Agent Tools

Synta MCP provides 23 active tools for searching nodes, shortlisting recommended nodes, configuring them, finding templates, building workflows, validating them, and testing them against a live n8n instance. The recommended flow is to discover first, shortlist likely nodes second, configure with exact node definitions third, and only then create or update workflows.

Getting Started with Agent Tools

Building Workflows
Editing Workflows

Phase 1: Discovery & Assessment

Discover Templates & Best Practices

For AI workflows, get patterns first. For standard workflows, search templates directly.

// AI Workflows: Get patterns FIRST
get_ai_workflow_patterns({mode: "list"})

// Standard Workflows: Search templates
search_templates({searchMode: "keyword", query: "slack notification"})
get_best_practices({mode: "list"})

Find Nodes

Search for specific nodes you need in your workflow.

// First pass: lightweight discovery
search_nodes({queries: ["webhook"]})
search_nodes({queries: ["slack"], source: "core"})

// Second pass: only when you need resource/operation/mode details
search_nodes({queries: ["slack"], includeOperations: true})

Phase 2: Planning

Reference Patterns & Templates

Get detailed examples and best practices for your workflow type.

// Get template details
get_template({templateId: 123, mode: "full", includeMermaid: true})

// Get best practices for techniques
get_best_practices({mode: "detail", technique: "universal"})
get_best_practices({mode: "detail", technique: "notification"})

// Get curated node suggestions for the workflow category
get_suggested_nodes({categories: ["notification"]})

// Get node configuration examples
get_node({nodeIds: [{nodeId: "n8n-nodes-base.slack"}], view: "standard", includeConfigExamples: "json"})

Phase 3: Implementation

Create Workflow

Deploy your workflow directly to n8n.

n8n_create_workflow({
  name: "My Workflow",
  nodes: [...],
  connections: {...}
})

Phase 4: Validation & Testing

Validate & Add Credentials

Check workflow structure and configure credentials.

n8n_validate_workflow({id: "wf-id"})
n8n_manage_credentials({mode: "check_workflow", workflowId: "wf-id"})

Test & Self-Heal

Execute and automatically fix runtime errors.

n8n_trigger_execution({id: "wf-id"})
// Analyzes errors, modifies config, re-executes until successful

Phase 1: Discovery & Assessment

Find & Analyze Workflow

Locate the workflow and understand its current structure.

// Find workflow by name
n8n_list_workflows({searchTerm: "slack", searchMode: "fuzzy"})

// Get workflow structure
n8n_get_workflow({id: "wf-id", mode: "structure"})

// Search within workflow
n8n_search_workflow({id: "wf-id", scope: "nodes", match_strategy: "regex", query: "HTTP"})

Phase 2: Planning

Reference Templates & Best Practices

Find examples similar to your intended changes.

search_templates({searchMode: "by_nodes", nodeTypes: ["n8n-nodes-base.slack"]})
get_best_practices({mode: "detail", technique: "data_transformation"})
get_suggested_nodes({categories: ["data_transformation"]})

Phase 3: Implementation

Modify Workflow

Make incremental updates using diff operations.

n8n_update_partial_workflow({id: "wf-id", operations: [
  {type: "addNode", node: {...}},
  {type: "updateNode", nodeName: "Transform", updates: {"parameters.keepOnlySet": true}},
  {type: "addConnection", source: "Webhook", target: "New Node"},
  {type: "rewireConnection", source: "IF", from: "OldNode", to: "NewNode", branch: "true"}
]})

Phase 4: Validation & Testing

Validate Changes

Verify your modifications are structurally correct.

n8n_validate_workflow({id: "wf-id", options: {validateConnections: true}})
n8n_autofix_workflow({id: "wf-id", applyFixes: true})

Test & Self-Heal

Execute the updated workflow and fix runtime issues.

n8n_trigger_execution({id: "wf-id"})
// If errors occur, analyzes and fixes automatically

Self-Healing: Synta MCP automatically tests workflows, detects runtime errors, and modifies configurations until successful execution. Requires N8N login credentials. See Installation for setup.

Tool Categories

Node Discovery (3)

search_nodes - Full-text search across nodesget_suggested_nodes - Curated node shortlists by workflow categoryget_node - Exact node definitions in standard, summary, or raw view

Templates (3)

search_templates - Search 10,000+ templatesget_template - Get workflow JSON by IDn8n_deploy_template - Deploy from n8n.io

AI Workflow Guides (2)

get_ai_workflow_patterns - AI architectural patternsget_best_practices - Technique guidance

Workflow Authoring (4)

n8n_create_workflow - Create workflowsn8n_get_workflow - Retrieve workflows by IDn8n_update_full_workflow - Replace full workflow definitionsn8n_update_partial_workflow - Diff-based updates with typeVersion support

Workflow Operations (3)

n8n_list_workflows - List all workflowsn8n_validate_workflow - Validate configs, connections, and expressionsn8n_delete_workflow - Permanently delete workflows

Execution & Testing (5)

n8n_trigger_execution - Self-healing testingn8n_test_workflow - External testingn8n_manage_executions - Execution managementn8n_manage_pindata - Mock data for testingn8n_inspect_node_io - Inspect node inputs and outputs

Workflow Analysis (2)

n8n_search_workflow - AST-based searchn8n_autofix_workflow - Auto-fix errors

Credentials (1)

n8n_manage_credentials - Manage credentials

Complete Tool Reference

Node Discovery & Configuration (3 tools)

search_nodes

tool

Search for n8n nodes by name or service. Use it in two passes: first for lightweight discovery, then again with includeOperations=true when you need discriminator details.

Show parameters

queries

string[]

required

Array of search terms like ["slack"], ["gmail"], or ["openai embeddings"].

includeOperations

boolean

default:"false"

When true, includes resource / operation / mode discriminator details and ready-to-copy follow-up guidance for get_node.

source

string

default:"all"

Filter: all, core, community, verified

Show recommended flow

First call search_nodes({queries: ["slack"]})
Then call search_nodes({queries: ["slack"], includeOperations: true}) only after you have found the node you want
Then call get_node(...) with the exact discriminator values you selected

get_suggested_nodes

tool

Get curated node recommendations for workflow technique categories like chatbot, notification, document_processing, or scraping_and_research.

Show parameters

tags

string[]

Filter by tags (exact match)

projectId

string

Filter by project ID (enterprise feature)

excludePinnedData

boolean

default:"true"

Exclude pinned data from response

searchTerm

string

Filter workflows by name within current page. Increase limit or use cursor for more results.

searchMode

string

default:"fuzzy"

Search mode: fuzzy=typo-tolerant (default), fulltext=prefix/token matching

excludeArchived

boolean

default:"true"

Exclude archived workflows from results

n8n_update_partial_workflow

tool

Update workflows incrementally with diff operations. Supports 17 operation types: addNode, removeNode, updateNode, moveNode, enable/disableNode, addConnection, removeConnection, rewireConnection, cleanStaleConnections, replaceConnections, updateSettings, updateName, add/removeTag, publishWorkflow, deactivateWorkflow. TypeVersion changes via updateNode are automatically validated with guidance. Supports smart parameters (branch=‘true’/‘false’ for IF nodes, case=N for Switch nodes) and AI connections.

Show parameters

string

required

Workflow ID to update

operations

object[]

required

Array of diff operations to apply sequentially

validateOnly

boolean

default:"false"

Only validate operations without applying

createBackup

boolean

Optional: create a backup/snapshot before applying operations.

executionMode

string

default:"best_effort"

Execution strategy: best_effort (recommended/default), atomic, or auto.

continueOnError

boolean

Deprecated legacy flag. Use executionMode instead.

intent

string

Optional intent text used to improve guidance and auto-mode behavior.

Show operation types

addNode, removeNode, updateNode, moveNode
enableNode, disableNode
addConnection, removeConnection, rewireConnection
cleanStaleConnections, replaceConnections
updateSettings, updateName
addTag, removeTag
publishWorkflow, deactivateWorkflow

Show connection parameters

For connections, use sourceOutput/targetInput for connection TYPE names (e.g., “main”, “ai_tool”), NOT numeric indices. For multi-output nodes (IF, Switch), use branch/case or sourceIndex.

sourceOutput: Connection type (default: “main”). AI types: ai_languageModel, ai_tool, ai_memory, etc.
targetInput: Target input type (default: “main”)
branch: For IF nodes: “true” or “false” instead of sourceIndex
case: For Switch nodes: case number (0-based) instead of sourceIndex
sourceIndex/targetIndex: Explicit indices (override branch/case)

n8n_update_full_workflow

tool

Replace an entire workflow with new configuration. For incremental updates, use n8n_update_partial_workflow instead.

Show parameters

string

required

Workflow ID to update

name

string

New workflow name

nodes

object[]

Complete array of workflow nodes

connections

object

Complete connections object

settings

object

Workflow settings to update

n8n_delete_workflow

tool

Permanently delete a workflow. This action cannot be undone.

Show parameters

string

required

Workflow ID to delete

n8n_validate_workflow

tool

Validate workflow configuration, connections, and expressions. When execution data exists, also performs runtime expression checks and reports actionable fixes.

Show parameters

string

required

Workflow ID to validate

options

object

Show properties

validateNodes

boolean

default:"true"

Validate node configurations

validateConnections

boolean

default:"true"

Validate workflow connections

validateExpressions

boolean

default:"true"

Validate n8n expressions

profile

string

default:"runtime"

minimal, runtime, ai-friendly, strict

Workflow Analysis & Utilities (2 tools)

n8n_search_workflow

tool

Search within a workflow to find nodes, connections, flow patterns, or text. Use regex matching by default for flexible substring search, exact for strict equality, or fuzzy for typo tolerance. Returns matching nodes with configurable detail levels.

Show parameters

string

required

Workflow ID to search within

scope

string

required

What to search: nodes, connections, flow, text, comprehensive

match_strategy

string

required

regex (default - flexible substring matching), exact (strict equality), fuzzy (typo-tolerant)

query

string or object

Search term. String or object with name/type/path/value. Flow patterns: “A->B->C” (use .* for any node)

options

object

Show properties

type

string or string[]

Filter by node type

target

string

Target node name (connections scope)

disabled

boolean

Filter by disabled status

parameter

object

Parameter filter: path, value, exists properties

fields

string[]

Limit text search to specific fields (text scope only)

detail_level

string

Output verbosity: minimal, standard, full

Show search strategies

regex (RECOMMENDED): Grep-like substring matching, case-insensitive. Finds “set” in “offset” or “reset”
exact: Strict equality only. Use when “set” should NOT match “reset”
fuzzy: Typo-tolerant for user errors. “slak” matches “Slack”

Show search scopes

nodes: Search by node name or type
connections: Find links between nodes
flow: Search execution paths (e.g., “Webhook->Code->Slack”)
text: Ripgrep-like regex search across all node data
comprehensive: Multi-criteria search with filters

n8n_autofix_workflow

tool

Automatically fix common workflow validation errors. Preview fixes before applying. Handles expression format, typeVersion corrections, error output config, node types, webhook paths, version migrations, and parameter locations.

Show parameters

string

required

Workflow ID to fix

applyFixes

boolean

default:"false"

Apply fixes to workflow (default: false - preview mode)

fixTypes

string[]

Types of fixes: expression-format, typeversion-correction, error-output-config, node-type-correction, webhook-missing-path, typeversion-upgrade, version-migration, parameter-location (default: all)

confidenceThreshold

string

default:"medium"

Minimum confidence level: high, medium (default), low

maxFixes

number

default:"50"

Maximum number of fixes to apply

Show fix types explained

expression-format: Fix n8n expression syntax issues
typeversion-correction: Correct node typeVersion mismatches
error-output-config: Fix error workflow configurations
node-type-correction: Update deprecated node types
webhook-missing-path: Add missing webhook paths
typeversion-upgrade: Upgrade nodes to latest supported versions
version-migration: Handle parameter migrations between versions
parameter-location: Fix misplaced parameters in node structure

Workflow Execution & Testing (5 tools)

n8n_trigger_execution

tool

Self-Healing

The most powerful tool in Synta MCP. Triggers workflows and enables true AI self-healing by automatically testing, detecting errors, analyzing root causes, and modifying configurations to fix issues. Works with n8n_manage_pindata for comprehensive testing.

Show parameters

string

required

Workflow ID to execute

triggerNode

string

Specific trigger node name to use (optional). If not specified, uses the first trigger node in the workflow.

chatMessage

string

default:"Hello world"

Message for Chat Trigger nodes

sessionId

string

Session ID for chat triggers only (optional, auto-generated if not provided)

formData

object

Form field values for Form Trigger nodes (e.g., field-0: value, field-1: 2003-05-21)

webhookData

object

JSON payload for webhook triggers (request body)

headers

object

Custom HTTP headers for webhook/form requests

timeout

number

default:"60"

Max seconds to wait for completion

includeData

boolean

default:"true"

Include execution output data

includeErrorStack

boolean

default:"false"

Include full error stack trace in error details

destinationNode

object

Partial execution target. Use mode: "exclusive" to run upstream nodes without running the destination (like n8n’s “Execute previous nodes”), or mode: "inclusive" (default) to run the destination too.

Show properties

nodeName

string

required

Target node name in the workflow

mode

string

default:"inclusive"

exclusive (run previous nodes only) or inclusive (run destination too)

Show self-healing capabilities

Auto-detection: Identifies Manual, Chat, Webhook, and Form triggers automatically
Error analysis: AI analyzes execution results to identify root causes
Self-correction: Modifies workflow configurations to fix detected issues
Full debugging: Complete execution data including all node outputs
Webhook handling: Automatically polls and calls webhook URLs when needed
Mock data integration: Works with n8n_manage_pindata to test workflows using saved mock data instead of live API calls

n8n_test_workflow

tool

External workflow testing without login credentials. Test workflows with webhook, form, or chat triggers. Workflow must be active.

Show parameters

workflowId

string

required

Workflow ID to execute

triggerType

string

webhook, form, chat (auto-detected if not specified)

httpMethod

string

GET, POST, PUT, DELETE (default: auto-detected from webhook config)

webhookPath

string

Override the webhook path

webhookData

object

JSON payload for webhook triggers (request body)

formData

object

Form field values for form triggers. Keys: field-0, field-1, etc.

message

string

Message for chat triggers

sessionId

string

Session ID for chat triggers only (optional, auto-generated if not provided)

headers

object

Custom HTTP headers for webhook/form requests

timeout

number

default:"120000"

Timeout in milliseconds

waitForResponse

boolean

default:"true"

Wait for workflow completion

returnExecution

boolean

default:"false"

Auto-fetch and return the latest execution after trigger (recommended — avoids a separate n8n_manage_executions call)

returnExecutionMode

string

default:"summary"

Detail level when returnExecution=true: summary (token-efficient) or full (complete payload)

n8n_manage_executions

tool

Comprehensive execution management with advanced correlation to trace execution chains. Use action: "get" with workflowId (no id) to fetch the latest execution for a workflow.

Show parameters

action

string

required

get, list, delete, retry, correlate

string

Execution ID (for get, delete, retry). Omit with action=get + workflowId to get the latest execution.

mode

string

default:"summary"

For get: preview, summary, filtered, full, error

includeInputData

boolean

default:"false"

For get: include input data in addition to output

itemsLimit

number

For get with mode=filtered: items per node (0=structure, 2=default, -1=unlimited)

nodeNames

string[]

For get with mode=filtered: filter to specific nodes by name

includeStackTrace

boolean

default:"false"

For get with mode=error: include full stack trace

includeExecutionPath

boolean

default:"true"

For get with mode=error: include execution path leading to error

errorItemsLimit

number

default:"2"

For get with mode=error: sample items from upstream node (max: 100)

fetchWorkflow

boolean

default:"true"

For get with mode=error: fetch workflow for accurate upstream detection

workflowId

string

For list: filter by workflow

status

string

For list: success, error, waiting

limit

number

default:"100"

For list: number of executions (1-100)

cursor

string

For list: pagination cursor from previous response

projectId

string

For list: filter by project ID (enterprise feature)

includeData

boolean

default:"false"

For list: include execution data

loadWorkflow

boolean

default:"true"

For retry: whether to load the workflow definition

executionId

string

For correlate: starting execution ID

timeWindowMs

number

default:"30000"

For correlate: time window in milliseconds

Show correlation features

Webhook path matching: Find executions triggered by HTTP calls
User context matching: Correlate by user_id, chat_id, correlation_id
Timing analysis: Find executions within configurable time window
Sub-workflow detection: Identify executeWorkflowTrigger patterns

n8n_manage_pindata

tool

Save and reuse mock data for testing workflows. Instead of calling real APIs or waiting for webhooks, save sample output from any node and reuse it in future test runs. Especially useful for triggers (webhooks, forms) but works with any node for consistent testing without external dependencies.Authentication: analyzePinDataRequirement works with API key/OAuth only. CRUD operations (add/update/remove/clear/read) require login credentials.

Show parameters

mode

string

required

analyzePinDataRequirement, addPinData, updatePinData, removePinData, clearPinData, readPinData

string

required

Workflow ID

nodeName

string

Node name to save mock data for (required for add/update/remove modes)

pinData

array

Array of mock data items to save (for add/update modes)

expectedChecksum

string

Optional checksum for conflict detection

autosaved

boolean

Mark update as autosaved (optional)

aiBuilderAssisted

boolean

Flag to mark AI-assisted updates (optional)

forceSave

boolean

Bypass checksum mismatch (optional)

Show use cases

Test webhook/form triggers without sending real HTTP requests
Avoid hitting API rate limits during development
Use the same test data every time for consistent results
Skip slow external API calls while building your workflow
Test error scenarios with custom mock data

n8n_inspect_node_io

tool

Inspect post-execution node input/output data. Use after any execution to debug expression errors, verify data shapes, or understand branch routing (IF/Switch outputs). Defaults to schema-style output (field/type shape) to keep context small.

Show parameters

executionId

string

Execution ID to inspect. Omit to use workflowId instead.

workflowId

string

Workflow ID shortcut — auto-resolves the latest execution for this workflow.

nodeName

string

Single node name to inspect (exact workflow node name)

nodeNames

string[]

Multiple node names to inspect. Omit to inspect all executed nodes.

runMode

string

default:"latest"

Run selection: latest, latestN, all, or indices

runIndices

number[]

For runMode="indices": specific 0-based run indices to inspect

runLimit

number

For runMode="latestN": how many recent runs to include

outputIndex

number

Single 0-based output index filter, useful for IF/Switch branches

valueMode

string

default:"schema"

schema (compact field/type shape) or full (raw item values)

detailMode

string

default:"summary"

summary (counts/structure) or detail (full item payloads)

outputIndices

number[]

Filter IF/Switch branches by 0-based output index

connectionTypes

string[]

Filter by connection type (main, ai_tool, ai_memory, ai_languageModel, etc.)

includeInput

boolean

default:"true"

Include input analysis (source lineage and/or inputOverride)

includeOutput

boolean

default:"true"

Include node outputs

inputMode

string

default:"both"

Input analysis mode: source, inputOverride, or both

itemsMode

string

default:"firstN"

How items are sampled from each input/output collection: firstN, lastN, all, or range

itemsLimit

number

default:"5"

For firstN and lastN: number of items to include (max 1000)

rangeStart

number

For itemsMode="range": inclusive start index

rangeEnd

number

For itemsMode="range": exclusive end index

includeBinary

boolean

default:"false"

Include binary payload metadata and content references

includePairedItem

boolean

default:"true"

Include paired item lineage metadata for each item

includeMetadata

boolean

default:"true"

Include run metadata such as status, execution time, and errors

nodePage

number

0-based node pagination page for large executions

nodePageSize

number

Number of nodes per page (1-200)

runPage

number

0-based run pagination page within each selected node

runPageSize

number

Number of runs per page (1-200)

itemPage

number

0-based item pagination page inside each inspected collection

itemPageSize

number

Items per page inside each inspected collection (1-1000)

includePaginationMeta

boolean

Include pagination metadata in the response. Defaults to true when pagination is used.

fetchWorkflow

boolean

default:"true"

Fetch workflow metadata to enrich node type and typeVersion when execution payloads are incomplete

includeContext

boolean

default:"false"

Append lightweight node context such as parents, children, counts, classification, and execution-presence flags

includeContextParameters

boolean

When includeContext=true, include workflow node parameters for inspected nodes

includeContextRunData

boolean

When includeContext=true, include the latest normalized runData entry for each inspected node

staticPreview

boolean

default:"false"

Mirror n8n NDV input preview using static upstream schemas without execution data. Requires workflowId and only works for previewable contexts.

Show usage notes

Use workflowId as a shortcut when you want the latest execution for a workflow.
Use n8n_trigger_execution with destinationNode first if you need missing input data populated for downstream nodes.
Start with valueMode="schema" and switch to full only when raw values are necessary.
staticPreview mirrors n8n’s editor preview and is best for Gmail -> Set, Telegram -> Switch, and similar previewable paths.
includeContextParameters and includeContextRunData only apply when includeContext=true.

Credentials (1 tool)

n8n_manage_credentials

tool

Manage n8n credentials with five modes: get_credential_docs, create, delete, get_schema, check_workflow.

Show parameters

mode

string

required

get_credential_docs, create, delete, get_schema, check_workflow

name

string

Credential name (for create)

type

string

Credential type e.g., “httpBasicAuth”, “gmailOAuth2Api” (for create)

data

object

Credential data with type-specific fields (for create)

string

Credential ID (for delete)

credentialTypeName

string

Credential type name (for get_schema or get_credential_docs)

nodeType

string

Node type to fetch credential docs for (for get_credential_docs when credentialTypeName not provided)

workflowId

string

Workflow ID to analyze (for check_workflow)

Next Steps

Best Practices

Learn tips and tricks for building better workflows with AI

Configure Agent Rules

Set up client-specific rules for optimal workflow building

Production Safety: Always test workflows in a development environment before deploying to production. Never edit production workflows directly without backups.

Getting Started

Features

Rules

Best Practices

Privacy

Getting Started with Agent Tools

Tool Categories

Node Discovery (3)

Templates (3)

AI Workflow Guides (2)

Workflow Authoring (4)

Workflow Operations (3)

Execution & Testing (5)

Workflow Analysis (2)

Credentials (1)

Complete Tool Reference

Next Steps

Best Practices

Configure Agent Rules

Getting Started

Features

Rules

Best Practices

Privacy

Documentation Index

​Getting Started with Agent Tools

​Tool Categories

Node Discovery (3)

Templates (3)

AI Workflow Guides (2)

Workflow Authoring (4)

Workflow Operations (3)

Execution & Testing (5)

Workflow Analysis (2)

Credentials (1)

​Complete Tool Reference

​Next Steps

Best Practices

Configure Agent Rules

Getting Started with Agent Tools

Tool Categories

Complete Tool Reference

Next Steps