Update basic agent

Author: saqadri

src/mcp_agent/data/templates/README_basic.md

@@ -17,8 +17,10 @@ Welcome! This project was generated by `mcp-agent init`. It’s a minimal, reada
 
 1. Add API keys to `mcp_agent.secrets.yaml` (or set env vars):
 
-   - `OPENAI_API_KEY` (recommended)
-   - `ANTHROPIC_API_KEY` (optional)
+NOTE: You can use another supported provider (e.g. Anthropic) instead, just be sure to set its API key in the `mcp_agent.secrets.yaml` (or set its env var) and import/use the relevant `AugmentedLLM` in `main.py`.
+
+- `OPENAI_API_KEY` (recommended)
+- `ANTHROPIC_API_KEY` (optional)
 
 2. Review `mcp_agent.config.yaml`:
 
@@ -38,23 +40,56 @@ You’ll see two summaries printed:
 - A summary of `README.md` from your current directory.
 - A summary of the intro page at modelcontextprotocol.io.
 
-4. Deploy a remote MCP server:
-
-### Run as an MCP server
+4. Run locally as an MCP server:
 
 - In `main.py`, UNCOMMENT the server lines that call `create_mcp_server_for_app(agent_app)` and `run_sse_async()`.
-- Start the server: `uv run main.py`
 
-When you're ready to deploy, simply run:
+- Once you see the server started, e.g.
+  ```bash
+  Uvicorn running on http://127.0.0.1:8000
+  ```
+  you can connect to it with your preferred MCP Client. For example, you can use [MCP Inspector](https://github.com/modelcontextprotocol/inspector) to explore and test the server:
 
 ```bash
-mcp-agent deploy "hello_world"
+npx @modelcontextprotocol/inspector --transport sse --server-url http://127.0.0.1:8000/sse
 ```
 
-- This wraps your app as a hosted MCP SSE server.
-- Anything decorated with `@app.tool` (or `@app.async_tool`) runs as a Temporal workflow in the cloud.
+5. Deploy a remote MCP server:
+
+When you're ready to deploy, ensure the required API keys are set in `mcp_agent.secrets.yaml` and then run:
+
+```bash
+uv run mcp-agent login
+```
+
+to authenticate to mcp-agent cloud. You will be redirected to the login page, create an mcp-agent cloud account through Google or Github.
+
+Set up your mcp-agent cloud API Key and copy & paste it into your terminal
+
+```bash
+INFO: Directing to MCP Agent Cloud API login...
+Please enter your API key 🔑:
+```
+
+In your terminal, deploy the MCP app:
+
+```bash
+uv run mcp-agent deploy hello_world --no-auth
+```
+
+The `deploy` command will bundle the app files and deploy them, wrapping your app as a hosted MCP SSE server with a URL of the form:
+`https://<server_id>.deployments.mcp-agent.com`.
+
+Anything decorated with `@app.tool` (or `@app.async_tool`) runs as a Temporal workflow in the cloud.
+
+Since the mcp-agent app is exposed as an MCP server, it can be used in any MCP client just
+like any other MCP server. For example, you can inspect and test the server using MCP Inspector:
+
+```bash
+npx @modelcontextprotocol/inspector --transport sse --server-url https://<server_id>.deployments.mcp-agent.com/sse
+```
 
-Notes
+## Notes
 
 - `app_ctx` is the MCPApp Context (configuration, logger, upstream session, etc.).
 - Logging uses `app.logger` and is forwarded as notifications when connected to an MCP client.

src/mcp_agent/data/templates/basic_agent.py

@@ -22,6 +22,8 @@
 from mcp_agent.agents.agent_spec import AgentSpec
 from mcp_agent.core.context import Context as AppContext
 from mcp_agent.workflows.factory import create_agent
+
+# We are using the OpenAI augmented LLM for this example but you can swap with others (e.g. AnthropicAugmentedLLM)
 from mcp_agent.workflows.llm.augmented_llm_openai import OpenAIAugmentedLLM
 
 # Create the MCPApp, the root of mcp-agent.
@@ -138,6 +140,7 @@ async def main():
         #########################################################
         # Create the MCP server that exposes both workflows and agent configurations,
         # optionally using custom FastMCP settings
+        # from mcp_agent.server.app_server import create_mcp_server_for_app
         # mcp_server = create_mcp_server_for_app(agent_app)
 
         # # Run the server
@@ -148,7 +151,7 @@ async def main():
     asyncio.run(main())
 
 # When you're ready to deploy this MCPApp as a remote SSE server, run:
-# > mcp-agent deploy "hello_world"
+# > uv run mcp-agent deploy "hello_world" --no-auth
 #
 # Congrats! You made it to the end of the getting-started example!
 # There is a lot more that mcp-agent can do, and we hope you'll explore the rest of the documentation.

src/mcp_agent/data/templates/secrets.yaml

@@ -2,26 +2,27 @@
 # WARNING: Keep this file secure and never commit to version control
 
 # Provider API Keys
+# We default to OpenAI, but you can configure your preferred providers here.
 # You can also set these as environment variables instead
 openai:
-  api_key: ""  # Or use OPENAI_API_KEY env var
+  api_key: "" # Or use OPENAI_API_KEY env var
 
-anthropic:
-  api_key: ""  # Or use ANTHROPIC_API_KEY env var
+# anthropic:
+#   api_key: ""  # Or remove and use ANTHROPIC_API_KEY env var
 
-google:
-  api_key: ""  # Or use GOOGLE_API_KEY env var
+# google:
+#   api_key: ""  # Or remove and use GOOGLE_API_KEY env var
 
-azure:
-  api_key: ""  # Or use AZURE_API_KEY env var
-  base_url: ""  # https://your-resource.openai.azure.com/
-  api_version: "2024-02-01"
-  # use_default_azure_credential: false  # Set to true for DefaultAzureCredential
+# azure:
+#   api_key: ""  # Or remove and use AZURE_API_KEY env var
+#   base_url: ""  # https://your-resource.openai.azure.com/
+#   api_version: "2024-02-01"
+#   # use_default_azure_credential: false  # Set to true for DefaultAzureCredential
 
-bedrock:
-  aws_access_key_id: ""  # Or use AWS_ACCESS_KEY_ID env var
-  aws_secret_access_key: ""  # Or use AWS_SECRET_ACCESS_KEY env var
-  aws_region: "us-east-1"
+# bedrock:
+#   aws_access_key_id: ""  # Or remove and use AWS_ACCESS_KEY_ID env var
+#   aws_secret_access_key: ""  # Or remove and use AWS_SECRET_ACCESS_KEY env var
+#   aws_region: "us-east-1"
 
 # MCP Server environment variables
 # mcp:
@@ -31,4 +32,4 @@ bedrock:
 #         GITHUB_PERSONAL_ACCESS_TOKEN: ghp_...
 #     brave-search:
 #       env:
-#         BRAVE_API_KEY: BSA_...
+#         BRAVE_API_KEY: BSA_...