Update README

Author: saqadri

README.md

@@ -1,4 +1,9 @@
-# OpenAI Agents SDK
+# OpenAI Agents SDK (MCP Compatible)
+
+!!!
+**This is a fork of the OpenAI Agents SDK with MCP compatibility using [mcp-agent](https://github.com/lastmile-ai/mcp-agent)**
+!!!
+
 
 The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows.
 
@@ -10,6 +15,7 @@ The OpenAI Agents SDK is a lightweight yet powerful framework for building multi
 2. [**Handoffs**](https://openai.github.io/openai-agents-python/handoffs/): Allow agents to transfer control to other agents for specific tasks
 3. [**Guardrails**](https://openai.github.io/openai-agents-python/guardrails/): Configurable safety checks for input and output validation
 4. [**Tracing**](https://openai.github.io/openai-agents-python/tracing/): Built-in tracking of agent runs, allowing you to view, debug and optimize your workflows
+5. [**MCP**](#using-with-mcp-model-context-protocol): Supports using MCP servers with the Agent abstraction
 
 Explore the [examples](examples) directory to see the SDK in action, and read our [documentation](https://openai.github.io/openai-agents-python/) for more details.
 
@@ -166,17 +172,42 @@ make lint   # run linter
 
 ## Using with MCP (Model Context Protocol)
 
-The OpenAI Agents SDK can be integrated with the Model Context Protocol ([MCP](https://modelcontextprotocol.github.io/)) to seamlessly use tools from MCP servers. This integration allows you to:
+The OpenAI Agents SDK can be integrated with the Model Context Protocol ([MCP](https://modelcontextprotocol.github.io/)) to seamlessly use tools from MCP servers. The integration allows agents to leverage tools from MCP servers alongside native OpenAI Agent SDK tools:
 
 1. Use tools from MCP servers directly in your agents
 2. Configure MCP servers using standard configuration files
 3. Combine local tools with tools from MCP servers
 
-### Setting up MCP Integration
+### Using MCP servers in Agents SDK
+
+#### `mcp_servers` property on Agent
 
-1. Create an `mcp_agent.config.yaml` file in your project directory that defines your MCP servers:
+You can specify the names of MCP servers to give an Agent access to by
+setting its `mcp_servers` property.
+
+The Agent will then automatically aggregate tools from the servers, as well as 
+any `tools` specified, and create a single extended list of tools. This means you can seamlessly 
+use local tools, MCP servers, and other kinds of Agent SDK tools through a single unified syntax.
+
+```python
+
+agent = Agent(
+    name="MCP Assistant",
+    instructions="You are a helpful assistant with access to MCP tools.",
+    tools=[your_other_tools], # Regular tool use for Agent SDK
+    mcp_servers=["fetch", "filesystem"]  # Names of MCP servers from your config file (see below)
+)
+```
+
+#### MCP Configuration File
+
+Configure MCP servers by creating an `mcp_agent.config.yaml` file. You can place this file in your project directory or any parent directory. 
+
+Here's an example configuration file that defines three MCP servers:
 
 ```yaml
+$schema: "https://raw.githubusercontent.com/lastmile-ai/mcp-agent/main/schema/mcp-agent.config.schema.json"
+
 mcp:
   servers:
     fetch:
@@ -185,35 +216,148 @@ mcp:
     filesystem:
       command: "npx"
       args: ["-y", "@modelcontextprotocol/server-filesystem", "."]
+    slack:
+      command: "npx"
+      args: ["-y", "@modelcontextprotocol/server-slack"]
+```
+
+For servers that require sensitive information like API keys, you can:
+1. Define them directly in the config file (not recommended for production)
+2. Use a separate `mcp_agent.secrets.yaml` file (more secure)
+3. Set them as environment variables
+
+### Methods for Configuring MCP
+
+The OpenAI Agents SDK supports several ways to configure MCP servers:
+
+#### 1. Automatic Discovery (Recommended)
+
+The simplest approach lets the SDK automatically find your configuration file if it's named `mcp_agent.config.yaml` and `mcp_agent.secrets.yaml`:
+
+```python
+from agents import Agent, Runner
+
+# Create an agent that references MCP servers
+agent = Agent(
+    name="MCP Assistant",
+    instructions="You are a helpful assistant with access to MCP tools.",
+    mcp_servers=["fetch", "filesystem"]  # Names of servers from your config file
+)
+
+# The context object will be automatically populated
+class AgentContext:
+    pass
+
+result = await Runner.run(agent, input="Hello world", context=AgentContext())
+```
+
+#### 2. Explicit Config Path
+
+You can explicitly specify the path to your config file:
+
+```python
+class AgentContext:
+    def __init__(self, mcp_config_path=None):
+        self.mcp_config_path = mcp_config_path  # Will be used to load the config
+
+context = AgentContext(mcp_config_path="/path/to/mcp_agent.config.yaml")
 ```
 
-2. Create a context object and specify which MCP servers to use with your agent:
+#### 3. Programmatic Configuration
+
+You can programmatically define your MCP settings:
 
 ```python
-from agents import Agent, Run, function_tool
+from mcp_agent.config import MCPSettings, MCPServerSettings
+
+# Define MCP config programmatically
+mcp_config = MCPSettings(
+    servers={
+        "fetch": MCPServerSettings(
+            command="uvx",
+            args=["mcp-server-fetch"]
+        ),
+        "filesystem": MCPServerSettings(
+            command="npx",
+            args=["-y", "@modelcontextprotocol/server-filesystem", "."]
+        )
+    }
+)
 
-# Create a simple context class that will hold the MCP server registry
 class AgentContext:
-    def __init__(self, mcp_config_path=None, mcp_config=None):
-        self.mcp_config_path = mcp_config_path  # Optional specific path to config file
-        self.mcp_config = mcp_config # Optional programmatic setting of MCP server settings
+    def __init__(self, mcp_config=None):
+        self.mcp_config = mcp_config
 
-# Create an agent that specifies which MCP servers to use
+context = AgentContext(mcp_config=mcp_config)
+```
+
+#### 4. Custom Server Registry
+
+You can create and configure your own MCP server registry:
+
+```python
+from mcp_agent.mcp_server_registry import ServerRegistry
+from mcp_agent.config import get_settings
+
+# Create a custom server registry
+settings = get_settings("/path/to/config.yaml")
+server_registry = ServerRegistry(config=settings)
+
+# Create an agent with this registry
+agent = Agent(
+    name="Custom Registry Agent",
+    instructions="You have access to custom MCP servers.",
+    mcp_servers=["fetch", "filesystem"],
+    mcp_server_registry=server_registry  # Use custom registry
+)
+```
+
+### Examples
+
+#### Basic Hello World
+
+A simple example demonstrating how to create an agent that uses MCP tools:
+
+```python
+# Create an agent with MCP servers
 agent = Agent(
     name="MCP Assistant",
-    instructions="You are a helpful assistant.",
-    tools=[your_local_tool],  # Local tools you define
-    mcp_servers=["fetch", "filesystem"],  # MCP servers to use (must be in config)
+    instructions="You are a helpful assistant with access to tools.",
+    tools=[get_current_weather],  # Local tools
+    mcp_servers=["fetch", "filesystem"],  # MCP servers
+)
+
+# Run the agent
+result = await Runner.run(
+    agent,
+    input="What's the weather in Miami? Also, can you fetch the OpenAI website?",
+    context=AgentContext(),
 )
 
-# Run the agent - tools from specified MCP servers will be automatically loaded
-result = await Run.run(
-    starting_agent=agent,
-    input="Print the first paragraph of https://openai.github.io/openai-agents-python/", # uses MCP fetch server
-    context=AgentContext(),  # Server registry loads automatically
+print(result.response.value)
+```
+
+See [hello_world.py](examples/mcp/basic/hello_world.py) for the complete example.
+
+#### Streaming Responses
+
+To stream responses instead of waiting for the complete result:
+
+```python
+result = Runner.run_streamed(  # Note: No await here
+    agent,
+    input="Print the first paragraph of https://openai.github.io/openai-agents-python/",
+    context=context,
 )
+
+# Stream the events
+async for event in result.stream_events():
+    if event.type == "raw_response_event" and isinstance(event.data, ResponseTextDeltaEvent):
+        print(event.data.delta, end="", flush=True)
 ```
 
+See [hello_world_streamed.py](examples/mcp/basic/hello_world_streamed.py) for the complete example.
+
 For more details, read the [MCP examples README](examples/mcp/README.md) and try out the [examples/mcp/basic/hello_world.py](examples/mcp/basic/hello_world.py) for a complete working example.
 
 ## Acknowledgements

pyproject.toml

@@ -1,12 +1,12 @@
 [project]
-name = "openai-agents"
+name = "openai-agents-mcp"
 version = "0.0.3"
-description = "OpenAI Agents SDK"
+description = "MCP-compatible fork of OpenAI Agents SDK"
 readme = "README.md"
 requires-python = ">=3.10"
 license = "MIT"
 authors = [
-    { name = "OpenAI", email = "[email protected]" },
+    { name = "Sarmad Qadri", email = "[email protected]" },
 ]
 dependencies = [
     "openai>=1.66.2",
@@ -32,8 +32,8 @@ classifiers = [
 ]
 
 [project.urls]
-Homepage = "https://github.com/openai/openai-agents-python"
-Repository = "https://github.com/openai/openai-agents-python"
+Homepage = "https://github.com/saqadri/openai-agents-mcp"
+Repository = "https://github.com/saqadri/openai-agents-mcp"
 
 [dependency-groups]
 dev = [