Get documentation for n8n MCP tools. Call without parameters for quick start guide. Use topic parameter to get documentation for specific tools. Use depth='full' for comprehensive documentation.

Search n8n nodes by keyword with optional real-world examples. Pass query as string. Example: query="webhook" or query="database". Returns max 20 results. Use includeExamples=true to get top 2 template configs per node.

Get node info with progressive detail levels and multiple modes. Detail: minimal (~200 tokens), standard (~1-2K, default), full (~3-8K). Modes: info (default), docs (markdown documentation), search_properties (find properties), versions/compare/breaking/migrations (version info). Use format='docs' for readable documentation, mode='search_properties' with propertyQuery for finding specific fields.

Validate n8n node configuration. Use mode='full' for comprehensive validation with errors/warnings/suggestions, mode='minimal' for quick required fields check. Example: nodeType="nodes-base.slack", config={resource:"channel",operation:"create"}

Get template by ID. Use mode to control response size: nodes_only (minimal), structure (nodes+connections), full (complete workflow).

Search templates with multiple modes. Use searchMode='keyword' for text search, 'by_nodes' to find templates using specific nodes, 'by_task' for curated task-based templates, 'by_metadata' for filtering by complexity/setup time/services, 'patterns' for lightweight workflow pattern summaries mined from 2700+ templates.

Full workflow validation: structure, connections, expressions, AI tools. Returns errors/warnings/fixes. Essential before deploy.

Create workflow. Requires: name, nodes[], connections{}. Created inactive. Returns workflow with ID.

Get workflow by ID with different detail levels. n8n has a draft/publish model: the workflow body holds the draft (latest edits); use mode='active' to see the published graph that is actually running. Modes: 'full' (draft + metadata), 'details' (full + execution stats), 'active' (published graph only), 'structure' (nodes/connections topology), 'filtered' (full config of only the nodes named in nodeNames - use to read one heavy node without the whole workflow), 'minimal' (id/name/active/tags).

Full workflow update. Requires complete nodes[] and connections{}. For incremental use n8n_update_partial_workflow.

Update workflow incrementally with diff operations. Types: addNode, removeNode, updateNode, patchNodeField, moveNode, enable/disableNode, addConnection, removeConnection, rewireConnection, cleanStaleConnections, replaceConnections, updateSettings, updateName, setNodeGroups, add/removeTag, activate/deactivateWorkflow, transferWorkflow, moveToFolder. patchNodeField requires fieldPath (dot path, e.g. "parameters.jsCode") and patches: [{find, replace}]. setNodeGroups replaces all canvas groups: [{name, nodeNames|nodeIds}] (or [] to ungroup). moveToFolder moves the workflow into a folder (n8n 2.32+): {parentFolderId: folder ID or null for project root}. See tools_documentation("n8n_update_partial_workflow", "full") for details.

Permanently delete a workflow. This action cannot be undone.

List workflows (minimal metadata only). Returns id/name/active/dates/tags. Check hasMore/nextCursor for pagination.

Validate workflow by ID. Checks nodes, connections, expressions. Returns errors/warnings/suggestions.

Automatically fix common workflow validation errors. Preview fixes or apply them. Fixes expression format, typeVersion, error output config, webhook paths, connection structure issues (numeric keys, invalid types, ID-to-name, duplicates, out-of-bounds indices).

Run a workflow. method=auto (default) triggers it over HTTP through its webhook/form/chat trigger. Workflows without such a trigger need n8n's MCP server: method=prepare lists the nodes that need pinned data, method=pinned runs the workflow with that data, method=direct starts a run with optional inputs. The official methods need N8N_MCP_ACCESS_TOKEN and the workflow's "Available in MCP" setting (exposeToMcp: true enables it after you confirm with the user).

Manage workflow executions: get details, list, or delete. Use action='get' with id for execution details, action='list' (the default) for listing executions, action='delete' to remove execution record.

Run and read evaluation test runs for a workflow. Reading requires n8n >= 2.30, run/cancel require n8n >= 2.32, and the API key must be created on the matching release to carry the testRun scopes; run/cancel also need the key owner to hold workflow:execute on the workflow. Actions: list_runs=list runs for a workflow, get_run=single run with aggregated metrics, list_cases=per-case results (paginate - cases can be large), run=trigger a run on a workflow with an evaluation trigger, cancel=stop a running run.

Check n8n instance health and API connectivity. Use mode='diagnostic' for detailed troubleshooting with env vars and tool status.

Manage workflow version history, rollback, comparison, and cleanup. Six modes:

• list: Show version history for a workflow

• get: Get details of a specific version

• rollback: Restore workflow to a previous version (creates backup first)

• diff: Compare two versions

• delete: Delete specific version or all versions for a workflow

• prune: Manually trigger pruning to keep N most recent versions

Two sources:

• source: 'local' (default) - snapshots n8n-mcp takes before it changes a workflow. Scoped to your n8n instance, works on any n8n version, and covers only changes made through n8n-mcp. Old backups are pruned automatically (10 most recent per workflow, plus an age-based retention window).

• source: 'native' - n8n's own workflow history, the same list the n8n UI shows, including edits made by people in the UI. Needs an n8n MCP access token and the workflow's "Available in MCP" setting; supports list, get, rollback and diff only. Native rollback is not pre-validated.

Deploy a workflow template from n8n.io directly to your n8n instance. Deploys first, then auto-fixes common issues (expression format, typeVersions). Returns workflow ID, required credentials, and fixes applied.

Manage n8n data tables, rows and columns. Actions: createTable, listTables, getTable, updateTable, deleteTable, getRows, insertRows, updateRows, upsertRows, deleteRows, addColumn, deleteColumn, renameColumn. The column actions run through n8n's own MCP server (N8N_MCP_ACCESS_TOKEN, n8n 2.34+) because the public API cannot change a table's columns after creation; everything else uses the public API.

Manage workflow folders (n8n 2.19+; folders need a registered Community instance or higher). Actions: create, list, get, rename, move, delete. projectId defaults to 'personal' (the calling user's personal project). Place workflows into folders via n8n_create_workflow's parentFolderId or the moveToFolder operation of n8n_update_partial_workflow (both n8n 2.32+). Note: n8n's API cannot report which folder a workflow is in - folder contents are visible only as counts.

Manage n8n credentials. Actions: list, get, create, update, delete, getSchema. Use getSchema to discover required fields before creating. For list, page beyond 100 results with cursor (from the previous response's nextCursor). NOTE: list/get need an n8n deployment whose public API permits credential reads — older n8n versions, restricted API keys, or instance settings can reject them, returning NOT_SUPPORTED (create, delete, getSchema — and update where the API version supports it — still work). SECURITY: credential data values are never logged.

Security audit of n8n instance. Combines n8n's built-in audit API (credentials, database, nodes, instance, filesystem risks) with deep workflow scanning (hardcoded secrets via 50+ regex patterns, unauthenticated webhooks, error handling gaps, data retention risks). Returns actionable markdown report with remediation steps using n8n_manage_credentials and n8n_update_partial_workflow.

Manage n8n Agents (persisted assistants with a model, instructions, tools, skills, tasks, memory and channels) through n8n's instance-level MCP server. Requires N8N_MCP_ACCESS_TOKEN (MCP API key from n8n Settings → Instance-level MCP) and n8n >= 2.34 with the agents module. Actions: reference, search, get, create, mutate, validate, call, publish, unpublish, revert, versions, delete, discover_assets, verify_mcp_server, update_integration. Start with action=reference (config shape and mutate operations), then discover_assets → create → mutate (one resource at a time, always with the latest configHash) → validate. projectId for create, discover_assets and verify_mcp_server defaults to your personal project. publish only when the user explicitly asks. call runs the agent with real credentials and tools and may return approvals[] that need a human decision — never approve on the user's behalf. This is not the AI Agent workflow node; use get_node for that.

Resolve the real options behind a node's dynamic dropdown (loadOptions) or resource-locator search (listSearch) using one of the instance's credentials — Slack channels, Google Sheets tabs, model lists — so workflow configs use existing IDs instead of invented ones. Requires N8N_MCP_ACCESS_TOKEN. Find methodName/methodType in get_node output (dynamicOptions on a property) and the credentialId with n8n_manage_credentials list.

List instance-level catalog entries: projects (with the personal project marked, needed as projectId for agents and data tables) or tags. Reads the Public API first; when team projects are not licensed there, falls back to n8n's MCP server if N8N_MCP_ACCESS_TOKEN is set.