René's URL Explorer Experiment

{"@context":"https://schema.org","@type":"DiscussionForumPosting","headline":"How to set / get `client_id`?","articleBody":"I'd like to be able to retrieve the `client_id` from inside a tool call on an MCP server. However, it is always `None`. What do I need to set in the MCP client in order to be able to retrieve it on the server?\n\nThe client code is basically taken from the documentation:\n```\nfrom mcp import ClientSession, StdioServerParameters, types\nfrom mcp.client.stdio import stdio_client\n\nserver_params = StdioServerParameters(\n    command=\"python\",  # Executable\n    args=[\"example_server.py\"],  # Optional command line arguments\n    env=None,  # Optional environment variables\n)\n\n\nasync def run():\n    async with stdio_client(server_params) as (read, write):\n        async with ClientSession(\n            read, write\n        ) as session:\n            # Initialize the connection\n            await session.initialize()\n\n            # Call a tool\n            result = await session.call_tool(\"my_tool\")\n```\n\nThe tool function is as follows:\n\n```\nmcp = FastMCP(\"docint\")\n\n@mcp.tool()\nasync def my_tool(ctx: Context) -\u003e Optional[str]:\n    \"\"\"\n    Extracts client ID and request ID from the context.\n\n    Returns:\n        client ID and request ID from the context.\n    \"\"\"\n    return f\"{ctx.client_id} {ctx.request_id}\" # \u003c----- THIS\n```\n\nThis prints `None 2` (`client_id` as `None`).\n\nWhat am I missing?\n\nThank you.\n","author":{"url":"https://github.com/samirbajaj","@type":"Person","name":"samirbajaj"},"datePublished":"2025-03-26T05:10:15.000Z","interactionStatistic":{"@type":"InteractionCounter","interactionType":"https://schema.org/CommentAction","userInteractionCount":2},"url":"https://github.com/373/python-sdk/issues/373"}