Building AI agents, atomically
atomic examples readme update for fastapi client
jon fox3978f484cd5e
diff --git a/atomic-examples/mcp-agent/README.md b/atomic-examples/mcp-agent/README.mdindex 061c468..694eb15 100644--- a/atomic-examples/mcp-agent/README.md+++ b/atomic-examples/mcp-agent/README.md@@ -14,9 +14,11 @@ An interactive agent that:- Dynamically discovers available tools- Processes natural language queries- Selects appropriate tools based on user intent-- Executes tools with extracted parameters+- Executes tools with extracted parameters (sync and async)- Provides responses in a conversational format+The client includes both synchronous (`main.py`) and asynchronous (`main_fastapi.py`) implementations. The FastAPI version demonstrates async MCP tool execution using `fetch_mcp_tools_async()` and the `arun()` method for non-blocking tool execution in web applications.+[View Example Client README](example-client/README.md)### 2. Example MCP Server (`example-mcp-server/`)@@ -110,6 +112,19 @@ This example shows the flexibility of the MCP architecture with two distinct trapoetry run python -m example_client.main --transport http_stream```+ **Using FastAPI async client:**++ ```bash+ # First terminal: Start the MCP server+ cd example-mcp-server+ poetry run python -m example_mcp_server.server --mode=http_stream++ # Second terminal: Run the async FastAPI client+ cd example-client+ poetry run python -m example_client.main_fastapi+ # Then visit http://localhost:8000 for the API interface+ ```+**Note:** When using SSE or HTTP Stream transport, make sure the server is running before starting the client. The server runs on port 6969 by default.## Example Queries