mirror of https://github.com/PrefectHQ/fastmcp.git synced 2026-08-09 15:19:10 +02:00

History

Jeremiah Lowin 74e01d5e08 Add SEP-2663 client half: transparent call_tool, ResultClaim, Task handle A FastMCP client now transparently completes tasked tools/call: the tasks ClientExtension advertises the capability and claims the CreateTaskResult, and the resolver drives the tasks/get poll loop to completion, answering in-task input through the client's elicitation handler and returning the tool's real result. call_tool is transparent, call_tool_mcp exposes the raw result, and call_tool_task yields a Task handle. The client half moves to fastmcp-tasks; the [tasks] client extension auto-wires into Client (ProxyClient opts out). Co-Authored-By: Claude <noreply@anthropic.com>		2026-07-22 15:21:10 -04:00
..
.envrc	Remove enable_tasks setting, enable task protocol by default	2025-12-09 09:34:42 -05:00
client.py	Add SEP-2663 client half: transparent call_tool, ResultClaim, Task handle	2026-07-22 15:21:10 -04:00
docker-compose.yml	[2.14] SEP-1686 tasks (#2378 )	2025-12-04 20:10:35 -05:00
README.md	Remove enable_tasks setting, enable task protocol by default	2025-12-09 09:34:42 -05:00
server.py	Add SEP-2663 client half: transparent call_tool, ResultClaim, Task handle	2026-07-22 15:21:10 -04:00

README.md

FastMCP Tasks Example

Demonstrates background task execution with Docket, including progress tracking, distributed backends, and CLI worker management.

Setup

# From the fastmcp root directory
uv sync

# Start Redis
cd examples/tasks
docker compose up -d

# Load environment (or source .envrc manually)
direnv allow

# Run the server
fastmcp run server.py

For single-process mode without Redis, set FASTMCP_DOCKET_URL=memory:// (note: CLI workers won't work).

Running the Client

# Background execution with progress callbacks
python examples/tasks/client.py --duration 10

# Immediate execution (blocks)
python examples/tasks/client.py immediate --duration 5

Starting Additional Workers

With Redis, you can run additional workers to process tasks in parallel:

fastmcp tasks worker server.py

# Configure via environment:
export FASTMCP_DOCKET_CONCURRENCY=20
fastmcp tasks worker server.py

Backend options:

memory:// - Single-process only (default)
redis:// - Distributed, multi-process (Redis or Valkey)

Environment Variables

Variable	Default	Description
`FASTMCP_DOCKET_URL`	`memory://`	Docket backend URL