MCP SERVERDescribe an automation and get importable n8n workflow JSON back, lint it for deprecated nodes and broken connections, push it to a running instance, and diagnose the executions that come out.
LABSCO SUMMARY
Most of the set is deterministic and offline, so an agent can generate a workflow, lint it and diff it before any credentials exist. The tools that reach a running instance are the exception, and need its URL and API key. A created workflow arrives inactive and needs a second call to switch on, and the diagnosis tools read an execution payload that execution_list can hand over with includeData set to true.
An n8n server that generates, lints and diffs workflow JSON offline, and separately talks to a running n8n instance over its API.
N8N_API_URL and N8N_API_KEY for every tool that reaches a live n8n instance; generation, linting, diffing and execution analysis run without them. The diagnosis tools expect the execution JSON pasted in, which the n8n UI's Show details view or the executions API returns.
One command plus a key — npm install -g @automatelab/n8n-mcp, then supply credentials
USE CASES
Generate the workflow JSON from prose, lint what comes back, post it to the instance, and switch it on once it looks right.
Find the failed run, get a per-node account of what each node emitted, and lay the same run out on a timeline to see where it stalled.
Pull the deployed workflow, then build a small replay workflow that feeds pinned items straight into the node under suspicion.
Fetch the live version, diff it against the local file to see node and connection changes, and lint whichever one you plan to keep.
Turn a sentence about what the node should do into a TypeScript file that already implements the interface n8n expects.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
execution_explainDiagnose a failed or surprising n8n execution. Paste the execution JSON (from the n8n UI 'Show details' or GET /executions/:id?includeData=true); returns a per-node summary highlighting nodes that returned 0 items, unresolved ={{ ... }} expressions, errors with hints, and LLM token usage. Hits the most common debugging pain point: items 'silently disappearing' between nodes. Deterministic, rule-based.
execution_listList recent executions from a live n8n instance (requires N8N_API_URL + N8N_API_KEY). Filter by workflowId, status (success|error|waiting), limit. Pass includeData: true to get the full execution body (large) — pair with execution_explain to diagnose a specific failure.
execution_replayBuild a self-contained replay workflow that exercises a single node from a larger workflow. The replay workflow is Manual Trigger -> Replay Seed (Code node with pinned items) -> target node. Optional inputItems or an execution payload pins what the target sees. Useful for iterating on one stubborn node without re-running the whole pipeline. Returns workflow JSON ready to import or push via workflow_create.
execution_timelineRender an n8n execution as a per-node timeline: start offset, duration, items in/out, error flag. Complements execution_explain — that one surfaces *why*, this surfaces *when*. Output is a markdown table sorted by start time. Deterministic.
node_scaffoldScaffold a TypeScript skeleton for an n8n custom node from a plain-English description. Returns a single TypeScript file implementing INodeType with description, credentials reference, and an execute method stub. Pure code generation — no network, no filesystem writes.
workflow_activateActivate or deactivate a workflow on a live n8n instance (requires N8N_API_URL + N8N_API_KEY). Pass active: false to deactivate. Idempotent — re-activating an already-active workflow is a no-op on n8n's side.
workflow_createCreate a workflow on a live n8n instance (requires N8N_API_URL + N8N_API_KEY). Strips read-only fields (id, active, createdAt, ...) before posting. Workflows are created inactive — call workflow_activate afterward. Pairs with workflow_generate for end-to-end 'describe -> deploy'.
workflow_diffSemantic diff between two workflows. Reports nodes added / removed / modified (with field-level deltas: type, typeVersion, parameters, credentials, disabled, position), connection topology changes, and settings drift. Ignores noise (small position deltas, createdAt/updatedAt). Pair with workflow_get to compare deployed vs local. Deterministic.
workflow_generateGenerate a valid n8n workflow JSON from a plain-English description. Handles webhook/schedule/RSS triggers, common action nodes (Slack, Google Sheets, Discord, Gmail, Notion, HTTP), and AI Agent setups (LangChain root agent + chat model + memory + optional HTTP tool, wired with ai_languageModel / ai_memory / ai_tool connections). Returns workflow JSON with unique node IDs, connections, positions, and typeVersion on every node. Output is non-deterministic (random node IDs and webhook paths).
workflow_getFetch a single workflow JSON by id from a live n8n instance (requires N8N_API_URL + N8N_API_KEY). Returns the full nodes/connections payload — pair with workflow_lint to audit a deployed workflow.
workflow_lintLint an n8n workflow JSON. Returns concrete errors and warnings: missing credentials, deprecated node types (Function -> Code, spreadsheetFile -> convertToFile/extractFromFile), broken connections, missing or non-numeric typeVersion, duplicate node names or IDs, AI Agent missing ai_languageModel sub-node, Webhook missing webhookId, IF node still on v1 condition schema, rate-sensitive nodes without retries, Code-node sandbox violations, expression staleness ($('NodeName') referencing missing nodes), manualTrigger in active workflows, disabled-but-wired nodes, empty Set nodes, HTTP method/body mismatches, Schedule trigger DST risk, credential drift, webhook test paths in active workflows. Deterministic, rule-based.
workflow_listList workflows from a live n8n instance (requires N8N_API_URL + N8N_API_KEY env vars). Returns id, name, active, nodeCount, updatedAt, tags. Filter by active, tags, name. Use this when the user asks 'what workflows do I have?' or before workflow_get.
BEFORE YOU INSTALL
12 tools when we connected. workflow_list, workflow_get, workflow_create, workflow_activate and execution_list need N8N_API_URL and N8N_API_KEY. N8N_MCP_READ_ONLY=1 disables workflow_create, workflow_activate and node_scaffold. Names use underscores, not dot notation.
CONTEXT COST
Rated by the size of the 12 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
npm install -g @automatelab/n8n-mcp{
"mcpServers": {
"n8n": {
"command": "npx",
"args": [
"-y",
"@automatelab/n8n-mcp"
],
"env": {
"N8N_API_URL": "<YOUR_N8N_API_URL>",
"N8N_API_KEY": "<YOUR_N8N_API_KEY>"
}
}
}
}git clone https://github.com/AutomateLab-tech/n8n-mcp
cd n8n-mcp
docker build -t n8n-mcp .
docker run --rm -i -e N8N_API_URL=<YOUR_N8N_API_URL> -e N8N_API_KEY=<YOUR_N8N_API_KEY> n8n-mcpMCP servers
pratapsfdc22-dev
leonardsellem
ninihen1