Skip to content

Connectors · Work & projects

Culture Amp MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Culture Amp and the rest of your systems. It gives your agent 9 Culture Amp actions (9 reads and 0 writes) and holds the Culture Amp credential itself, so the agent never does. It paces Culture Amp'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: "culture_amp.employees.list",  intent: "check which Culture Amp account is connected"}# List employees · read · 1 upstream call
  • 9actionsin one signed file
  • 9readlook, never change
  • 0writecreate and update
  • 0wait for a yesdestructive, confirmed first

Set up

Connect Culture Amp 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 Culture Amp.

    OAuth 2.0, client credentials. Paste the app's client id and secret; actionlake fetches and renews the token, and nobody has to sign in. actionlake stores what you paste write-only, sealed under your tenant's key.

    • client_idClient ID of a Culture Amp API credential (Settings > Account > API, administrators only)
    • client_secretClient secret of that Culture Amp API credential
    • entity_idYour Culture Amp entity id
    • permissionsYour Culture Amp permissions
    account { op: "connections.requirements", service: "culture_amp" }
    # 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: "culture_amp.employees.list" }# list employees · read · 1 upstream call

Culture Amp at a glance

Sign-in
OAuth 2.0, client credentials. Paste the app's client id and secret; actionlake fetches and renews the token, and nobody has to sign in.
You provide
client_idclient_secret
Setup fields
entity_idpermissions
Limits we pace to
10 calls a second, per connection
API covered
Culture Amp Public API v1 (OpenAPI 3.0.1, spec version 0.0.1)api.cultureamp.com/v1
Built from
Culture Amp's documentation, read 23 October 2026api.cultureamp.comdocs.api.cultureamp.com
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
9 of 9 reads, for up to 5 minutes; a write clears what it affects
Shared entities
1, so ask can line Culture Amp up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Culture Amp.

9 actions in 6 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 9readlook, never change
  • 0writecreate and update
  • 0destructivewait for a confirmation
  1. Employees

    2

    2 read · 0 write · 0 destructive

    List employees · Get employee

  2. Manager reviews

    2

    2 read · 0 write · 0 destructive

    List manager reviews · Get manager review

  3. Performance cycles

    2

    2 read · 0 write · 0 destructive

    List performance cycles · Get performance cycle

  4. Employee demographics

    1

    1 read · 0 write · 0 destructive

    List demographics by employee

  5. Employee manager reviews

    1

    1 read · 0 write · 0 destructive

    List manager reviews by employee

  6. Performance cycle manager reviews

    1

    1 read · 0 write · 0 destructive

    List manager reviews by performance cycle

Top actions

The Culture Amp API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems.

ActionWhat it doesEffectSame name in
culture_amp.employees.listList employeesReturns all employees in the account.readthis connector
culture_amp.manager_reviews.listList manager reviewsReturns all manager reviews in the account.readthis connector
culture_amp.performance_cycles.listList performance cyclesReturns all performance cycles in the account.readthis connector
culture_amp.employee_demographics.listList demographics by employeeReturns the demographic assignments for a given employee.readthis connector
culture_amp.employee_manager_reviews.listList manager reviews by employeeReturns manager reviews for a given employee.readthis connector
culture_amp.performance_cycle_manager_reviews.listList manager reviews by performance cycleReturns manager reviews for a given performance cycle.readthis connector
culture_amp.employees.getGet employeeReturns the details of an employee corresponding to the provided Culture Amp employee identifier.readthis connector
culture_amp.manager_reviews.getGet manager reviewReturns the details of a manager review corresponding to the provided id.readthis connector
culture_amp.performance_cycles.getGet performance cycleReturns the details of a performance cycle by its id.readthis connector

Try it

Prompts to paste into Claude.

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

  1. Readread

    List everyone in Culture Amp with their department and start date.

    callsculture_amp.employees.list

Governance for Culture Amp

Every write can wait for a yes.

None of Culture Amp's actions is destructive. A key can still be held to reads, capped, and set so a person confirms every write.

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.

a key for this connector
account {  op: "keys.create", name: "culture-amp-agent",  allowed_actions: ["culture_amp.*"], cap_calls: 2000,  confirm_policy: "human_for_writes"}
Illustrative. Scoped to Culture Amp only, capped at 2,000 upstream calls, every write confirmed.

Cost

What Culture Amp costs on actionlake.

Every Culture Amp action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Culture Amp 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 9 Culture Amp actions
  • 9actions pageeach page of a long list is one call
  • 9reads 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 Culture Amp action.

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

Employees2
  • culture_amp.employees.getGet employeeread
  • culture_amp.employees.listList employeesread
Manager reviews2
  • culture_amp.manager_reviews.getGet manager reviewread
  • culture_amp.manager_reviews.listList manager reviewsread
Performance cycles2
  • culture_amp.performance_cycles.getGet performance cycleread
  • culture_amp.performance_cycles.listList performance cyclesread
Employee demographics1
  • culture_amp.employee_demographics.listList demographics by employeeread
Employee manager reviews1
  • culture_amp.employee_manager_reviews.listList manager reviews by employeeread
Performance cycle manager reviews1
  • culture_amp.performance_cycle_manager_reviews.listList manager reviews by performance cycleread

Questions

The Culture Amp MCP server, answered.

Is there a Culture Amp MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 9 Culture Amp actions across employees, manager reviews, performance cycles and employee demographics, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Culture Amp.

What do I need to connect Culture Amp?

Client ID of a Culture Amp API credential (Settings > Account > API, administrators only) and Client secret of that Culture Amp API credential. Plus your entity id and your permissions. The free call account { op: "connections.requirements", service: "culture_amp" } lists exactly what to paste.

Will an AI agent use up my Culture Amp API limit?

actionlake paces every call to the limits in the Culture Amp service file: 10 calls a second per connection. Repeated reads are answered from cache (9 Culture Amp actions can be), which never reaches Culture Amp.

What does a Culture Amp action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (9 Culture Amp actions page). Cache hits, searches, dry runs and calls Culture Amp 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 Culture Amp API does it cover?

The Culture Amp Public API v1 (OpenAPI 3.0.1, spec version 0.0.1) at api.cultureamp.com/v1. It is built from Culture Amp's documentation as read on 23 October 2026. 9 actions in 6 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Culture Amp data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, 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 Culture Amp 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 Culture Amp today.

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