Back to Details

using-n8n-mcp-skills

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Using the n8n-mcp Skills

使用n8n-mcp技能

This is a router, not a reference. It tells you which skill owns the rules for what you're about to do. The skill bodies hold the actual guidance — invoke them with the Skill tool. When in doubt, load more skills rather than fewer.
The community n8n-mcp server and n8n itself move faster than any model's training cutoff. Tool names, parameters, node 
typeVersion
s, and default behaviors drift between releases. When you spot drift — a tool a skill names doesn't exist, a parameter shape doesn't match what 
get_node
returns, behavior differs from what a skill describes — trust the live tool, tell the user, and suggest updating the pack and the instance.
这是一个路由技能，而非参考文档。它会告诉你，你即将执行的任务对应的规则由哪个技能负责。具体的指导内容在各技能主体中——请使用Skill工具调用它们。如有疑问，应加载更多技能而非更少。
社区版n8n-mcp服务器和n8n本身的更新速度快于任何模型的训练截止日期。工具名称、参数、节点
typeVersion
以及默认行为会随版本迭代发生变化。当你发现差异时——比如技能提及的工具不存在、参数结构与
get_node
返回的不匹配、行为与技能描述不符——请以实时工具为准，告知用户，并建议更新技能包和实例。

Non-negotiables

不可协商的规则

Three rules with no exceptions. Each one prevents a class of workflow that looks correct but breaks in production.
  1. Invoke the relevant skill before any n8n action — not just before MCP calls. Before writing an expression, configuring a node, designing a workflow, wiring a connection, or writing Code, invoke the matching skill. PreToolUse hooks remind you on the highest-impact tool calls, but they exist only in the Claude Code plugin install. Everywhere else — Claude.ai skill uploads, and any client that loads this pack as an Agent Plugin (Codex, Cursor, Copilot and the rest) — nothing nudges you and the responsibility is entirely yours. Assume you are un-hooked unless you have seen a hook fire this session.
  2. Validate AND verify before activating. Run 
    validate_workflow
    (or 
    n8n_validate_workflow
    by id) before you activate, and call 
    n8n_get_workflow
    after every create or update to inspect the 
    connections
    object. Validation alone misses silently dropped wires, Merge index off-by-one, and error outputs that were never wired. Validation passing means the JSON is well-formed — not that the workflow is correct.
  3. Secrets never go in text fields. Tokens, API keys, and passwords always go through the n8n credential system. If no native node exists, use the HTTP Request node with the official credential type. A Set node holding a token referenced via 
    {{ $json.token }}
    is a leak with extra steps. See 
    n8n-mcp-tools-expert
    .
三条无例外规则，每条规则都能避免一类看似正常但会在生产环境中崩溃的工作流。
  1. 执行任何n8n操作前调用相关技能——不仅是调用MCP工具之前。在编写表达式、配置节点、设计工作流、连接节点或编写代码之前，调用对应的技能。PreToolUse钩子会在高影响工具调用时提醒你，但该钩子仅在Claude Code插件安装版本中存在。在其他环境中——Claude.ai技能上传、任何将此技能包作为Agent插件加载的客户端（Codex、Cursor、Copilot等）——没有任何提示，责任完全由你承担。除非你在本次会话中看到钩子触发，否则默认你未启用钩子。
  2. 激活前必须验证并确认。激活前运行
    validate_workflow
    （或通过ID调用
    n8n_validate_workflow
    ），每次创建或更新后调用
    n8n_get_workflow
    检查
    connections
    对象。仅靠验证无法发现静默断开的连接、Merge节点索引偏移以及未连接的错误输出。验证通过仅表示JSON格式正确——不代表工作流功能正常。
  3. 机密信息绝不能放在文本字段中。令牌、API密钥和密码必须始终通过n8n凭证系统处理。如果没有原生节点，使用带有官方凭证类型的HTTP Request节点。使用Set节点存储令牌并通过
    {{ $json.token }}
    引用，只会增加泄露风险。详情请见
    n8n-mcp-tools-expert
    。

Lean on skills, not training data

依赖技能，而非训练数据

n8n changes constantly. "Remembered" parameter names are often silently wrong — they validate as plain strings and then do nothing at runtime. Trust the skills and the live tools (
get_node
, 
search_nodes
, 
tools_documentation
) over recollection. If a skill contradicts your memory, trust the skill. If 
get_node
contradicts a skill, trust the tool and flag the drift.
n8n一直在变化。“记忆中的”参数名称往往已悄悄失效——它们会被验证为普通字符串，但在运行时毫无作用。相比记忆，更应信任技能和实时工具（
get_node
、
search_nodes
、
tools_documentation
）。如果技能与你的记忆不符，请信任技能。如果
get_node
与技能不符，请信任工具并标记差异。

Strong defaults

强默认规则

Each skill owns its own exceptions; these are the defaults.
  • The Code node is a last resort. Expression first, then an arrow function inside Edit Fields, then a Code node only when neither can do the job. See 
    n8n-code-javascript
    .
  • A Set node feeding 0–1 consumers is almost always wrong. Inline the expression at the consumer instead. See 
    n8n-expression-syntax
    .
  • Per-item iteration is automatic. Don't add a Loop Over Items node to "make it loop" when default per-item execution already handles the case.
  • Configure from the live schema, never from memory. 
    get_node
    before you set parameters. See 
    n8n-node-configuration
    .
每个技能都有自己的例外情况；以下是默认规则。
  • Code节点是最后选择。优先使用表达式，其次是Edit Fields中的箭头函数，仅当两者都无法完成任务时才使用Code节点。详情请见
    n8n-code-javascript
    。
  • Set节点仅为0-1个消费者提供数据几乎总是错误的。应在消费者节点处内联表达式。详情请见
    n8n-expression-syntax
    。
  • 逐项迭代是自动的。当默认的逐项执行已能处理时，无需添加Loop Over Items节点来“实现循环”。
  • 始终根据实时模式配置，而非记忆。设置参数前先调用
    get_node
    。详情请见
    n8n-node-configuration
    。

Red flags: "about to ___" → invoke ___

危险信号：“即将___” → 调用___

If you catch yourself thinking any of these, stop and invoke the named skill first.
ThoughtInvoke
"This workflow is simple, I'll just build it"
n8n-workflow-patterns
— most "simple" flows ship at 10+ nodes
"I'll add a Set node to map these fields"
n8n-expression-syntax
— Set feeding ≤1 consumer is the #1 antipattern
"I'll just use a Code node, it's easier"
n8n-code-javascript
— the bar is high; most reaches are expressions or Edit Fields
"The user mentioned data, I'll write Python"
n8n-code-javascript
— default JS; Python (
n8n-code-python
) only on explicit ask
"I'm writing code an AI agent will call"
n8n-code-tool
— a different runtime contract from the Code node
"Date math — I'll drop in a DateTime node"
n8n-expression-syntax
— Luxon inline is almost always right
"I'll wire a Merge with 3 sources"
n8n-node-configuration
— Merge defaults to 2 inputs; the 3rd silently drops
"Validation passed, I'm ready to activate"
n8n-validation-expert
+ 
n8n-workflow-patterns
— run the antipattern scan
"Validation threw an error I don't understand"
n8n-validation-expert
— what each error and warning means, and which are must-fix vs. best-practice advice
"I'll reference 
$json.x
here"
n8n-expression-syntax
— prefer 
$('Node').item.json.x
in branchy workflows
"This webhook/scheduled flow is happy-path only"
n8n-error-handling
— wire an error branch on every fallible node; 4xx caller faults, 5xx yours
"I'll pass this file/image through as JSON"
n8n-binary-and-data
— file contents live in 
$binary
, and can't cross the agent-tool boundary
"I'll wire up an AI agent and give the model some tools"
n8n-agents
— tool names & descriptions ARE the prompt; memory, structured output, and topology have traps
"I'll copy this logic into another workflow" / "this is getting big"
n8n-subworkflows
— extract a reusable sub-workflow; search before building
"I'll create that credential / open that workflow" (account has >1 instance)
n8n-multi-instance
— every call hits the currently-targeted instance; reads misroute silently, and an ambiguous credential write fails closed with 
INSTANCE_AMBIGUOUS
如果你产生以下任何想法，请立即停止并先调用指定技能。
想法调用技能
“这个工作流很简单，我直接构建就行”
n8n-workflow-patterns
——大多数“简单”流程实际包含10个以上节点
“我要添加一个Set节点来映射这些字段”
n8n-expression-syntax
——Set节点仅为≤1个消费者提供数据是头号反模式
“我直接用Code节点，更简单”
n8n-code-javascript
——使用门槛很高；大多数场景用表达式或Edit Fields即可
“用户提到了数据，我要写Python代码”
n8n-code-javascript
——默认使用JS；仅当用户明确要求时才使用Python（
n8n-code-python
）
“我要编写AI Agent会调用的代码”
n8n-code-tool
——与Code节点的运行时协议不同
“日期计算——我要添加一个DateTime节点”
n8n-expression-syntax
——内联Luxon几乎总是正确选择
“我要连接3个源到Merge节点”
n8n-node-configuration
——Merge节点默认仅支持2个输入；第3个会被静默丢弃
“验证通过了，我可以激活了”
n8n-validation-expert
+ 
n8n-workflow-patterns
——运行反模式扫描
“验证抛出了我看不懂的错误”
n8n-validation-expert
——解释每个错误和警告的含义，以及哪些必须修复、哪些是最佳实践建议
“我要在这里引用
$json.x
”
n8n-expression-syntax
——在分支较多的工作流中，优先使用
$('Node').item.json.x
“这个Webhook/定时工作流只处理正常情况”
n8n-error-handling
——为每个可能出错的节点连接错误分支；4xx错误由调用方导致，5xx错误由我方导致
“我要将这个文件/图片作为JSON传递”
n8n-binary-and-data
——文件内容存储在
$binary
中，无法跨Agent-工具边界传递
“我要连接AI Agent并给模型提供一些工具”
n8n-agents
——工具名称和描述就是提示词；内存、结构化输出和拓扑结构存在陷阱
“我要把这个逻辑复制到另一个工作流中” / “这个工作流变得太大了”
n8n-subworkflows
——提取可复用的子工作流；先搜索再构建
“我要创建该凭证/打开该工作流”（账号有多个实例）
n8n-multi-instance
——每次调用都会命中当前目标实例；读取操作会静默路由错误，模糊的凭证写入操作会因
INSTANCE_AMBIGUOUS
失败并关闭

Skill index

技能索引

SkillReach for it when
using-n8n-mcp-skills
This router (auto-loaded). Names the skill that owns your task.
n8n-mcp-tools-expert
Choosing or calling any n8n-mcp tool; node discovery; credentials; data tables; security audit; templates
n8n-workflow-patterns
Designing or building a workflow; picking an architecture (webhook / HTTP API / database / AI agent / scheduled / batch)
n8n-node-configuration
Configuring any node; operation-aware required fields; property dependencies; surgical field edits
n8n-expression-syntax
Writing 
{{ }}
, 
$json
/
$node
/
$now
; mapping data between nodes; the transform gatekeeper; Set-node discipline
n8n-validation-expert
Interpreting validation errors/warnings; false positives; the validation loop; auto-fix; reviewing an existing workflow
n8n-code-javascript
Any Code node in JavaScript; data access; 
this.helpers
; DateTime; SplitInBatches loop patterns
n8n-code-python
A Code node specifically requested in Python; standard-library limits
n8n-code-tool
The AI-agent-callable Custom Code Tool (
toolCode
) — returns a string, no 
$fromAI
/
$input
n8n-error-handling
Webhook/API or unattended workflows; wiring error outputs; retries; 4xx/5xx response shapes; silent failures
n8n-binary-and-data
Files, images, PDFs, attachments, uploads/downloads, vision; passing a file to/from an agent tool
n8n-subworkflows
Reusable / multi-step builds; Execute Workflow; extracting shared logic; Define-Below inputs; all-vs-each; exposing a workflow as an agent tool
n8n-agents
AI Agent / LLM-with-tools / Text Classifier; tool design & 
$fromAI
; system prompts; structured output; memory; RAG; human review; chat bots
n8n-multi-instance
Accounts with multiple instances (the 
n8n_instances
tool is present); switching the target instance; verifying before credential writes; recovering from an unexpected 
NOT_FOUND
, wrong/empty reads, or an 
INSTANCE_AMBIGUOUS
credential-write fail-close
n8n-self-hosting
Deployment, not workflow-building — self-hosting / installing / deploying n8n on a VM (Docker Compose + Caddy, single vs queue mode), or updating / backing up / hardening it. Triggers on its own; not part of the build flow above.
技能使用场景
using-n8n-mcp-skills
本路由技能（自动加载）。指明你的任务对应的负责技能。
n8n-mcp-tools-expert
选择或调用任何n8n-mcp工具；节点发现；凭证管理；数据表；安全审计；模板
n8n-workflow-patterns
设计或构建工作流；选择架构（Webhook / HTTP API / 数据库 / AI Agent / 定时 / 批量）
n8n-node-configuration
配置任何节点；基于操作的必填字段；属性依赖；精准字段编辑
n8n-expression-syntax
编写
{{ }}
、
$json
/
$node
/
$now
；节点间数据映射；转换管控；Set节点规范
n8n-validation-expert
解读验证错误/警告；误报；验证循环；自动修复；审查现有工作流
n8n-code-javascript
任何JavaScript语言的Code节点；数据访问；
this.helpers
；日期时间；SplitInBatches循环模式
n8n-code-python
用户明确要求使用Python的Code节点；标准库限制
n8n-code-tool
AI Agent可调用的自定义代码工具（
toolCode
）——返回字符串，无
$fromAI
/
$input
n8n-error-handling
Webhook/API或无人值守工作流；连接错误输出；重试；4xx/5xx响应格式；静默故障
n8n-binary-and-data
文件、图片、PDF、附件、上传/下载、视觉处理；在Agent工具间传递文件
n8n-subworkflows
可复用/多步骤构建；执行工作流；提取共享逻辑；Define-Below输入；全量vs逐项；将工作流暴露为Agent工具
n8n-agents
AI Agent / 带工具的LLM / 文本分类器；工具设计与
$fromAI
；系统提示词；结构化输出；内存；RAG；人工审核；聊天机器人
n8n-multi-instance
拥有多个实例的账号（存在
n8n_instances
工具）；切换目标实例；凭证写入前验证；从意外的
NOT_FOUND
、错误/空读取或
INSTANCE_AMBIGUOUS
凭证写入失败中恢复
n8n-self-hosting
部署，而非工作流构建——在VM上自托管/安装/部署n8n（Docker Compose + Caddy，单实例vs队列模式），或更新/备份/加固n8n。会自行触发；不属于上述构建流程。

n8n-mcp tools — working knowledge from turn one

n8n-mcp工具——从入门到精通

Qualified names look like 
mcp__<server>__<tool>
(
<server>
is usually 
n8n-mcp
). This closes the gap where a tool's full description isn't loaded until first use.
Two tiers, and how to tell which one you have. The documentation and validation tools below work offline and are always present. The 
n8n_*
management tools talk to a live n8n instance and appear only once one is connected. If they are absent, nothing is broken and there is nothing to retry — say so plainly and point the user at the right fix for their install:
  • Hosted (
    https://api.n8n-mcp.com/mcp
    )     — sign in through the OAuth prompt the client shows on first use, then connect the n8n instance in the dashboard. No environment variables, and no API key pasted into a config file.
  • Self-hosted (
    npx n8n-mcp
    , Docker)     — the server needs 
    N8N_API_URL
    and 
    N8N_API_KEY
    in its environment, exported before the client starts.
n8n_health_check
confirms a working connection and returns the resolved instance.
Discovery & docs
  • tools_documentation
    — meta-docs for every tool; 
    {topic:"ai_agents_guide", depth:"full"}
    for the agent guide.
  • search_nodes
    — find nodes by keyword.
  • get_node
    — node info. Takes a single SHORT-form 
    nodeType
    (
    nodes-base.httpRequest
    , 
    nodes-langchain.agent
    ), plus 
    detail
    (minimal/standard/full) and 
    mode
    (info/docs/search_properties/versions).
  • validate_node
    — validate one node's config in isolation (profiles: minimal/runtime/ai-friendly/strict).
  • search_templates
    / 
    get_template
    — the template library (by keyword, nodes, task, metadata).
Build & edit
  • n8n_create_workflow
    — create from full workflow JSON.
  • n8n_update_partial_workflow
    — incremental diff ops (
    {id, operations:[…]}
    ): addNode, updateNode, patchNodeField, addConnection, setNodeGroups, activateWorkflow, etc. Preferred for edits.
  • Canvas groups (n8n 2.28+) survive your edits without being managed: a grouped node you remove is pruned from its group, and a group n8n can no longer accept is ungrouped so the edit still lands — nodes and connections untouched, every adjustment reported in 
    details.warnings
    . To create or change groups, use the 
    setNodeGroups
    op (full replacement; 
    []
    ungroups everything). See 
    n8n-mcp-tools-expert
    .
  • n8n_update_full_workflow
    — full replacement.
  • n8n_autofix_workflow
    — auto-fix common issues.
  • n8n_deploy_template
    — deploy a template to the instance.
Validate (necessary, not sufficient — always pair with the antipattern scan)
  • validate_workflow
    — full JSON in, errors/warnings/fixes out. Node types here are LONG form (
    n8n-nodes-base.set
    ).
  • n8n_validate_workflow
    — validate a deployed workflow by 
    {id}
    (no node JSON to inspect).
Inspect & lifecycle
  • n8n_get_workflow
    — fetch a workflow (full / structure / active / filtered / minimal). Use it to verify 
    connections
    after edits; 
    mode="filtered"
    + 
    nodeNames
    reads one heavy node (e.g. long Code source) without pulling the whole workflow, which can truncate client-side.
  • n8n_list_workflows
    — list/filter (search before duplicating logic).
  • n8n_delete_workflow
    , 
    n8n_workflow_versions
    (history/rollback), 
    n8n_instances
    (multi-instance accounts only: list/switch the target instance — see 
    n8n-multi-instance
    ), 
    n8n_health_check
    (returns the resolved 
    instanceName
    ).
Test & run
  • n8n_test_workflow
    — runs real nodes (Code, HTTP, DB writes, sends all fire). Ask the user before running when side effects exist.
  • n8n_executions
    — list/inspect executions. There is no 
    execute_workflow
    tool.
  • n8n_evaluations
    — evaluation test runs: list runs, aggregated metrics, per-case results (n8n ≥ 2.30), plus 
    run
    /
    cancel
    to start or stop a run (n8n ≥ 2.32). 
    run
    executes the workflow against its whole dataset — real nodes fire, so ask the user first. A 403 can mean the API key was created before the action's minimum version (re-create it for the testRun scopes), evaluations aren't licensed on the plan, or the key's owner lacks access to the workflow — for 
    run
    /
    cancel
    , specifically the 
    workflow:execute
    scope.
Data, folders, credentials, audit
  • n8n_manage_datatable
    — Data Table CRUD, filtering, dry-run.
  • n8n_manage_folders
    — workflow folder CRUD with contents counts (n8n ≥ 2.19, registered Community tier and up; 
    projectId
    defaults to 
    personal
    ). Place workflows via 
    parentFolderId
    on 
    n8n_create_workflow
    or the 
    moveToFolder
    op (n8n ≥ 2.32). Placement is write-only — verify via a folder's 
    get
    counts, never by reading the workflow. 
    delete
    without 
    transferToFolderId
    moves the folder's workflows to the project root and ARCHIVES them — they still exist, but deactivated (
    transferToFolderId: "0"
    = transfer to project root without archiving).
  • n8n_manage_credentials
    — credential CRUD + 
    getSchema
    discovery.
  • n8n_audit_instance
    — security audit (hardcoded secrets, unauthenticated webhooks, error-handling gaps).
Node-type form trap: 
get_node
/ 
validate_node
take SHORT form (
nodes-base.set
); workflow JSON inside 
validate_workflow
/ 
n8n_create_workflow
uses LONG form (
n8n-nodes-base.set
). Mixing them is a common, silent mistake — see 
n8n-mcp-tools-expert
.
完整名称格式为
mcp__<server>__<tool>
（
<server>
通常为
n8n-mcp
）。这填补了工具完整描述需首次使用后才加载的空白。
两个层级，以及如何区分。以下文档和验证工具可离线使用，且始终存在。
n8n_*
管理工具会与实时n8n实例通信，仅在连接实例后才会出现。如果这些工具不存在，并非出现故障，无需重试——直接告知用户，并根据其安装方式提供正确的修复方案：
  • 托管版（
    https://api.n8n-mcp.com/mcp
    ）    ——首次使用时通过客户端显示的OAuth提示登录，然后在仪表板中连接n8n实例。无需环境变量，也无需将API密钥粘贴到配置文件中。
  • 自托管版（
    npx n8n-mcp
    ，Docker）    ——服务器环境中需要设置
    N8N_API_URL
    和
    N8N_API_KEY
    ，需在客户端启动前导出。
n8n_health_check
可确认连接正常，并返回已解析的实例。
发现与文档
  • tools_documentation
    ——所有工具的元文档；使用
    {topic:"ai_agents_guide", depth:"full"}
    获取Agent指南。
  • search_nodes
    ——按关键词查找节点。
  • get_node
    ——节点信息。接受单个短格式
    nodeType
    （如
    nodes-base.httpRequest
    、
    nodes-langchain.agent
    ），以及
    detail
    （minimal/standard/full）和
    mode
    （info/docs/search_properties/versions）参数。
  • validate_node
    ——单独验证一个节点的配置（配置文件：minimal/runtime/ai-friendly/strict）。
  • search_templates
    / 
    get_template
    ——模板库（按关键词、节点、任务、元数据检索）。
构建与编辑
  • n8n_create_workflow
    ——从完整工作流JSON创建工作流。
  • n8n_update_partial_workflow
    ——增量差异操作（
    {id, operations:[…]}
    ）：addNode、updateNode、patchNodeField、addConnection、setNodeGroups、activateWorkflow等。优先用于编辑操作。
  • 画布分组（n8n 2.28+）会在编辑时自动保留：移除分组中的节点会将其从分组中删除，n8n无法接受的分组会被取消分组以确保编辑生效——节点和连接不受影响，所有调整会在
    details.warnings
    中报告。要创建或修改分组，请使用
    setNodeGroups
    操作（完全替换；
    []
    表示取消所有分组）。详情请见
    n8n-mcp-tools-expert
    。
  • n8n_update_full_workflow
    ——完全替换工作流。
  • n8n_autofix_workflow
    ——自动修复常见问题。
  • n8n_deploy_template
    ——将模板部署到实例。
验证（必要但不充分——始终需配合反模式扫描）
  • validate_workflow
    ——输入完整JSON，输出错误/警告/修复方案。此处节点类型为长格式（如
    n8n-nodes-base.set
    ）。
  • n8n_validate_workflow
    ——通过
    {id}
    验证已部署的工作流（无需检查节点JSON）。
检查与生命周期
  • n8n_get_workflow
    ——获取工作流（完整/结构/激活状态/过滤/极简）。用于编辑后检查
    connections
    ；使用
    mode="filtered"
    + 
    nodeNames
    可读取单个大型节点（如长代码源）而无需拉取整个工作流，避免客户端截断。
  • n8n_list_workflows
    ——列出/过滤工作流（复制逻辑前先搜索）。
  • n8n_delete_workflow
    、
    n8n_workflow_versions
    （历史/回滚）、
    n8n_instances
    （仅多实例账号可用：列出/切换目标实例——详情请见
    n8n-multi-instance
    ）、
    n8n_health_check
    （返回已解析的
    instanceName
    ）。
测试与运行
  • n8n_test_workflow
    ——运行真实节点（Code、HTTP、数据库写入、发送操作都会执行）。当存在副作用时，运行前需询问用户。
  • n8n_executions
    ——列出/检查执行记录。没有
    execute_workflow
    工具    。
  • n8n_evaluations
    ——评估测试运行：列出运行记录、聚合指标、单案例结果（n8n ≥ 2.30），以及
    run
    /
    cancel
    启动或停止运行（n8n ≥ 2.32）。
    run
    会针对整个数据集执行工作流——真实节点会执行，因此运行前需询问用户。403错误可能表示API密钥创建早于操作的最低版本（为testRun权限重新创建密钥）、计划未授权使用评估功能，或密钥所有者无工作流访问权限——对于
    run
    /
    cancel
    ，特指
    workflow:execute
    权限。
数据、文件夹、凭证、审计
  • n8n_manage_datatable
    ——数据表CRUD、过滤、试运行。
  • n8n_manage_folders
    ——工作流文件夹CRUD及内容计数（n8n ≥ 2.19，已注册社区版及以上；
    projectId
    默认为
    personal
    ）。通过
    n8n_create_workflow
    的
    parentFolderId
    或
    moveToFolder
    操作（n8n ≥ 2.32）放置工作流。放置为写入操作——需通过文件夹的
    get
    计数验证，而非读取工作流。不带
    transferToFolderId
    的
    delete
    操作会将文件夹中的工作流移至项目根目录并归档——工作流仍存在，但处于停用状态（
    transferToFolderId: "0"
    表示移至项目根目录但不归档）。
  • n8n_manage_credentials
    ——凭证CRUD + 
    getSchema
    发现。
  • n8n_audit_instance
    ——安全审计（硬编码机密、未认证Webhook、错误处理漏洞）。
节点类型格式陷阱：
get_node
/ 
validate_node
接受短格式（如
nodes-base.set
）；
validate_workflow
/ 
n8n_create_workflow
中的工作流JSON使用长格式（如
n8n-nodes-base.set
）。混用格式是常见的静默错误——详情请见
n8n-mcp-tools-expert
。

The protocol, in order

流程步骤

  1. Recognize the matching skill from the index and invoke it before the first MCP call.
  2. Skim 
    tools_documentation
    once per session to refresh the tool surface if you're unsure.
  3. get_node
    before configuring any node — read the live schema, don't assume.
  4. Build / edit, then 
    validate_workflow
    before activating     and 
    n8n_get_workflow
    after     to check 
    connections
    .
  5. Surface any drift you notice (missing tool, changed parameter, diverging behavior).
  1. 从索引中识别匹配的技能，并在首次调用MCP工具前调用该技能。
  2. 若不确定工具情况，每次会话先浏览一次
    tools_documentation
    以刷新工具认知。
  3. 配置任何节点前先调用
    get_node
    ——读取实时模式，不要凭假设。
  4. 构建/编辑后，激活前调用
    validate_workflow
    ，并调用
    n8n_get_workflow
    检查
    connections
    。
  5. 发现任何差异（工具缺失、参数变更、行为不符）时告知用户。

When in doubt

疑问处理

  • Can't find a workflow the user built in the UI? The most common cause is per-workflow MCP access being off. Ask them to open it in n8n, go to Settings, and enable MCP access.
  • User says it's broken? Believe them. Re-check parameters against 
    get_node
    , trace data references, inspect the execution. See 
    n8n-validation-expert
    .
  • No skill fits and the task is non-trivial? Ask before guessing.
These are opinionated best practices, not laws. Disagree with a call? It's all markdown — edit the skill.
  • **在UI中找不到用户构建的工作流？**最常见原因是该工作流的MCP访问权限未开启。请用户在n8n中打开该工作流，进入设置并启用MCP访问。
  • **用户说工作流坏了？**请相信用户。对照
    get_node
    重新检查参数，追踪数据引用，检查执行记录。详情请见
    n8n-validation-expert
    。
  • **找不到匹配的技能且任务非 trivial？**请先询问用户再猜测。
这些是有倾向性的最佳实践，而非强制规定。不同意某个规则？所有内容都是markdown格式——你可以编辑该技能。