Thought Industries MCP Server

Learners, enrollments, waitlists and completion reports for your Thought Industries academy.

Hosted MCP Server

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

Installs into Claude Code, Codex, Cursor and more

Documentation

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

Thought Industries API and MCP server: Let your AI agent handle Thought Industries enrollments.

Not an MCP server you can use yet: the developer docs mark it "Coming soon" and say "The MCP Server is not yet available" (checked 27 Oct 2026). The REST API reads learners, courses and the course action feed and can enroll and import, but "API, webhooks and SFTP" is included only on Enterprise, an add-on on Professional and missing on Starter. Cotlet runs 11 Thought Industries tools hosted, over MCP for agents and REST for scripts, on any plan.

Learners, enrollments, waitlists and completion reports for your Thought Industries academy. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.

MCP setup REST API guide

What can you automate in Thought Industries?

  • Import new hires and send invites
  • Enroll a learner on request
  • Move people off a waitlist
  • Mark outside training as completed
  • Report completions and certificates weekly
  • Check Auto Assignment rules

Does Thought Industries have an MCP server or an API?

  • The announced MCP server lists 5 tools (courses, a learner, enrollments, enroll, create a course) and will need a scoped API key, so it needs API access too.
  • The TI Admin Claude Plugin is in beta, runs in Claude desktop only and writes course drafts. It has no learner, enrollment or report skills.
  • The REST API has no call for waitlists, seat limits or Auto Assignment rules, and no call that sets a learner's status on a course.
What you needREST APIClaude plugin (beta)Cotlet
List learners and their coursesYesNoYes, by name or email
Enroll and import learnersYes, import from a CSV URLNoYes, after your OK
Completions and certificatescourseAction feedNoContent Actions Log
Waitlists and seat limitsWaitlist read onlyNoRead and change
Draft course contentYesYes, draftsNo
What you need firstEnterprise, or the Professional add-on, plus codeAPI access and Claude desktopAn admin login, any plan

Checked 27 Oct 2026. Sources: Thought Industries developer docs: MCP Server, Thought Industries developer docs: REST API, Thought Industries developer docs: TI Admin Claude Plugin, Thought Industries developer docs: Webhooks, Thought Industries pricing

How does Cotlet connect to Thought Industries?

  1. Sign in to Thought Industries. 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 Thought Industries password, and no enrollment, import, status change or waitlist edit is saved before you approve it.

Connect Thought Industries 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 your academy. Create a Cotlet account, open Thought Industries in its Cloud Browser, sign in on your academy domain with an admin login that can manage learners, then press Enable for agents.
  2. Add the Cotlet address. Paste https://cotlet.dev/mcp/v1 into the MCP server or connector field of your agent.
  3. Approve the connection. Chat apps send you to a Cotlet sign-in page. Code editors, n8n and scripts send an API key made in the Cotlet console.

https://cotlet.dev/mcp/v1 serves every Cotlet app you enable, Thought Industries included. Enable the academy after connecting and refresh the connector, and its tools show up.

Claude:

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

Claude Code:
claude mcp add --transport http cotlet \
  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": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": { "Authorization": "Bearer ${env:COTLET_API_KEY}" }
    }
  }
}

Codex:

# ~/.codex/config.toml
[mcp_servers.cotlet]
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: thought_industries_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: thought_industries_write

How to use the Thought Industries REST API

Create your Cotlet API key

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

Connect Thought Industries in Cotlet and enable it for agents. Account access: Your own Thought Industries admin login on your academy domain (an admin who can manage learners, courses and reports). You sign in yourself in your Cloud Browser.

Make your first Thought Industries API request

REST:

curl https://cotlet.dev/api/v1/thought-industries/learners \
  -H "Authorization: Bearer $COTLET_API_KEY"

Read learners 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": "thought-industries",
  "tool": "list_learners",
  "result": {
    "learners": [
      {
        "learner_id": "3f9a2b18-7c4d-4e2a-9b1f-0c5d6e7f8a90",
        "name": "Priya Nair",
        "email": "priya.nair@example.com",
        "panorama": "Retail"
      },
      {
        "learner_id": "5e1d7c2a-9b8f-4e3d-8c0a-1b2c3d4e5f60",
        "name": "Tom Becker",
        "email": "tom.becker@example.com",
        "panorama": "Retail"
      }
    ],
    "next_cursor": null
  }
}

Reads the Users > Learners list. Returns each learner's learner_id, name, email and Panorama.

Pass learner_id or the email to get_learner, enroll_learner and set_content_status. Use cursor to read the next page.

Reading changes nothing.

cursor: Next page cursor from the previous call.

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

Thought Industries workflows for agents and automations

ToolConnect throughExample workflow
n8nHTTP RequestOne learner's profile with the content on the Access tab and any waitlisted content. Use get_learner in your configured learning report.
MakeHTTP > Make a requestContent from Courses > All Courses with its content_id and type. Use list_courses in your configured learning report.
Python or Node.jsREST APIEnrollments, status changes, certificate grants and revoked access from the Content Actions Log. Use list_content_actions 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 Thought Industries; 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.

Thought Industries API endpoints and MCP tools

Learners and access

Waitlisted Content shows only to admins allowed to provision learner access, so sign in with that role.

  • List learners (list_learners, read): Learners of your academy with email and Panorama; search by name or email.
  • Get learner access (get_learner, read): One learner's profile with the content on the Access tab and any waitlisted content.
  • Enroll learner (enroll_learner, write, asks first): Add a course or other content to an existing learner's Access tab.
  • Import and invite learners (import_learners, write, asks first): Create learners in bulk, give them content and optionally send invites.

Courses and seats

Seat limits and waitlisting belong to a session, so a webinar with three sessions has three maximums.

  • List courses (list_courses, read): Content from Courses > All Courses with its content_id and type.
  • Get course enrollment settings (get_course, read): Enrollment limit and waitlist setting of one course.

Waitlists

Only content with an active waitlist takes a learner. Putting someone back sends them to the end of the list.

  • Add learner to waitlist (add_to_waitlist, write, asks first): Put a learner on the waitlist of content that has one.
  • Remove learner from waitlist (remove_from_waitlist, write, asks first): Take a learner off the waitlist of one piece of content.

Progress and reports

A completion date is accepted only when none is recorded. Auto Assignment rules exist only where the feature is on, up to 50.

  • List content actions (list_content_actions, read): Enrollments, status changes, certificate grants and revoked access from the Content Actions Log.
  • Set content status (set_content_status, write, asks first): Mark a learner as not-started, started, completed or not-completed on content.
  • List Auto Assignment rules (list_auto_assignment_rules, read): Rules that enroll learners automatically, with conditions and unenroll setting.

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

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

  • What we store. Your signed-in academy profile, encrypted with AES-256-GCM, in Finland. Never the password.
  • What your agent gets. 11 Thought Industries tools. No cookie, no login and no TI API key.
  • What the session sees. What your admin role sees in the academy, Panoramas included.
  • What no tool touches. Course authoring and publishing, ecommerce, Panorama and sublicense settings, removing access.
  • If the academy signs you out. We email you a sign-in link. With SSO you sign in through your own provider, never us.
  • How to cut access. Disable for agents, reset the browser or delete the key. The next call fails.

Learner emails and progress pass through the session, so the customer data stays under your contract with Thought Industries and your own privacy terms. The Cotlet site has A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory (live results); there is no SOC 2 report or third-party pentest yet.

Is it against Thought Industries' terms? Account safety

non-exclusive, non-sublicensable, non-transferable, and limited licensed right throughout the applicable subscription period to access and use the Services, for the Customer's internal business purposes

Thought Industries AI Capabilities Terms, section 1 (undated, read 27 Oct 2026)

These are the only customer terms Thought Industries publishes, and they cover its AI add-ons. They say nothing on robots, scripts or agents. The main subscription agreement is signed per order and is not public, so read yours before you connect. An agent that enrolls your own learners for your own academy is internal business use. We found no public case of an academy blocked over automation (checked 27 Oct 2026).

How we keep your academy looking like you:

  • Your own admin login, typed in by you, or your SSO
  • One Cloud Browser with a steady IP and cookies, like the admin's laptop
  • Every enrollment, import, status change and waitlist edit waits for your OK
  • No tool exports the whole learner list in one go
  • If Thought Industries objects, we pause the tools for everyone within 24 h

An import sends an invitation to every new learner, and invitations do not expire. Run a large list in batches and check the first one before the rest.

What happens when Thought Industries changes?

  • 12 h between tests of the learner, course and report reads
  • 24 h between tests of enrollments and imports a learner would see
  • $0 for a call to a Thought Industries tool paused for a fix

Thought Industries rebuilt its developer docs in 2026, ships the Claude plugin in beta (last commit 14 Aug 2026) and has an MCP server announced, while its REST changelog page still says "coming soon". When an admin screen moves, we repair the tool and keep its name. When the official MCP server ships, this page says what it covers. status.cotlet.dev checks the site, console and API every 3 minutes.

Approvals, undo and mistakes

  1. Checks the seat. get_course reads the session's limit; get_learner shows who is waitlisted.
  2. Plans the move. Enroll the next learner, then take them off the waitlist, nobody else.
  3. Waits for your OK. Both writes wait in your Cotlet console, with the learner and the session named.
  4. Reports back. The learner's Access tab after the change, and who is still waiting.
ActionUndo
Enroll a learnerRemove the content on their Access tab; it was already on their dashboard
Import and inviteDisable the user and the invitation stops working; the email has gone out
Set content statusSet the old status back; a recorded completion date stays
Add to a waitlistremove_from_waitlist
Remove from a waitlistadd_to_waitlist, but at the end of the list

All 5 write tools ask first, because a learner sees each of them: a course on the dashboard, an invitation, a status or a place in line. The 6 reads run at once. For a weekly import you trust, you can switch the wait off per tool.

Auto Assignment ignores seat limits and waitlists, and a rule plus a purchase can enroll the same person twice. The agent reads the Access tab first so it never adds a second copy.

MCP call:

{
  "name": "enroll_learner",
  "arguments": {
    "learner": "priya.nair@example.com",
    "content_id": "4b1c2d3e-6a7b-4c8d-9e0f-1a2b3c4d5e6f"
  }
}

REST:

curl -X POST https://cotlet.dev/api/v1/thought-industries/contents/4b1c2d3e-6a7b-4c8d-9e0f-1a2b3c4d5e6f/learner/enroll \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"learner":"priya.nair@example.com"}'

Response:

{
  "learner_id": "3f9a2b18-7c4d-4e2a-9b1f-0c5d6e7f8a90",
  "content_id": "4b1c2d3e-6a7b-4c8d-9e0f-1a2b3c4d5e6f",
  "title": "Safety basics",
  "status": "enrolled"
}

An HR system hook or a nightly job can call the same tools over REST at /api/v1/thought-industries, with one Cotlet key and one price. A call your admin role may not make returns an error and costs nothing. Each tool row above shows its REST path.

How much does the Thought Industries MCP server cost?

About $19 a month for one academy with about 1,500 active learners, 3,320 credits. Works on Starter, which has no API.

JobCallsCredits
Import and enroll the week's new learners3 × 4120
Weekly completions, certificates and lost access6 × 4240
Enroll one learner on request5 × 201,000
Mark training done elsewhere as completed2 × 10200
Move a learner off a waitlist4 × 6240
Audit Auto Assignment rules, monthly2 × 120
Cloud Browser, 30 days1,500
Total3,320
  • Free 7-day trial, no card
  • 10 credits per successful call, MCP or REST
  • 50 credits a day for the Cloud Browser
  • No API add-on or Enterprise plan needed

The month is our example: about 40 new learners a week in 4 imports, 20 enrollments on request, 10 outside completions, 6 waitlist moves and one rule audit. Thought Industries publishes no typical size; its plans cap active learners at 500, 2,000 and 5,000 a year, all priced on request. Dollars at the $29 pack rate.

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

OptionWhat it doesWhere it stops
thoughtindustries/ti-admin-pluginThe official Claude plugin, MIT. 0 stars, last commit 14 Aug 2026.Course drafts only; needs API access and Claude desktop.
nowk/thoughtindustriesA Go client for the API, marked "WIP". 1 star, last push 21 Jul 2018.Unmaintained, no MCP, needs an API key.
PyDataTy/TIexternalCourseActivityA Python script that uploads course completions. 0 stars, last push 12 May 2021.One job, needs an API key.
Zapier or Workato on webhooksSends enrollments and completions to your CRM as they happen.One way only, and webhooks come with the same Enterprise or add-on line as the API.

If your academy is on Enterprise and you have a developer, the REST API and webhooks are the official route. If you want course drafts in Claude, try the plugin. If your agent should enroll, import, work the waitlist and read the Content Actions Log on any plan, Cotlet does that hosted.

Also listed on: Odel, mcpbeat

Who runs Cotlet

Take Group sp. z o.o. runs Cotlet: a software company registered in Poland, EU (VAT PL6342984273), in business since 2019. The founders are Bart Krawczyk (Co-founder, CTO) and Jake Slugocki (Co-founder, SEO, sales and marketing). Questions about the Thought Industries tools go to contact@cotlet.dev.

Thought Industries API and MCP: questions

How do I get access?

Sign up free at https://cotlet.dev, open Thought Industries under Integrations in the console and sign in to your academy in its Cloud Browser. The trial starts when you sign up and needs no card.

How do I connect Thought Industries to ChatGPT or Claude?

Sign up at cotlet.dev, log in to Thought Industries 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 Thought Industries account through Cotlet, in their phone apps too.

What can ChatGPT do in Thought Industries?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Thought Industries: enroll new hires in onboarding courses; weekly course completion report; enroll a learner in a course. You ask in plain words, and anything that reaches other people waits for your OK first.

Do I need API access on my Thought Industries instance?

No. Cotlet works in your own admin session in the Cloud Browser and creates no API key. The official REST API, the Zapier app and the Claude plugin all need a key from Settings > Security, and the plugin docs list an instance with API access enabled as a prerequisite. What your agent can do still follows your admin role (Thought Industries developer docs, checked 23 Oct 2026).

How does this differ from the Thought Industries Claude plugin?

The plugin runs in the Claude desktop app on the REST API and is in beta. It browses the catalog and writes course content as drafts, and publishing stays manual. Cotlet covers learners: access, enrollments, imports, waitlists and the Content Actions Log, and it works from Claude Code, n8n or a script (Thought Industries developer docs, checked 23 Oct 2026).

What can it not do yet?

The tools read learners, courses, the Content Actions Log and Auto Assignment rules, and write enrollments, imports, content status and waitlists. They do not author or publish courses, remove a learner's access, change Auto Assignment rules, touch ecommerce, or edit Panorama and sublicense settings. Learning paths, subscriptions and Panorama access can only be set for new learners in an import, which is how Thought Industries bulk import works (Thought Industries Help, checked 23 Oct 2026).

Does Thought Industries have webhooks?

Yes. Admins add them under Users > Manager Notifications, with SFTP and email as other channels, and they sit on the same plan line as the API: included on Enterprise, an add-on on Professional. Cotlet does not send webhooks; run your agent on a schedule and read the Content Actions Log.

Does it work with SSO?

Yes. You sign in through your own identity provider in the Cloud Browser, the way you do on your laptop. Cotlet never sees the SSO password.

Is the MCP server different from the REST API?

Only in how you call it. Both have the same 11 tools, inputs and answers, with one Cotlet key and one price. Agents use MCP; HR hooks and scripts use REST.

Is Cotlet affiliated with Thought Industries?

No. Cotlet is independent and not affiliated with Thought Industries, Inc.

Can I use the Thought Industries 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.