Practical MCP with FastMCP & LangChain

Progress Handler

The progress handler is responsible for receiving progress notifications from the server and using them to update the user on the status of long-running operations. This is mainly used for tools that take a significant amount of time to complete.

To report progress from the server, you use the report_progress() method on the context object. Here's an example of how that might look inside a tool (server side code):

from fastmcp import Context

async def some_long_running_task(ctx: Context):
    # ... do some work ...
    # report progress
    await ctx.report_progress(progress=<current>, total=<total>)
    # ... do more work ...
    # report more progress
    await ctx.report_progress(progress=<current>, total=<total>)
    # ... finish up ...

The client, if you want to handle these progress updates, needs to implement a handler that will receive these notifications and do something with them. In our case, we're simply going to print them in the terminal.

Here is our code:

cat > $HOME/workspace/puppy_guide/client/handlers/progress.py << 'EOF'
async def progress_handler(
    progress: float,  # current progress value sent by the server
    total: float |