Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mcp_client | Test and interact with MCP servers. This tool provides a complete MCP client implementation for testing and using MCP servers from within a Strands Agent. Args: action: Action to perform - "connect", "disconnect", "list_tools", "call_tool", "list_connections" connection_id: Unique identifier for this connection transport: Transport type - "http", "stdio", or "sse" server_url: URL for HTTP/SSE transport (e.g., "http://localhost:8000/mcp") command: Command for stdio transport (e.g., "python") args: Arguments for stdio command (e.g., ["mcp_server_stdio.py"]) tool_name: Name of tool to call (for call_tool action) tool_args: Arguments to pass to tool (for call_tool action) Returns: Result dictionary with status and content Examples: # Connect to HTTP server mcp_client( action="connect", connection_id="my-server", transport="http", server_url="http://localhost:8000/mcp" ) # Connect to stdio server
mcp_client(
action="connect",
connection_id="stdio-server",
transport="stdio",
command="python",
args=["mcp_server_stdio.py"]
)
# List tools from connection
mcp_client(action="list_tools", connection_id="my-server")
# Call a tool
mcp_client(
action="call_tool",
connection_id="my-server",
tool_name="calculator",
tool_args={"expression": "2 + 2"}
)
# List all connections
mcp_client(action="list_connections")
# Disconnect
mcp_client(action="disconnect", connection_id="my-server") Notes: - stdio transport: Server must be launchable as subprocess - HTTP transport: Server must be already running - Connections are maintained in global state for reuse |
| greet | Greet someone with different styles. Args: name: The name of the person to greet style: Greeting style - "friendly", "formal", or "enthusiastic" Returns: str: A greeting message |
| invoke_agent | Invoke the full strands-mcp-cli agent with a natural language prompt. Use this for complex queries that require reasoning across multiple tools or when you need a conversational response from the agent. |