_KEY=\"your-openai-key\"\n\n# MCP Server Authentication (as needed)\nMCP_API_KEY=\"your-mcp-api-key\"\n```\n\n## Examples\n\n### Advanced IATP Integration\n\n```python\nfrom traia_iatp import find_utility_agent\nfrom traia_iatp.client import A2AToolkit\n\n# Find multiple utility agents\ntrading_agent = find_utility_agent(agent_id=\"trading-mcp-agent\")\nsentiment_agent = find_utility_agent(agent_id=\"finbert-mcp-agent\") \n\ntools = []\nfor agent in [trading_agent, sentiment_agent]:\n if agent:\n # Get endpoint and create tool\n endpoint = agent.endpoints.get('iatp_endpoint', agent.base_url)\n tool = A2AToolkit.create_tool_from_endpoint(\n endpoint=endpoint,\n name=agent.name,\n description=agent.description,\n iatp_endpoint=endpoint\n )\n tools.append(tool)\n\n# Use multiple IATP tools in one agent\nmulti_tool_agent = Agent(\n role=\"Multi-Domain Analyst\", \n goal=\"Analyze markets using multiple specialized AI agents\",\n tools=tools,\n backstory=\"Expert analyst with access to specialized AI agents for trading and sentiment analysis\"\n)\n```\n\n### Local Docker Deployment\n\n```python\nfrom traia_iatp.utils.docker_utils import LocalDockerRunner\nfrom pathlib import Path\n\n# Deploy a generated agency locally (not yet configured properly)\nrunner = LocalDockerRunner()\ndeployment_info = await runner.run_agent_docker(\n agent_path=Path(\"./utility_agencies/my-trading-agent\"),\n port=8000,\n detached=True\n)\n\nif deployment_info[\"success\"]:\n print(f\"Agency deployed at: {deployment_info['iatp_endpoint']}\")\n print(f\"Container: {deployment_info['container_name']}\")\n print(f\"Stop with: {deployment_info['stop_command']}\")\n```\n\n## Development\n\n### Setting Up Development Environment\n\n```bash\n# Clone the repository\ngit clone https://github.com/Traia-IO/IATP.git\ncd IATP\n\n# Create virtual environment\npython -m venv venv\nsource venv/bin/activate # On Windows: venv\\Scripts\\activate\n\n# Install in development mode with dev dependencies\npip install -e \".[dev]\"\n\n# Run tests\npytest\n\n# Run linting\nblack .\nflake8 .\nmypy .\n```\n\n### Running Tests\n\n```bash\n# Run all tests\npytest\n\n# Run specific test file\npytest tests/test_client.py\n\n# Run with coverage\npytest --cov=traia_iatp --cov-report=html\n```\n\n## Contributing\n\nWe welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.\n\nThis is a private code base hence only members of Dcentralab can contribute\n\n1. Fork the repository\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes (`git commit -m 'Add amazing feature'`)\n4. Push to the branch (`git push origin feature/amazing-feature`)\n5. Open a Pull Request\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## Support\n\n- \ud83d\udcd6 **Documentation**: [https://pypi.org/project/traia-iatp](https://pypi.org/project/traia-iatp)\n- \ud83d\udc1b **Bug Reports**: [GitHub Issues](https://github.com/Traia-IO/IATP/issues)\n- \ud83d\udcac **Community**: [Visit our website](https://traia.io)\n- \ud83d\udce7 **Email**: support@traia.io\n\n## Related Projects\n\n- [A2A Protocol](https://github.com/google-a2a/A2A) - Agent-to-Agent communication protocol\n- [CrewAI](https://github.com/joaomdmoura/crewAI) - Framework for orchestrating role-playing AI agents\n- [FastMCP](https://github.com/modelcontextprotocol/fastmcp) - Fast implementation of Model Context Protocol\n\n---\n\n**Made with \u2764\ufe0f by the Traia Team** \n",
"bugtrack_url": null,
"license": null,
"summary": "Inter-Agent Transfer Protocol (IATP) - Enable AI Agents to utilize other AI Agents as tools",
"version": "0.1.4",
"project_urls": {
"Documentation": "https://pypi.org/project/traia-iatp",
"Source": "https://github.com/Traia-IO/IATP"
},
"split_keywords": [
"crewai",
" iatp",
" agent-to-agent",
" a2a",
" mcp",
" web3",
" cryptocurrency",
" tools"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "0e3d7f77a243c13503ae1f666b276eafcdb4767e941bb93ba52b60dd1c600ff3",
"md5": "43469f955535cd9ad227f8f2dde549fb",
"sha256": "0b6a03c2e95a1f1c556c361ed93e6685873658a790005140eb1251d7d8501583"
},
"downloads": -1,
"filename": "traia_iatp-0.1.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "43469f955535cd9ad227f8f2dde549fb",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.12.8",
"size": 138828,
"upload_time": "2025-07-16T16:57:25",
"upload_time_iso_8601": "2025-07-16T16:57:25.729029Z",
"url": "https://files.pythonhosted.org/packages/0e/3d/7f77a243c13503ae1f666b276eafcdb4767e941bb93ba52b60dd1c600ff3/traia_iatp-0.1.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "db141b29e11d0848a00f027bfa9ff1efd20fd69d710839801e8564189283c9b3",
"md5": "739fa52a27a031d4b74bb048a2c4ce7a",
"sha256": "6f8a19f775ad100770e03d9f5d0ba0cfe096072a5354c8c5c26dadb8de79711f"
},
"downloads": -1,
"filename": "traia_iatp-0.1.4.tar.gz",
"has_sig": false,
"md5_digest": "739fa52a27a031d4b74bb048a2c4ce7a",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.12.8",
"size": 113499,
"upload_time": "2025-07-16T16:57:27",
"upload_time_iso_8601": "2025-07-16T16:57:27.079431Z",
"url": "https://files.pythonhosted.org/packages/db/14/1b29e11d0848a00f027bfa9ff1efd20fd69d710839801e8564189283c9b3/traia_iatp-0.1.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-16 16:57:27",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Traia-IO",
"github_project": "IATP",
"github_not_found": true,
"lcname": "traia-iatp"
}
JSON
