Overview
Logic MCP servers support asynchronous task execution, allowing AI platforms to start long-running tasks without blocking while they complete. Instead of waiting for completion, the AI platform receives an execution ID and can check back later for results.How It Works
When an AI platform executes a Logic agent through MCP:- Task starts immediately - Logic begins processing
- Execution ID returned - AI platform receives a unique identifier
- Status checking - Use the
_logic_check_execution_statustool with the execution ID - Results retrieved - When complete, the tool returns the output
_logic_check_execution_status is one of Logic’s built-in
tools. In most clients it shows up with a Logic:
prefix (for example, Logic: Check Execution Status), the same naming used
for Logic: Call Agent, which starts the run this tool polls. It’s distinct
from View executions (_logic_view_executions), which lists an agent’s
past runs rather than tracking a single in-flight one.Example Flow
Running Multiple Tasks
The async model enables parallel execution. AI platforms can:- Start multiple Logic agents simultaneously
- Poll each execution ID separately
- Retrieve results as each task completes
- Without async: 10 × 30 seconds = 5 minutes total
- With async: ~30 seconds total (parallelized)
Platform Support
Different AI platforms handle async tasks automatically:- Claude platforms: Automatically poll and manage multiple executions
- ChatGPT: Check platform documentation for async behavior
- Custom clients: Call the
_logic_check_execution_statustool and implement polling logic
Next Steps
- Built-in Tools - The full set of
Logic:tools, including the status check - Review agent scope - Control which agents support async execution
- Explore integrations - See how platforms handle async tasks