Implemented
0
Feature request: Expose stop execution in Instance-level MCP
Source: n8n-io/n8n#40367 · opened by @gfrish
Summary Please expose an addressable workflow execution stop operation through the Instance-level MCP server. n8n already supports stopping a specific execution through the public API: POST /api/v1/executions/{executionId}/stop with the execution:stop scope. However, the Instance-level MCP currently exposes execution inspection tools such as: • get_workflow_execution • search_workflow_executions but does not expose an MCP tool for stopping a specific execution. This creates an important capability gap for MCP clients such as ChatGPT: they can discover executions and start workflows, but cannot safely stop one specific running or waiting execution through the same MCP interface. Environment verified Tested on: • self-hosted n8n 2.41.6 • Docker deployment • EXECUTIONS_MODE=regular • Instance-level MCP enabled The deployment uses the standard upstream n8n Docker image. What I verified For n8n 2.41.6: 1. The public API supports stopping o…
No pledges yet. Be the first to back this.
Comments
Similar requests
MCP tool calls fail in queue mode: `Tool node "<name>" does not have supplyData method` + `Worker tool execution timeout`
0 votes · 0 comments
n8n MCP server tool descriptions cause excessive token usage in Claude, hitting conversation limits quickly
0 votes · 0 comments
SQLite database file never shrinks after execution pruning/deletion — disk fills up despite pruning being enabled
0 votes · 0 comments
Feature: cross-workflow agent memory — persistent verified memory for AI Agent nodes
0 votes · 0 comments
Dynamic Multi-Action AI Tool Nodes (Unified Tool Definition for AI Agents)
0 votes · 0 comments
No comments yet.