ai-mirow-projects
/
swarms
mirror of https://github.com/kyegomez/swarms
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

docs fixed [no tables], added to mkdocs.yml

Browse Source
pull/1057/head
Aksh Parekh 1 month ago
parent fc451df6a0
commit 5675235554
2 changed files with 45 additions and 34 deletions
Show Stats Download Patch File Download Diff File

78
docs/examples/mcp_ds.md
Unescape View File

@ -4,18 +4,22 @@
The Model Context Protocol (MCP) provides a standardized way to create and manage AI agents through a server-client architecture. Running agents on MCP offers several key benefits: The Model Context Protocol (MCP) provides a standardized way to create and manage AI agents through a server-client architecture. Running agents on MCP offers several key benefits:
- **Standardized Interface**: Consistent API for agent creation and management across different systems | Benefit | Description |
- **Scalability**: Handle multiple agents simultaneously through a single MCP server |------------------------|-----------------------------------------------------------------------------|
- **Interoperability**: Agents can be called from any MCP-compatible client | Standardized Interface | Consistent API for agent creation and management across different systems |
- **Resource Management**: Centralized control over agent lifecycle and resources | Scalability | Handle multiple agents simultaneously through a single MCP server |
- **Protocol Compliance**: Follows the established MCP standard for AI tool integration | Interoperability | Agents can be called from any MCP-compatible client |
| Resource Management | Centralized control over agent lifecycle and resources |
| Protocol Compliance | Follows the established MCP standard for AI tool integration |
## Step 1: Setup and Installation ## Step 1: Setup and Installation
### Prerequisites ### Prerequisites
- Python 3.8 or higher | Requirement |
- pip package manager |-----------------------|
| Python 3.8 or higher |
| pip package manager |
### Required Packages ### Required Packages
@ -102,7 +106,7 @@ from mcp.client.streamable_http import (
async def create_agent_via_mcp(): async def create_agent_via_mcp():
"""Create and use an agent through MCP using streamable HTTP.""" """Create and use an agent through MCP using streamable HTTP."""
print("🔧 Starting MCP client connection...") print(" Starting MCP client connection...")
# Connect to the MCP server using streamable HTTP # Connect to the MCP server using streamable HTTP
try: try:
@ -120,7 +124,7 @@ async def create_agent_via_mcp():
print("Listing available tools...") print("Listing available tools...")
try: try:
tools = await session.list_tools() tools = await session.list_tools()
print(f"📋 Available tools: {[tool.name for tool in tools.tools]}") print(f" Available tools: {[tool.name for tool in tools.tools]}")
except Exception as e: except Exception as e:
print(f"Failed to list tools: {e}") print(f"Failed to list tools: {e}")
@ -187,7 +191,7 @@ from mcp.client.streamable_http import (
async def create_agent_via_mcp(session, agent_name, system_prompt, model_name, task): async def create_agent_via_mcp(session, agent_name, system_prompt, model_name, task):
"""Create and use an agent through MCP using streamable HTTP.""" """Create and use an agent through MCP using streamable HTTP."""
print(f"🔧 Creating agent '{agent_name}' with task: {task}") print(f" Creating agent '{agent_name}' with task: {task}")
try: try:
arguments = { arguments = {
"agent_name": agent_name, "agent_name": agent_name,
@ -223,7 +227,7 @@ async def create_agent_via_mcp(session, agent_name, system_prompt, model_name, t
raise raise
async def main(): async def main():
print("🔧 Starting MCP client connection...") print(" Starting MCP client connection...")
try: try:
async with http_client("http://localhost:8000/mcp") as (read, write, _): async with http_client("http://localhost:8000/mcp") as (read, write, _):
@ -239,7 +243,7 @@ async def main():
print("Listing available tools...") print("Listing available tools...")
try: try:
tools = await session.list_tools() tools = await session.list_tools()
print(f"📋 Available tools: {[tool.name for tool in tools.tools]}") print(f" Available tools: {[tool.name for tool in tools.tools]}")
except Exception as e: except Exception as e:
print(f"Failed to list tools: {e}") print(f"Failed to list tools: {e}")
raise raise
@ -307,27 +311,33 @@ Here's a complete overview of all the steps needed to set up your agent initiali
### **Step-by-Step Summary:** ### **Step-by-Step Summary:**
1. **📦 Package Installation** - Install MCP SDK, FastMCP, Swarms, and dependencies | Step | Description |
2. **🔧 Server Creation** - Create the MCP server with agent creation tool |------|-------------|
3. **🚀 Server Startup** - Run the MCP server to handle client requests | 1. Package Installation | Install MCP SDK, FastMCP, Swarms, and dependencies |
4. **📱 Basic Client** - Create a simple client to run single agents | 2. Server Creation | Create the MCP server with agent creation tool |
5. **🔄 Advanced Client** - Build multi-agent workflows with sequential processing | 3. Server Startup | Run the MCP server to handle client requests |
| 4. Basic Client | Create a simple client to run single agents |
| 5. Advanced Client | Build multi-agent workflows with sequential processing |
### **What You'll Have After Following These Steps:** ### **What You'll Have After Following These Steps:**
- ✅ **MCP Server** running and ready to handle agent creation requests | Component | Description |
- ✅ **Single Agent Client** for basic agent tasks |-----------|-------------|
- ✅ **Multi-Agent Client** for complex, chained workflows | MCP Server | Running and ready to handle agent creation requests |
- ✅ **Complete System** for dynamic agent creation and management | Single Agent Client | For basic agent tasks |
- ✅ **Scalable Architecture** that can handle multiple concurrent agent requests | Multi-Agent Client | For complex, chained workflows |
| Complete System | For dynamic agent creation and management |
| Scalable Architecture | Can handle multiple concurrent agent requests |
### **Key Benefits Achieved:** ### **Key Benefits Achieved:**
- **Standardized Interface** for agent management | Benefit | Description |
- **Scalable Architecture** for multiple agents |---------|-------------|
- **Protocol Compliance** with MCP standards | Standardized Interface | For agent management |
- **Resource Management** for efficient agent lifecycle | Scalable Architecture | For multiple agents |
- **Interoperability** with any MCP-compatible client | Protocol Compliance | With MCP standards |
| Resource Management | For efficient agent lifecycle |
| Interoperability | With any MCP-compatible client |
This setup gives you a complete, production-ready system for running AI agents through the Model Context Protocol! This setup gives you a complete, production-ready system for running AI agents through the Model Context Protocol!
@ -337,10 +347,10 @@ If you'd like technical support, join our Discord below and stay updated on our
| Platform | Link | Description | | Platform | Link | Description |
|----------|------|-------------| |----------|------|-------------|
| 📚 Documentation | [docs.swarms.world](https://docs.swarms.world) | Official documentation and guides | | Documentation | [docs.swarms.world](https://docs.swarms.world) | Official documentation and guides |
| 📝 Blog | [Medium](https://medium.com/@kyeg) | Latest updates and technical articles | | Blog | [Medium](https://medium.com/@kyeg) | Latest updates and technical articles |
| 💬 Discord | [Join Discord](https://discord.gg/EamjgSaEQf) | Live chat and community support | | Discord | [Join Discord](https://discord.gg/EamjgSaEQf) | Live chat and community support |
| 🐦 Twitter | [@kyegomez](https://twitter.com/kyegomez) | Latest news and announcements | | Twitter | [@kyegomez](https://twitter.com/kyegomez) | Latest news and announcements |
| 👥 LinkedIn | [The Swarm Corporation](https://www.linkedin.com/company/the-swarm-corporation) | Professional network and updates | | LinkedIn | [The Swarm Corporation](https://www.linkedin.com/company/the-swarm-corporation) | Professional network and updates |
| 📺 YouTube | [Swarms Channel](https://www.youtube.com/channel/UC9yXyitkbU_WSy7bd_41SqQ) | Tutorials and demos | | YouTube | [Swarms Channel](https://www.youtube.com/channel/UC9yXyitkbU_WSy7bd_41SqQ) | Tutorials and demos |
| 🎫 Events | [Sign up here](https://lu.ma/5p2jnc2v) | Join our community events | | Events | [Sign up here](https://lu.ma/5p2jnc2v) | Join our community events |

1
docs/mkdocs.yml
Unescape View File

@ -327,6 +327,7 @@ nav:
- Overview: "swarms_tools/overview.md" - Overview: "swarms_tools/overview.md"
- BaseTool Reference: "swarms/tools/base_tool.md" - BaseTool Reference: "swarms/tools/base_tool.md"
- MCP Client Utils: "swarms/tools/mcp_client_call.md" - MCP Client Utils: "swarms/tools/mcp_client_call.md"
- MCP Agent Tool: "swarms/tools/mcp_agent_tool.md"
- Vertical Tools: - Vertical Tools:
- Finance: "swarms_tools/finance.md" - Finance: "swarms_tools/finance.md"

Write Preview
Loading…
Cancel
Save