Skip to content

Connectors · Work & projects

TalentLMS MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to TalentLMS and the rest of your systems. It gives your agent 62 TalentLMS actions (32 reads, 21 writes and 9 that wait for a confirmation) and holds the TalentLMS credential itself, so the agent never does. It paces TalentLMS's limits and records every call.

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp
the first call
do {  action: "talentlms.users.list",  intent: "check which TalentLMS account is connected"}# List users · read · 1 upstream call
  • 62actionsin one signed file
  • 32readlook, never change
  • 21writecreate and update
  • 9wait for a yesdestructive, confirmed first

Set up

Connect TalentLMS in three steps.

  1. 01

    Add actionlake to Claude.

    Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.

    https://connect.actionlake.com/mcp
  2. 02

    Connect TalentLMS.

    Username and secret. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.

    • api_keyTalentLMS API key: as the super-administrator, Account & Settings > Basic settings > enable API and copy the key
    • hostWhere your TalentLMS lives: your host
    account { op: "connections.requirements", service: "talentlms" }
    # free: exactly what to paste, and what is found for you
  3. 03

    Make the first call. Check before a write.

    Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

    do    { action: "talentlms.users.list" }# list users · read · 1 upstream callcheck { action: "talentlms.users.signup", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

TalentLMS at a glance

Sign-in
Username and secret. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide
api_key
Setup fields
host
Limits we pace to
200 calls per 5 seconds and 2,000 an hour, per connection
API covered
TalentLMS REST API v1, at your TalentLMS instance's API base URL, which you enter when connecting
Built from
TalentLMS's documentation, read 22 October 2026talentlms.comdocs.talentlms.com
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
32 of 32 reads, for up to an hour; a write clears what it affects
Shared entities
3, so ask can line TalentLMS up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in TalentLMS.

62 actions in 8 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 32readlook, never change
  • 21writecreate and update
  • 9destructivewait for a confirmation
  1. Users

    17

    7 read · 9 write · 1 destructive

    List users · Sign up (create) a user · Get a user · Update a user

  2. Courses

    14

    5 read · 5 write · 4 destructive

    Create a course · Enroll a user in a course · Find courses by a custom field value · Log a user in straight into a course

  3. Branches

    8

    2 read · 4 write · 2 destructive

    List branches · Add a course to a branch · Add a user to a branch · Create a branch

  4. Groups

    7

    2 read · 3 write · 2 destructive

    List groups · Create a group · Get a group · Delete a group

  5. Timeline

    6

    6 read · 0 write · 0 destructive

    List the latest timeline events of one type · List the latest timeline events of one type for a branch · List the latest timeline events of one type for a course · List the latest timeline events of one type for a group

  6. Units

    5

    5 read · 0 write · 0 destructive

    List the sessions of an instructor-led training unit · List every user's score and status in a unit · Get a user's answers in a survey · Get a user's answers in a test

  7. Categories

    3

    3 read · 0 write · 0 destructive

    List course categories · Get a course category · Get a category's subcategories and courses

  8. Site

    2

    2 read · 0 write · 0 destructive

    Get the portal's details and totals · Get the current API rate-limit status

Top actions

The TalentLMS API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 9 of TalentLMS's 9 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
talentlms.users.listList usersList users.readidentity.user.list474 connectors
talentlms.groups.listList groupsList groups.readidentity.group.list262 connectors
talentlms.users.signupSign up (create) a userSign up (create) a user.writeidentity.user.create262 connectors
talentlms.groups.createCreate a groupCreate a group.writeidentity.group.create205 connectors
talentlms.users.deleteDelete a userDelete a user.destructiveidentity.user.delete253 connectors
talentlms.branches.listList branchesList branches.readthis connector
talentlms.users.loginLog a user in and get a single-use login URLLog a user in and get a single-use login URL.writethis connector
talentlms.courses.gotoLog a user in straight into a courseLog a user in straight into a course.writethis connector
talentlms.users.logoutLog a user outLog a user out.writethis connector
talentlms.branches.createCreate a branchCreate a branch.writethis connector
talentlms.groups.add_userAdd a user to a groupAdd a user to a group.writethis connector
talentlms.groups.add_courseAdd a course to a groupAdd a course to a group.writethis connector

Try it

Prompts to paste into Claude.

Each one names the TalentLMS actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    Who has access in TalentLMS? List every user and their role.

    callstalentlms.users.list

  2. Writewrite

    Sign up (create) a user in TalentLMS. Show me exactly what you will send before you save it.

    callstalentlms.users.signup

Governance for TalentLMS

Destructive actions wait for a yes.

9 TalentLMS actions are destructive. These are all of them:

  • Delete a usertalentlms.users.delete
  • Delete a grouptalentlms.groups.delete
  • Delete a coursetalentlms.courses.delete
  • Delete a branchtalentlms.branches.delete
  • Remove a user from a grouptalentlms.groups.remove_user
  • Remove a user from a branchtalentlms.branches.remove_user
  • Remove a user from a coursetalentlms.courses.unenroll_user
  • Reset a user's progress in a coursetalentlms.courses.reset_user_progress
  • Reset a user's progress in a course and remove their certificationtalentlms.courses.reset_user_progress_and_certification

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

dotalentlms.users.deleteconfirm_policy: human

Delete a user?

intent: the user asked me to delete a user

run suspended · waiting for a named person · key talentlms-agent cannot confirm itself
In the console, or from an emailed signed link.
a key for this connector
account {  op: "keys.create", name: "talentlms-agent",  allowed_actions: ["talentlms.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "talentlms.users.delete", approver: "[email protected]" },    { match: "talentlms.groups.delete", approver: "[email protected]" },    { match: "talentlms.courses.delete", approver: "[email protected]" }  ]}
Illustrative. Scoped to TalentLMS only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What TalentLMS costs on actionlake.

Every TalentLMS action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call TalentLMS refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

  • 1upstream call per actionall 62 TalentLMS actions
  • 62actions pageeach page of a long list is one call
  • 32reads can be cacheda cache hit costs nothing
  • 100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every TalentLMS action.

62 actions by area: the id your agent calls, what it does, and its effect.

Users17
  • talentlms.users.deleteDelete a userdestructive
  • talentlms.users.forgot_passwordEmail a user password-reset instructionswrite
  • talentlms.users.forgot_password_with_urlsEmail a user password-reset instructions, with a custom portal URL and redirectwrite
  • talentlms.users.forgot_usernameEmail a user their usernamewrite
  • talentlms.users.forgot_username_with_domain_urlEmail a user their username, showing a custom portal URLwrite
  • talentlms.users.getGet a userread
  • talentlms.users.get_by_custom_fieldFind users by a custom field valueread
  • talentlms.users.get_by_emailGet a user by email addressread
  • talentlms.users.get_by_usernameGet a user by usernameread
  • talentlms.users.is_onlineCheck whether a user is onlineread
  • talentlms.users.listList usersread
  • talentlms.users.list_custom_fieldsList custom user registration fieldsread
  • talentlms.users.loginLog a user in and get a single-use login URLwrite
  • talentlms.users.logoutLog a user outwrite
  • talentlms.users.set_statusActivate or deactivate a userwrite
  • talentlms.users.signupSign up (create) a userwrite
  • talentlms.users.updateUpdate a userwrite
Courses14
  • talentlms.courses.createCreate a coursewrite
  • talentlms.courses.deleteDelete a coursedestructive
  • talentlms.courses.enroll_userEnroll a user in a coursewrite
  • talentlms.courses.getGet a courseread
  • talentlms.courses.get_by_custom_fieldFind courses by a custom field valueread
  • talentlms.courses.get_user_statusGet a user's status and unit progress in a courseread
  • talentlms.courses.gotoLog a user in straight into a coursewrite
  • talentlms.courses.goto_hiding_header_itemsLog a user in straight into a course, hiding header itemswrite
  • talentlms.courses.goto_with_redirectsLog a user in straight into a course, with logout and completion redirectswrite
  • talentlms.courses.listList coursesread
  • talentlms.courses.list_custom_fieldsList custom course fieldsread
  • talentlms.courses.reset_user_progressReset a user's progress in a coursedestructive
  • talentlms.courses.reset_user_progress_and_certificationReset a user's progress in a course and remove their certificationdestructive
  • talentlms.courses.unenroll_userRemove a user from a coursedestructive
Branches8
  • talentlms.branches.add_courseAdd a course to a branchwrite
  • talentlms.branches.add_userAdd a user to a branchwrite
  • talentlms.branches.createCreate a branchwrite
  • talentlms.branches.deleteDelete a branchdestructive
  • talentlms.branches.getGet a branchread
  • talentlms.branches.listList branchesread
  • talentlms.branches.remove_userRemove a user from a branchdestructive
  • talentlms.branches.set_statusActivate or deactivate a branchwrite
Groups7
  • talentlms.groups.add_courseAdd a course to a groupwrite
  • talentlms.groups.add_userAdd a user to a groupwrite
  • talentlms.groups.createCreate a groupwrite
  • talentlms.groups.deleteDelete a groupdestructive
  • talentlms.groups.getGet a groupread
  • talentlms.groups.listList groupsread
  • talentlms.groups.remove_userRemove a user from a groupdestructive
Timeline6
  • talentlms.timeline.listList the latest timeline events of one typeread
  • talentlms.timeline.list_for_branchList the latest timeline events of one type for a branchread
  • talentlms.timeline.list_for_courseList the latest timeline events of one type for a courseread
  • talentlms.timeline.list_for_groupList the latest timeline events of one type for a groupread
  • talentlms.timeline.list_for_unitList the latest timeline events of one type for a unitread
  • talentlms.timeline.list_for_userList the latest timeline events of one type for a userread
Units5
  • talentlms.units.get_survey_answersGet a user's answers in a surveyread
  • talentlms.units.get_test_answersGet a user's answers in a testread
  • talentlms.units.get_user_progressGet one user's score and status in a unitread
  • talentlms.units.list_ilt_sessionsList the sessions of an instructor-led training unitread
  • talentlms.units.list_users_progressList every user's score and status in a unitread
Categories3
  • talentlms.categories.getGet a course categoryread
  • talentlms.categories.get_leafs_and_coursesGet a category's subcategories and coursesread
  • talentlms.categories.listList course categoriesread
Site2
  • talentlms.site.get_infoGet the portal's details and totalsread
  • talentlms.site.get_rate_limitGet the current API rate-limit statusread

Questions

The TalentLMS MCP server, answered.

Is there a TalentLMS MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 62 TalentLMS actions across users, courses, branches and groups, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by TalentLMS.

What do I need to connect TalentLMS?

TalentLMS API key: as the super-administrator, Account & Settings > Basic settings > enable API and copy the key. Plus your host. The free call account { op: "connections.requirements", service: "talentlms" } lists exactly what to paste.

Can an AI agent delete or change things in TalentLMS?

Only if its key allows it, and only with an explicit confirmation. 9 TalentLMS actions are destructive, including delete a user, delete a group and delete a course. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my TalentLMS API limit?

actionlake paces every call to the limits in the TalentLMS service file: 200 calls per 5 seconds and 2,000 an hour per connection. Repeated reads are answered from cache (32 TalentLMS actions can be), which never reaches TalentLMS.

What does a TalentLMS action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (62 TalentLMS actions page). Cache hits, searches, dry runs and calls TalentLMS refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which TalentLMS API does it cover?

The TalentLMS REST API v1 at your TalentLMS instance's API base URL, which you enter when connecting. It is built from TalentLMS's documentation as read on 22 October 2026. 62 actions in 8 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my TalentLMS data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to an hour, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your TalentLMS credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

Give your agent TalentLMS today.

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.