Skip to main content
Glama
czlonkowski

n8n-MCP

by czlonkowski
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
TypeScript
Hybrid

search_templates

Read-onlyIdempotent

Find n8n workflow templates by keyword, node types, task, metadata, or pattern. Use search modes to locate automation templates based on text, specific nodes, complexity, setup time, or services.

Instructions

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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskNoFor searchMode=by_task: the type of task. For searchMode=patterns: optional category filter (omit for overview of all categories).
limitNoMaximum number of results. Default 20.
queryNoFor searchMode=keyword: search keyword (e.g., "chatbot")
fieldsNoFor searchMode=keyword: fields to include in response. Default: all fields.
offsetNoPagination offset. Default 0.
categoryNoFor searchMode=by_metadata: filter by category (e.g., "automation", "integration")
nodeTypesNoFor searchMode=by_nodes: array of node types (e.g., ["n8n-nodes-base.httpRequest", "n8n-nodes-base.slack"])
complexityNoFor searchMode=by_metadata: filter by complexity level
searchModeNoSearch mode. keyword=text search (default), by_nodes=find by node types, by_task=curated task templates, by_metadata=filter by complexity/services, patterns=lightweight workflow pattern summarieskeyword
targetAudienceNoFor searchMode=by_metadata: filter by target audience (e.g., "developers", "marketers")
maxSetupMinutesNoFor searchMode=by_metadata: maximum setup time in minutes
minSetupMinutesNoFor searchMode=by_metadata: minimum setup time in minutes
requiredServiceNoFor searchMode=by_metadata: filter by required service (e.g., "openai", "slack")

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.66.2
  2. Removedv2.65.2
  3. Addedv2.56.0
  4. Removedv2.55.0
  5. Changed3 schema fields changedv2.48.3
    • changedInput schema / properties / searchMode / description
      Previous value: -"Search mode. keyword=text search (default), by_nodes=find by node types, by_task=curated task templates, by_metadata=filter by complexity/services"New value: +"Search mode. keyword=text search (default), by_nodes=find by node types, by_task=curated task templates, by_metadata=filter by complexity/services, patterns=lightweight workflow pattern summaries"
    • changedInput schema / properties / searchMode / enum
      Previous value: -[
-  "keyword",
-  "by_nodes",
-  "by_task",
-  "by_metadata"
-]New value: +[
+  "keyword",
+  "by_nodes",
+  "by_task",
+  "by_metadata",
+  "patterns"
+]
    • changedInput schema / properties / task / description
      Previous value: -"For searchMode=by_task: the type of task"New value: +"For searchMode=by_task: the type of task. For searchMode=patterns: optional category filter (omit for overview of all categories)."
  6. Changed15 schema fields changedv1.0.0
    • addedInput schema / properties / category
      Added value: +{
+  "description": "For searchMode=by_metadata: filter by category (e.g., \"automation\", \"integration\")",
+  "type": "string"
+}
    • addedInput schema / properties / complexity
      Added value: +{
+  "description": "For searchMode=by_metadata: filter by complexity level",
+  "enum": [
+    "simple",
+    "medium",
+    "complex"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / fields
      Added value: +{
+  "description": "For searchMode=keyword: fields to include in response. Default: all fields.",
+  "items": {
+    "enum": [
+      "id",
+      "name",
+      "description",
+      "author",
+      "nodes",
+      "views",
+      "created",
+      "url",
+      "metadata"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / limit / maximum
      Added value: +100
    • addedInput schema / properties / limit / minimum
      Added value: +1
    • addedInput schema / properties / maxSetupMinutes
      Added value: +{
+  "description": "For searchMode=by_metadata: maximum setup time in minutes",
+  "maximum": 480,
+  "minimum": 5,
+  "type": "number"
+}
    • addedInput schema / properties / minSetupMinutes
      Added value: +{
+  "description": "For searchMode=by_metadata: minimum setup time in minutes",
+  "maximum": 480,
+  "minimum": 5,
+  "type": "number"
+}
    • addedInput schema / properties / nodeTypes
      Added value: +{
+  "description": "For searchMode=by_nodes: array of node types (e.g., [\"n8n-nodes-base.httpRequest\", \"n8n-nodes-base.slack\"])",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / offset
      Added value: +{
+  "default": 0,
+  "description": "Pagination offset. Default 0.",
+  "minimum": 0,
+  "type": "number"
+}
    • changedInput schema / properties / query / description
      Previous value: -"Search keyword as string. Example: \"chatbot\""New value: +"For searchMode=keyword: search keyword (e.g., \"chatbot\")"
    • addedInput schema / properties / requiredService
      Added value: +{
+  "description": "For searchMode=by_metadata: filter by required service (e.g., \"openai\", \"slack\")",
+  "type": "string"
+}
    • addedInput schema / properties / searchMode
      Added value: +{
+  "default": "keyword",
+  "description": "Search mode. keyword=text search (default), by_nodes=find by node types, by_task=curated task templates, by_metadata=filter by complexity/services",
+  "enum": [
+    "keyword",
+    "by_nodes",
+    "by_task",
+    "by_metadata"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / targetAudience
      Added value: +{
+  "description": "For searchMode=by_metadata: filter by target audience (e.g., \"developers\", \"marketers\")",
+  "type": "string"
+}
    • addedInput schema / properties / task
      Added value: +{
+  "description": "For searchMode=by_task: the type of task",
+  "enum": [
+    "ai_automation",
+    "data_sync",
+    "webhook_processing",
+    "email_automation",
+    "slack_integration",
+    "data_transformation",
+    "file_processing",
+    "scheduling",
+    "api_integration",
+    "database_operations"
+  ],
+  "type": "string"
+}
    • removedInput schema / required
      Removed value: -[
-  "query"
-]
  7. First observed

TDQS

A4.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the tool is safe and idempotent. The description adds behavioral clarity by detailing the five distinct search modes and their parameters (e.g., 'patterns' mode uses 2700+ templates for summaries), without contradicting annotations. The explanation of 'patterns' as lightweight summaries is extra context beyond annotations, but it lacks details on pagination behavior or result format, keeping it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that efficiently enumerates all five modes and their purposes without redundancy. Every clause adds value (e.g., 'lightweight workflow pattern summaries mined from 2700+ templates'), and it's front-loaded with the main action ('Search templates with multiple modes').

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 13 parameters, no output schema, and rich sibling context, the description is remarkably complete. It covers the core behavior (five search modes), when to use each, and hints at return differences (e.g., 'patterns' yields summaries). With readOnlyHint and idempotentHint annotations, no additional safety info is needed. The only minor gap is no explicit mention of result pagination, but the schema's offset/limit parameters suffice.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters. The description adds value by grouping parameters by search mode (e.g., 'query' for keyword, 'nodeTypes' for by_nodes), providing context not in the schema. However, for parameters like 'category' and 'targetAudience', the description only restates what the schema says, offering no deeper semantics, so it doesn't fully reach a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches templates with multiple modes, enumerates each mode with its specific use case (e.g., 'searchMode=keyword' for text search, 'by_nodes' to find templates using specific nodes), and distinguishes itself from siblings like search_nodes (which likely searches for nodes, not templates). The explicit listing of five search modes provides a precise scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells when to use each mode (e.g., 'Use searchMode=keyword for text search, by_nodes to find templates using specific nodes'), which directly guides the AI agent in selecting the right approach. It implies that for template-related searches this tool is appropriate, while siblings like search_nodes are for node-level searches, providing clear separation of concerns.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools