n8n MCP Community

Overview Schema Source Related Servers Discussions Admin

Inspect n8n workflow

n8n_introspect

Read-onlyIdempotent

Inspect any n8n workflow and its saved executions against 23 local rules. Choose quick or deep profiles to catch configuration problems without running or modifying anything.

Instructions

Inspect one workflow and saved executions with 23 deterministic local rules. profile sets paired defaults: quick uses 24h/20 and caps maxExecutions at 25; deep uses 168h/50 and reads at most four redacted details. includeSanitizedLabels=false keeps labels opaque; true opts into bounded sanitized labels. Use n8n_audit_generate for instance security or n8n_workflows_get for raw structure. Requires workflow/execution read permission; never executes or calls AI; returns findings and coverage.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`profile`	No	Use quick for metadata triage or deep for up to four redacted execution details.	quick
`workflowId`	Yes	Stable ID of the workflow to inspect without executing it.
`lookbackHours`	No	History window in hours; defaults to 24 for quick and 168 for deep.
`maxExecutions`	No	Maximum saved executions to inspect; defaults to 20 for quick and 50 for deep, with quick capped at 25.
`includeSanitizedLabels`	No	Include bounded pattern-sanitized workflow/node labels instead of opaque identifiers only (default false).

Output Schema

TableJSON Schema

Name	Required	Description
`sample`	Yes	Exact execution-history scope, ordering confidence, requests, and byte budget used.
`status`	Yes	Whether all requested bounded evidence was collected and analyzed.
`metrics`	Yes	Factual status, duration, node-timing, and value-free error-cluster measurements.
`profile`	Yes	Effective quick or deep analysis profile used for this result.
`summary`	Yes	Counts of findings, rule outcomes, and any details omitted by output bounds.
`findings`	Yes	Ordered deterministic findings retained within the configured output limit.
`guidance`	Yes	Boundary guidance pointing to the separate instance-level n8n security audit tool.
`workflow`	Yes	Sanitized identity and basic structure of the inspected workflow.
`limitations`	Yes	Collection or analysis limitations that constrain interpretation of this result.
`ruleCoverage`	Yes	Per-rule outcome and completeness evidence, including omitted finding counts.
`engineVersion`	Yes	Version of the deterministic local analysis engine that produced this result.
`schemaVersion`	Yes	Version of the stable structured introspect result contract.

Schema Changelog

Changes observed during successful MCP inspections.

Changed17 schema fields changedv0.1.2Aug 4, 2026

addedInput schema / properties / includeSanitizedLabels / description

Added value: +"Include bounded pattern-sanitized workflow/node labels instead of opaque identifiers only (default false)."

addedInput schema / properties / lookbackHours / description

Added value: +"History window in hours; defaults to 24 for quick and 168 for deep."

addedInput schema / properties / maxExecutions / description

Added value: +"Maximum saved executions to inspect; defaults to 20 for quick and 50 for deep, with quick capped at 25."

addedInput schema / properties / profile / description

Added value: +"Use quick for metadata triage or deep for up to four redacted execution details."

addedInput schema / properties / workflowId / description

Added value: +"Stable ID of the workflow to inspect without executing it."

addedOutput schema / properties / engineVersion / description

Added value: +"Version of the deterministic local analysis engine that produced this result."

addedOutput schema / properties / findings / description

Added value: +"Ordered deterministic findings retained within the configured output limit."

addedOutput schema / properties / guidance / description

Added value: +"Boundary guidance pointing to the separate instance-level n8n security audit tool."

addedOutput schema / properties / limitations / description

Added value: +"Collection or analysis limitations that constrain interpretation of this result."

addedOutput schema / properties / metrics / description

Added value: +"Factual status, duration, node-timing, and value-free error-cluster measurements."

addedOutput schema / properties / profile / description

Added value: +"Effective quick or deep analysis profile used for this result."

addedOutput schema / properties / ruleCoverage / description

Added value: +"Per-rule outcome and completeness evidence, including omitted finding counts."

addedOutput schema / properties / sample / description

Added value: +"Exact execution-history scope, ordering confidence, requests, and byte budget used."

addedOutput schema / properties / schemaVersion / description

Added value: +"Version of the stable structured introspect result contract."

addedOutput schema / properties / status / description

Added value: +"Whether all requested bounded evidence was collected and analyzed."

addedOutput schema / properties / summary / description

Added value: +"Counts of findings, rule outcomes, and any details omitted by output bounds."

addedOutput schema / properties / workflow / description

Added value: +"Sanitized identity and basic structure of the inspected workflow."

Addedv0.1.1Jul 22, 2026

TDQS

A5/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint, idempotentHint, etc.), the description adds key behavioral context: '23 deterministic local rules,' 'never executes or calls AI,' 'requires workflow/execution read permission,' and 'returns findings and coverage.' This enriches the agent's understanding of safety and output.

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 well-structured and concise. It front-loads the core purpose, then compactly explains profile behaviors, label options, alternatives, and safety guarantees. Every sentence provides value with no filler.

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 the tool's moderate complexity, the presence of a full input schema and output schema, and clear annotations, the description is complete. It covers purpose, usage distinctions, behavior, and permissions, leaving no critical gaps for the agent to resolve.

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

Parameters5/5

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

Although schema coverage is 100%, the description adds substantial meaning beyond the schema: profile sets paired defaults (quick 24h/20 capped at 25; deep 168h/50 with at most four redacted details), and includeSanitizedLabels semantics are clarified. This helps the agent choose parameters correctly.

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 opens with a specific verb and resource: 'Inspect one workflow and saved executions with 23 deterministic local rules.' This clearly states what the tool does and differentiates it from siblings by explicitly naming alternatives like n8n_audit_generate and n8n_workflows_get for other use cases.

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 provides explicit guidance on when to use this tool versus alternatives: 'Use n8n_audit_generate for instance security or n8n_workflows_get for raw structure.' It also describes profile-based usage (quick for metadata triage, deep for redacted details) and notes the required permission.

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

Deploy Server