The server itself exposes 35 tools, and some of them can write to your n8n account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches n8n.

How is this different from connecting n8n MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the n8n MCP API changes?

We track the n8n MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different n8n tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in n8n?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the n8n MCP server myself?

No. TrustGate connects to the n8n MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to n8n directly.

Connect n8n MCP to your AI agents, securely.

One secured endpoint for every n8n call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try n8n MCP now

What your agents can ask once n8n MCP is connected.

Select the tools your AI agents can call

35 tools from the n8n MCP schema.

Showing 35 tools

search_workflowsreadSearches for workflows with optional filters on name, project, tags and folder. Returns a preview of each workflow.
get_workflow_detailsreadGets detailed information about a workflow, including trigger details. Credential references are stripped.
execute_workflowhigh riskExecutes a workflow by ID in manual or production mode. Returns the execution ID immediately.
test_workflowwriteTests a workflow using pin data to bypass external services and credentials.
prepare_workflow_pin_datareadPrepares test pin data for a workflow, returning JSON Schemas for each node that needs it.
publish_workflowhigh riskPublishes a workflow, creating an active version from the current draft and making it live.
unpublish_workflowhigh riskUnpublishes a workflow, stopping it from running in production.
get_workflow_historyreadLists the saved version history of a workflow, newest first.
get_workflow_versionreadRetrieves the full content of a specific workflow version from its history.
get_workflow_versions_diffreadCompares two saved versions of a workflow and returns what changed between them.
restore_workflow_versionwriteRestores a workflow to a previous version from its history as the current draft.
update_workflowwriteUpdates an existing workflow by applying an ordered batch of targeted partial updates.
archive_workflowwriteArchives a workflow by its ID.
get_workflow_executionreadGets execution details by execution ID and workflow ID. Returns metadata only by default.
search_workflow_executionsreadSearches for workflow executions with filters on status and start time.
get_workflow_sdk_referencereadGets the n8n Workflow SDK reference: patterns, expression syntax, functions, rules and design guidance.
search_nodesreadSearches for n8n nodes by service name, trigger type or utility function.
get_node_typesreadGets TypeScript type definitions for n8n nodes, with exact parameter names and structures.
get_workflow_best_practicesreadGets best-practices guidance for a workflow technique such as scheduling, triage or enrichment.
explore_node_resourcesreadResolves the real values behind a node's dropdown, such as Slack channels or Sheets tabs. Reaches out to the external service.
validate_workflowreadValidates n8n Workflow SDK code, parsing it into a workflow and checking for errors.
validate_node_configreadValidates one or more node configurations independently against their node schemas.
create_workflow_from_codewriteCreates a workflow in n8n from validated SDK code.
search_projectsreadSearches for projects accessible to the current user.
search_foldersreadSearches for folders within a project.
list_workflow_tagsreadLists all workflow tags in the instance, usable as search filters.
list_credentialsreadLists credentials the current user can access. Credential secret data is never returned.
get_instance_contextreadReads the opening picture of the instance: which workflows exist, what changed recently and what has run.
get_instance_activityreadReads the instance activity log: what was created, changed, published or deleted, and by whom.
expand_instance_activityreadReads one activity log entry together with everything else the log holds about the same resource.
get_node_usagereadReports which node types the instance already uses and how widely.
search_agentsreadSearches the agents the current user can access.
get_agentreadReads an agent draft, its skills, tasks, custom tools and runnable state.
get_agent_builder_referencereadReturns the reference for agent configuration, including the agent configuration JSON Schema.
discover_agent_assetsreadDiscovers model catalogs, chat integrations, attachable workflows, published sub-agents or MCP registry servers for configuring an agent.

What n8n MCP exposes

n8n MCP groups its 35 tools into 7 categories, each with a suggested starting policy.

All 35 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Workflows	Workflow search, details, execution, testing, publishing and version history	Read / Write	Require approval before executing or publishing workflows
Executions	Execution details and search with status and time filters	Read	Execution data can contain payloads; treat it as sensitive
Builder	SDK reference, node search, node types, validation and workflow creation from code	Read / Write	Validate before creating; approve workflow creation
Projects & Folders	Project search, folder search and workflow tags	Read	Limit to intended projects
Credentials	Listing credentials the user can access, never their secret data	Read	Secrets are never returned; still limit who can list them
Instance Context	Instance snapshot, activity log and node usage across the estate	Read	Reports only workflows marked Available in MCP
Agents	Searching and reading agents, the agent builder reference and assets available to configure an agent	Read	Read-only; safe to allow

Connect n8n MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect n8n
Find n8n in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow n8n MCP or block it. You allow the exact tools each agent can call, one by one.

n8n MCP	35 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 35 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is n8n MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	n8n MCP35 documented tools.
Coding assistants	Connection & credentialsper user	Workflows13 tools
Internal copilots	Tool access policiesdeny by default	Builder8 tools
Workflow automations	Request & response inspectioninline	Instance Context4 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools10 tools