MCP server for n8n: generate workflow JSON, lint, explain failed executions, diff workflows, and drive a live n8n instance via REST. 9 tools across workflow, node, and execution namespaces.
MCP server for n8n with tools for generating workflows, linting, diagnosing failed executions, and driving live n8n instances. Built for AI agents. Runs locally from the @automatelab/n8n-mcp npm package.
Gemini CLI instructions for actions-marketplace-validations/AutomateLab-tech_n8n-mcp, covering n8n-mcp, tool routing, when the user describes a flow and loading deeper context.
Use when the user wants to build, debug, or extend an n8n workflow - generating workflow JSON from a description, scaffolding a custom TypeScript node, building an AI agent (LangChain cluster), iterating over items, writing Code-node JS, linting an existing workflow, diagnosing a failed execution, or driving a live…
Scan an MCP server for protocol features deprecated or removed by the 2026-07-28 spec release candidate, and emit a dated migration checklist. CLI + GitHub Action + MCP server. Runs locally from the mcp-deprecate npm package.
Static analysis scanner for MCP server code and multi-tenant SaaS applications. 57 deterministic rules covering tenant isolation, tool visibility, cache key scoping, RLS, IDOR, and credential vault isolation. MCP server for AI agent integration. Runs locally from the mcp-tenant-isolation npm package.
Vet a Model Context Protocol (MCP) server for safety before installing or connecting it. Use when the user wants to check, audit, scan, or review an MCP server for prompt-injection, data-exfiltration, or malicious capabilities — given a directory, npm package, GitHub repo, or a tools/list JSON dump.
Heimdall — a security scanner for Model Context Protocol (MCP) servers. Vet a server, or a whole agent config, before your agent trusts it. Runs locally from the mcp-heimdall-scan npm package.
Audit an MCP server for conformance — lint its tool schemas and behaviorally fuzz it (call tools with malformed input), then score it 0–100 (grade A–F) with the exact findings and fixes. Use when the user wants to check, test, validate, score, benchmark, or debug an MCP server, its tools or tool schemas, or figure out…