Trainual MCP Server

由您的代理构建的 Trainual 中的主题、话题、步骤和任务。

托管 MCP 服务器

npx add-mcp 'https://cotlet.dev/mcp/v1/trainual'

可安装到 Claude Code、Codex、Cursor 等客户端

文档

Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up

Trainual API and MCP server: Let your AI agent write your Trainual SOPs.

Trainual has an official MCP server and a REST API, both on the Premium and Enterprise plans only (checked 28 Oct 2026). The MCP server only reads, and the API assigns training and manages users but cannot create, edit or publish a subject. Cotlet runs 11 Trainual tools hosted, over MCP for agents and REST for scripts, and does the writing.

Subjects, topics, steps and assignments in your Trainual, built by your agent. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.

MCP setup REST API guide

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by Trainual. Trainual is a trademark of its owner. If Trainual's own integrations cover what you need, use them first.

What can you automate in Trainual?

  • Turn notes into a draft subject
  • Add topics and steps
  • Change a policy in every step
  • Publish a finished subject
  • Assign onboarding to new hires
  • List who has not finished

Does Trainual have an MCP server or an API?

  • Trainual's help center on its MCP server: "All MCP tools are read-only. Connected agents and apps can query your Trainual data, but they can't create, edit, or delete anything in Trainual." Tokens come from an Admin+ user and expire after 365 days.
  • On the API: "Content creation and editing aren't supported by the API yet." The v3 spec has GET routes for subjects, documents and pages and none that write them; content reads return published content only.
  • Zapier can invite, archive and assign subjects and roles on any plan. No Zapier action writes content, and n8n has no Trainual node.
What you needOfficial MCPAPI v3Cotlet
PlansPremium, EnterprisePremium, EnterpriseAny plan
Search subjects and read stepsYesPublished onlyYes, drafts too
Create a subject, topics and stepsNoNo, "on our roadmap"Yes, as a draft
Edit a step, publish a subjectNoNoYes, after your OK
Assign a subject to peopleNoYesYes, after your OK

Checked 28 Oct 2026. Sources: Trainual Help: Trainual's API & Webhooks, Trainual Help: The Trainual MCP Server, Trainual Help: Create & Publish Subjects, Trainual Help: Integrations, Trainual API v3 reference, Zapier: Trainual integrations

How does Cotlet connect to Trainual?

  1. Sign in to Trainual. Use your own account in its Cotlet Cloud Browser.
  2. Choose MCP or REST. Connect your agent or create a Cotlet API key.
  3. Run your workflow. Ask your agent or send an HTTP request.

We never keep your Trainual password, and nothing your employees see changes until you approve it.

Connect Trainual to your agent or workflow

Use MCP with your AI agent, or HTTP requests in n8n, Make, Zapier and scripts. Follow the MCP setup below or jump to the REST guide.

  1. Sign in to Trainual in a Cloud Browser. Make a Cotlet account, open Trainual in its Cloud Browser, log in with your usual Trainual login or SSO and press Enable for agents.
  2. Add the Cotlet address. Enter https://cotlet.dev/mcp/v1 as the MCP server or connector URL in your agent.
  3. Approve the connection. Chat apps send you to a Cotlet sign-in page. Code editors, n8n and scripts use an API key from the console.

One address, https://cotlet.dev/mcp/v1, serves Trainual and any other app you enable. You need no Trainual MCP token and no Admin+ role. If the Trainual tools are missing after you enable it, refresh the connector.

Claude:

Settings > Connectors > Add custom connector
URL: https://cotlet.dev/mcp/v1/connect

Claude Code:
claude mcp add --transport http cotlet-trainual \
  https://cotlet.dev/mcp/v1 \
  --header "Authorization: Bearer $COTLET_API_KEY"

ChatGPT:

Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth

Cursor:

// ~/.cursor/mcp.json
{
  "mcpServers": {
    "cotlet-trainual": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": { "Authorization": "Bearer ${env:COTLET_API_KEY}" }
    }
  }
}

Codex:

# ~/.codex/config.toml
[mcp_servers.cotlet-trainual]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"

n8n:

MCP Client Tool (inside an AI Agent)
Transport: HTTP Streamable
URL: https://cotlet.dev/mcp/v1
Auth: Bearer, <your key>
Tool: trainual_read

Make, Zapier:

Make: MCP Client > Call a tool
Zapier: MCP Client by Zapier > Run Tool
Server URL: https://cotlet.dev/mcp/v1
Token: <your key>
Tool: trainual_write

How to use the Trainual REST API

Create your Cotlet API key

Create a Cotlet API key with access to Trainual and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.

Connect Trainual in Cotlet and enable it for agents. Account access: Your own Trainual account. Creating and editing content needs the Author permission or higher. You sign in in your own browser and keep your SSO or 2-step verification.

Make your first Trainual API request

REST:

curl https://cotlet.dev/api/v1/trainual/subjects \
  -H "Authorization: Bearer $COTLET_API_KEY"

Read subjects and apply the operation limits

A successful REST call puts the tool output in result. This illustrative response excerpt omits call IDs, messages and credit details.

Illustrative response excerpt:

{
  "status": "success",
  "app": "trainual",
  "tool": "list_subjects",
  "result": {
    "subjects": [
      {
        "subject_id": "sub_8f2a41",
        "title": "Opening checklist",
        "tab": "Processes",
        "status": "published"
      },
      {
        "subject_id": "sub_3c9d07",
        "title": "Refund policy",
        "tab": "Policies",
        "status": "unpublished"
      }
    ]
  }
}

Returns each subject with its ID, title, tab and status (published or unpublished). Subjects you cannot open with your Trainual role are not listed.

Use the ID with get_subject, create_topic and assign_subject.

Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.

Trainual workflows for agents and automations

ToolConnect throughExample workflow
n8nHTTP RequestRead one subject with its topics and steps. Use get_subject in your configured learning report.
MakeHTTP > Make a requestRead the text of one step. Use get_step in your configured learning report.
Python or Node.jsREST APISee who has a subject assigned and whether they completed it. Use list_assignments in your configured learning report.

Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.

Cotlet reads Trainual; your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template.

Python and Node.js can use the same HTTP requests without an AI agent. Keep access keys in credentials, outside shared workflow exports.

The API and MCP reference lists operations and inputs. The REST API guide explains authentication, errors and approvals.

Trainual API endpoints and MCP tools

Subjects, topics and steps

Reads include drafts your role can open. Writing needs the Author permission or higher. Steps are text: no image, video or file uploads.

  • List subjects (list_subjects, read): Search the subjects in your Content page, with their status.
  • Get subject (get_subject, read): Read one subject with its topics and steps.
  • Get step (get_step, read): Read the text of one step.
  • Create subject (create_subject, write): Create a new subject as a draft.
  • Create topic (create_topic, write): Add a topic under a subject.
  • Add step (add_step, write): Add a step with its text to a topic.
  • Update step (update_step, write, asks first): Replace the title or text of an existing step.

Publishing and assignments

Publish as is or finish every topic first, the two choices Trainual's Publish dialog gives. Assigned people see the subject once it is published.

  • Publish subject (publish_subject, write, asks first): Publish a subject so assigned people can open it.
  • List users (list_users, read): Find people in your Trainual account.
  • Assign subject (assign_subject, write, asks first): Assign a subject to people.
  • List assignments (list_assignments, read): See who has a subject assigned and whether they completed it.

Inputs, REST path and example response of every tool: https://cotlet.dev/integrations/trainual-api-mcp-server#tools

Who can see my Trainual session, and how do I revoke it?

  • What we store. Your signed-in Trainual profile, AES-256-GCM encrypted, in Finland. No password.
  • What your agent gets. The 11 Trainual tools. No cookie, no Trainual token.
  • What the session sees. The subjects, people and completions your Trainual role can open.
  • What no tool touches. Billing, account settings, permissions, SSO, API and MCP tokens.
  • If Trainual signs you out. Your agent gets a link and you log in again. We never log in for you.
  • How to cut access. Disable Trainual for agents, reset the browser or delete the key.

Edits show under your name in Trainual's activity and version history, as if you made them. The Cotlet site scores A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory (live results).

Approvals, undo and mistakes

  1. Drafts the subject. Title, topics and steps from your notes, unpublished.
  2. Shows you the draft. Reads it back with get_subject for you to check.
  3. Waits for your OK. Publish and assign show up in your Cotlet console.
  4. Reports back. Topics published, people assigned, anyone skipped.
ActionUndo
Create a subject, topic or stepDelete it in Trainual; nobody saw a draft
Edit a stepVersion history: 30 days on Core, 90 on Pro, unlimited on Premium
Publish a subjectSet it back to Unpublished
Assign a subjectUnassign it; the person may have seen it

3 of 11 tools ask first: update_step, publish_subject and assign_subject. Reads and drafts run at once, since a draft reaches nobody. Turn the wait off per tool for a scheduled run.

Read a drafted policy before you publish it. Trainual's terms put AI text at your own risk, and the steps carry your name.

MCP call:

{
  "name": "add_step",
  "arguments": {
    "topic_id": "top_2b7",
    "title": "Set the alarm",
    "body": "Arm the alarm panel by the back door. You have 60 seconds to leave."
  }
}

REST:

curl -X POST https://cotlet.dev/api/v1/trainual/topics/top_2b7/steps \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"title":"Set the alarm","body":"Arm the alarm panel by the back door. You have 60 seconds to leave."}'

Response:

{
  "step_id": "stp_620",
  "topic_id": "top_2b7",
  "title": "Set the alarm",
  "position": 3
}

Scripts and cron jobs reach the same tools over REST at /api/v1/trainual, one key, one price. A write your Trainual role cannot make, such as add_step without Author permission, fails and costs nothing. The tools table lists the REST path of each tool.

How much does the Trainual MCP server cost?

About $16 a month for a business of about 40 people that adds a subject a week, 2,680 credits. Trainual bills your plan as before.

JobCallsCredits
Notes into a draft subject: 3 topics, 12 steps, weekly17 × 4680
Policy change across 6 steps, twice a month11 × 2220
Publish the finished subject, weekly2 × 480
Assign onboarding to new hires, weekly3 × 4120
Friday list of incomplete training2 × 480
Cloud Browser, 30 days1,500
Total2,680
  • Free 7-day trial, no card
  • 10 credits per successful call, MCP or REST
  • 50 credits a day for the Cloud Browser
  • Works on Core and Pro, no Premium needed

The month is our example. Trainual's average contract is about $4.1K a year (Getlatka, Oct 2024), and most reviewers on G2 work at 50 people or fewer. Trainual no longer shows prices; third-party sites list Core at $249 and Premium at $399 a month billed yearly for 10 seats. Dollars at the $29 pack rate.

Trainual MCP server on GitHub, Zapier or hosted: which to use

OptionWhat it doesWhere it stops
Trainual MCP serverOfficial, mcp.trainual.com: searches content and reads users, groups, responsibilities, assignments and profile documents.Read-only, Premium and Enterprise, Admin+ token that expires after 365 days.
Trainual API v3Official REST: users, groups, responsibilities, assignments, completions, activities and webhooks.Content is view-only and published-only; you write and host the code.
ZapierTriggers on completions and new users; invite, archive, assign subjects and roles.No content action at all.
GitHubNo community Trainual MCP server or CLI found. Trainual's own trainual/tiptap-collaboration-mcp (11 stars) talks to Tiptap, not to Trainual data.Nothing to run.

On Premium or Enterprise, the official MCP server answers questions from your training for free, and the API or Zapier can assign it. For drafting subjects, editing steps and publishing on any plan, Cotlet works in your own login.

Also listed on: Odel, mcpbeat

Who runs Cotlet

Cotlet belongs to Take Group sp. z o.o., a software company registered in Poland, EU (VAT PL6342984273), trading since 2019. Its founders are Bart Krawczyk (Co-founder, CTO) and Jake Slugocki (Co-founder, SEO, sales and marketing). Write to contact@cotlet.dev about the Trainual tools.

Trainual API and MCP: questions

How do I get access?

Sign up free at https://cotlet.dev, open Trainual under Integrations in the console and log in to Trainual in its Cloud Browser. The trial starts when you sign up, with no card.

How do I connect Trainual to ChatGPT or Claude?

Sign up at cotlet.dev, log in to Trainual once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your Trainual account through Cotlet, in their phone apps too.

What can ChatGPT do in Trainual?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Trainual: turn a process into a Trainual subject; update a policy across steps; assign onboarding to new hires. You ask in plain words, and anything that reaches other people waits for your OK first.

Do I need a Premium or Enterprise plan?

Trainual's own MCP server and its content endpoints need a Premium or Enterprise training plan, and tokens come from an Admin+ user (checked 28 Oct 2026). Cotlet works in your signed-in account, so it depends on your role: creating and editing content needs the Author permission or higher. Your plan still decides which features the app shows you.

Can my agent write whole subjects?

Yes, as text. It creates a subject as a draft, adds topics and steps, and you publish when you are happy. Images, video and file uploads are not covered. Trainual also has its own Smart Outline and Compose AI tools inside the editor.

Should I use Trainual's own MCP server instead?

Use it if you are on Premium or Enterprise and only want answers from published training: it is official and costs nothing extra. It cannot draft, edit, publish or assign. You can connect both to the same agent: the official one for search, Cotlet for the writing.

Does Trainual have webhooks?

Yes, on Premium and Enterprise: up to 10 per user, for events such as a completed subject, published content or an archived user. Cotlet sends no events, so run your agent on a schedule, for example a weekly list_assignments.

Is the MCP server different from the REST API?

Only the way in differs. Both carry the same 11 tools, inputs and answers, with one API key and one price. Agents use MCP; scripts and HTTP steps use REST.

Is Cotlet affiliated with Trainual?

No. Cotlet is independent and not affiliated with Trainual.

Can I use the Trainual API without an AI agent?

Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.


Give your AI agents your signed-in browser.

Product: Integrations · How it works · Pricing · Security

Resources: Blog · API docs · Help center · Changelog · GitHub

Solutions: For developers · For automation agencies

Company: About · AI info: company facts · Contact

Legal: Terms of service · Privacy policy · Refund policy · Acceptable use · Cookie policy · DPA · Subprocessors

Elsewhere: Status page · Cotlet on GitHub · Cotlet on X · Cotlet on LinkedIn · Cotlet on Product Hunt · Cotlet on Crunchbase · Cotlet on SaaSHub

Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. About us

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.