Skip to content
actionlake
Start free

Connectors · AI

OpenAI Platform MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to OpenAI Platform and the rest of your systems. It gives your agent 186 OpenAI Platform actions (85 reads, 61 writes and 40 that wait for a confirmation) and holds the OpenAI Platform credential itself, so the agent never does. It paces OpenAI Platform's limits and records every call.

Connect OpenAI Platform freeSee pricing

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: "openai.files.list",  intent: "check which OpenAI Platform account is connected"}# List files · read · 1 upstream call
  • 186actionsin one signed file
  • 85readlook, never change
  • 61writecreate and update
  • 40wait for a yesdestructive, confirmed first

Set up

Connect OpenAI Platform 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 OpenAI Platform.

    API key. 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_keyOpenAI API key (sk-proj-… project key or sk-svcacct-… service account key)
    account { op: "connections.requirements", service: "openai" }
# 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: "openai.files.list" }# list files · read · 1 upstream callcheck { action: "openai.live_sessions.fork", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

OpenAI Platform at a glance

Sign-in
API key. 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
Limits we pace to
3,000 calls a minute, per connection
API covered
OpenAI Platform API OpenAPI 2.3.0 (openai/openai-openapi main @ 40496db (2026-10-01T05:02:17Z))api.openai.com/v1
Built from
OpenAI Platform's documentation, read 1 October 2026OpenAPI spec (GitHub)
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
8 of 85 reads, for up to an hour; a write clears what it affects
Shared entities
1, so ask can line OpenAI Platform up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in OpenAI Platform.

186 actions in 64 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 85readlook, never change
  • 61writecreate and update
  • 40destructivewait for a confirmation

  1. Videos

    7

    2 read · 4 write · 1 destructive

    Create a video · Create a video edit · Create a video extension · Create a video remix

  2. Webhook endpoints

    7

    2 read · 3 write · 2 destructive

    Create Webhook Endpoint · List Webhook Endpoints · Update Webhook Endpoint · Retrieve Webhook Endpoint

  3. Beta responses

    6

    2 read · 2 write · 2 destructive

    Beta: compact a conversation into a shorter context · Beta: create a model response · Beta: count a model response's input tokens · Beta: get a model response

  4. Fine tuning jobs

    6

    2 read · 3 write · 1 destructive

    List fine-tuning jobs · Create fine-tuning job · Retrieve fine-tuning job · Cancel a fine-tuning job

  5. Live sessions

    6

    0 read · 4 write · 2 destructive

    Create a Live session or place an outbound SIP call · Fork a stored Live session onto a new connection · Transfer a Live SIP call · Accept an incoming Live SIP call

  6. Responses

    6

    2 read · 2 write · 2 destructive

    Compact a conversation into a shorter context · Create a model response · Count a model response's input tokens · Get a model response

  7. Vector store files

    6

    3 read · 2 write · 1 destructive

    List vector store files · Create vector store file · Retrieve vector store file · Retrieve vector store file content

  8. Vector stores

    6

    3 read · 2 write · 1 destructive

    List vector stores · Create vector store · Retrieve vector store · Modify vector store

56 more areas · 136 actions
  • Agent environment templates 5
  • Agent sessions 5
  • Agents 5
  • Chat completions 5
  • Eval runs 5
  • Evals 5
  • Vault credentials 5
  • Batches 4
  • Container files 4
  • Containers 4
  • Conversation items 4
  • Conversations 4
  • Realtime calls 4
  • Skills 4
  • Vaults 4
  • Vector store file batches 4
  • Voice consents 4
  • Agent session artifacts 3
  • Chatkit threads 3
  • Files 3
  • Fine tuning checkpoint permissions 3
  • Models 3
  • Skill versions 3
  • Uploads 3
  • Agent environment files 2
  • Agent session subagent turns 2
  • Agent session subagents 2
  • Agent session turns 2
  • Chatkit sessions 2
  • Eval run output items 2
  • Graders 2
  • Images 2
  • Agent environments 1
  • Agent session events 1
  • Agent session items 1
  • Agent session subagent items 1
  • Agent session subagent turn items 1
  • Agent session traces 1
  • Beta response input items 1
  • Chat completion messages 1
  • Chatkit thread items 1
  • Completions 1
  • Embeddings 1
  • Fine tuning job checkpoints 1
  • Fine tuning job events 1
  • Moderations 1
  • Realtime client secrets 1
  • Realtime sessions 1
  • Realtime transcription sessions 1
  • Realtime translation client secrets 1
  • Response input items 1
  • Safety alerts 1
  • Safety cases 1
  • Video characters 1
  • Voices 1
  • Webhook event types 1

Top actions

The OpenAI Platform API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 65 of OpenAI Platform's 65 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
openai.files.listList filesReturns a list of files.readcontent.file.list77 connectors
openai.container_files.listList container filesList Container filesreadcontent.file.list77 connectors
openai.conversation_items.listList conversation itemsList all items for a conversation with the given ID.readcomm.message.list42 connectors
openai.chatkit_thread_items.listList ChatKit thread itemsList items that belong to a ChatKit thread.readcomm.message.list42 connectors
openai.live_sessions.forkFork a stored Live session onto a new connectionFork a stored Live session onto a new WebRTC connection.writecomm.call.create38 connectors
openai.live_sessions.createCreate a Live session or place an outbound SIP callCreate a Live WebRTC session or place an outbound SIP call.writecomm.call.create38 connectors
openai.conversations.createCreate a conversationCreate a conversation.writecomm.chat.create15 connectors
openai.files.deleteDelete fileDelete a file and remove it from all vector stores.destructivecontent.file.delete68 connectors
openai.realtime_sessions.createCreate a Realtime session and its client secretCreate an ephemeral API token for use in client-side applications with the Realtime API.writeidentity.api_key.create100 connectors
openai.realtime_client_secrets.createCreate a Realtime client secretCreate a Realtime client secret with an associated session configuration.writeidentity.api_key.create100 connectors
openai.graders.runRun graderRun a grader.writeanalytics.inference.create17 connectors
openai.images.editEdit or extend images from a promptCreates edited or extended images from source images (by URL or file id) and a prompt.writeanalytics.inference.create17 connectors

Try it

Prompts to paste into Claude.

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

  1. Readread

    Which OpenAI Platform files changed this week, and who changed them?

    callsopenai.files.list

  2. Writewrite

    Fork a stored Live session onto a new connection in OpenAI Platform. Show me exactly what you will send before you save it.

    callsopenai.live_sessions.fork

Governance for OpenAI Platform

Destructive actions wait for a yes.

40 OpenAI Platform actions are destructive. The first 10:

  • Delete fileopenai.files.delete
  • Delete a container fileopenai.container_files.delete
  • Delete an agent session artifactopenai.agent_session_artifacts.delete
  • Delete a conversation itemopenai.conversation_items.delete
  • Delete a conversationopenai.conversations.delete
  • Delete a ChatKit threadopenai.chatkit_threads.delete
  • Delete Webhook Endpointopenai.webhook_endpoints.delete
  • Delete a vault credentialopenai.vault_credentials.delete
  • Hang up a Live sessionopenai.live_sessions.hangup
  • Reject an incoming Live SIP callopenai.live_sessions.reject

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.

doopenai.files.deleteconfirm_policy: human

Delete file?

intent: the user asked me to delete file

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

Cost

What OpenAI Platform costs on actionlake.

Every OpenAI Platform action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call OpenAI Platform 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 186 OpenAI Platform actions
  • 186actions pageeach page of a long list is one call
  • 8reads 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 OpenAI Platform action.

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

Videos7
  • openai.videos.createCreate a videowrite
  • openai.videos.deleteDelete a videodestructive
  • openai.videos.editCreate a video editwrite
  • openai.videos.extendCreate a video extensionwrite
  • openai.videos.getRetrieve a videoread
  • openai.videos.listList videosread
  • openai.videos.remixCreate a video remixwrite
Webhook endpoints7
  • openai.webhook_endpoints.createCreate Webhook Endpointwrite
  • openai.webhook_endpoints.deleteDelete Webhook Endpointdestructive
  • openai.webhook_endpoints.getRetrieve Webhook Endpointread
  • openai.webhook_endpoints.listList Webhook Endpointsread
  • openai.webhook_endpoints.rotate_secretRotate Webhook Endpoint Signing Secretdestructive
  • openai.webhook_endpoints.testTest Webhook Endpointwrite
  • openai.webhook_endpoints.updateUpdate Webhook Endpointwrite
Beta responses6
  • openai.beta_responses.cancelBeta: cancel a responsedestructive
  • openai.beta_responses.compactBeta: compact a conversation into a shorter contextwrite
  • openai.beta_responses.count_input_tokensBeta: count a model response's input tokensread
  • openai.beta_responses.createBeta: create a model responsewrite
  • openai.beta_responses.deleteBeta: delete a model responsedestructive
  • openai.beta_responses.getBeta: get a model responseread
Fine tuning jobs6
  • openai.fine_tuning_jobs.cancelCancel a fine-tuning jobdestructive
  • openai.fine_tuning_jobs.createCreate fine-tuning jobwrite
  • openai.fine_tuning_jobs.getRetrieve fine-tuning jobread
  • openai.fine_tuning_jobs.listList fine-tuning jobsread
  • openai.fine_tuning_jobs.pausePause a fine-tuning jobwrite
  • openai.fine_tuning_jobs.resumeResume a paused fine-tuning jobwrite
Live sessions6
  • openai.live_sessions.acceptAccept an incoming Live SIP callwrite
  • openai.live_sessions.createCreate a Live session or place an outbound SIP callwrite
  • openai.live_sessions.forkFork a stored Live session onto a new connectionwrite
  • openai.live_sessions.hangupHang up a Live sessiondestructive
  • openai.live_sessions.referTransfer a Live SIP callwrite
  • openai.live_sessions.rejectReject an incoming Live SIP calldestructive
Responses6
  • openai.responses.cancelCancel a responsedestructive
  • openai.responses.compactCompact a conversation into a shorter contextwrite
  • openai.responses.count_input_tokensCount a model response's input tokensread
  • openai.responses.createCreate a model responsewrite
  • openai.responses.deleteDelete a model responsedestructive
  • openai.responses.getGet a model responseread
Vector store files6
  • openai.vector_store_files.createCreate vector store filewrite
  • openai.vector_store_files.deleteDelete vector store filedestructive
  • openai.vector_store_files.getRetrieve vector store fileread
  • openai.vector_store_files.get_contentRetrieve vector store file contentread
  • openai.vector_store_files.listList vector store filesread
  • openai.vector_store_files.updateUpdate vector store file attributeswrite
Vector stores6
  • openai.vector_stores.createCreate vector storewrite
  • openai.vector_stores.deleteDelete vector storedestructive
  • openai.vector_stores.getRetrieve vector storeread
  • openai.vector_stores.listList vector storesread
  • openai.vector_stores.searchSearch vector storeread
  • openai.vector_stores.updateModify vector storewrite
Agent environment templates5
  • openai.agent_environment_templates.createCreate an agent environment templatewrite
  • openai.agent_environment_templates.deleteDelete an agent environment templatedestructive
  • openai.agent_environment_templates.getRetrieve an agent environment templateread
  • openai.agent_environment_templates.listList agent environment templatesread
  • openai.agent_environment_templates.updateUpdate an agent environment templatewrite
Agent sessions5
  • openai.agent_sessions.createCreate an agent sessionwrite
  • openai.agent_sessions.deleteDelete an agent sessiondestructive
  • openai.agent_sessions.getRetrieve an agent sessionread
  • openai.agent_sessions.listList agent sessionsread
  • openai.agent_sessions.updateUpdate an agent sessionwrite
Agents5
  • openai.agents.createCreate an agentwrite
  • openai.agents.deleteDelete an agentdestructive
  • openai.agents.getRetrieve an agentread
  • openai.agents.listList agentsread
  • openai.agents.updateUpdate an agentwrite
Chat completions5
  • openai.chat_completions.createCreate chat completionwrite
  • openai.chat_completions.deleteDelete chat completiondestructive
  • openai.chat_completions.getGet chat completionread
  • openai.chat_completions.listList Chat Completionsread
  • openai.chat_completions.updateUpdate chat completionwrite
Eval runs5
  • openai.eval_runs.cancelCancel eval rundestructive
  • openai.eval_runs.createCreate eval runwrite
  • openai.eval_runs.deleteDelete eval rundestructive
  • openai.eval_runs.getGet an eval runread
  • openai.eval_runs.listGet eval runsread
Evals5
  • openai.evals.createCreate evalwrite
  • openai.evals.deleteDelete an evaldestructive
  • openai.evals.getGet an evalread
  • openai.evals.listList evalsread
  • openai.evals.updateUpdate an evalwrite
Vault credentials5
  • openai.vault_credentials.createCreate a vault credentialwrite
  • openai.vault_credentials.deleteDelete a vault credentialdestructive
  • openai.vault_credentials.getRetrieve a vault credentialread
  • openai.vault_credentials.listList vault credentialsread
  • openai.vault_credentials.rotateRotate a vault credential's secretdestructive
Batches4
  • openai.batches.cancelCancel batchdestructive
  • openai.batches.createCreate batchwrite
  • openai.batches.getRetrieve batchread
  • openai.batches.listList batchesread
Container files4
  • openai.container_files.createCreate container filewrite
  • openai.container_files.deleteDelete a container filedestructive
  • openai.container_files.getRetrieve container fileread
  • openai.container_files.listList container filesread
Containers4
  • openai.containers.createCreate containerwrite
  • openai.containers.deleteDelete a containerdestructive
  • openai.containers.getRetrieve containerread
  • openai.containers.listList containersread
Conversation items4
  • openai.conversation_items.createCreate conversation itemswrite
  • openai.conversation_items.deleteDelete a conversation itemdestructive
  • openai.conversation_items.getRetrieve a conversation itemread
  • openai.conversation_items.listList conversation itemsread
Conversations4
  • openai.conversations.createCreate a conversationwrite
  • openai.conversations.deleteDelete a conversationdestructive
  • openai.conversations.getRetrieve a conversationread
  • openai.conversations.updateUpdate a conversationwrite
Realtime calls4
  • openai.realtime_calls.acceptAccept an incoming Realtime SIP callwrite
  • openai.realtime_calls.hangupHang up a Realtime calldestructive
  • openai.realtime_calls.referTransfer a Realtime SIP callwrite
  • openai.realtime_calls.rejectReject an incoming Realtime SIP calldestructive
Skills4
  • openai.skills.deleteDelete Skilldestructive
  • openai.skills.getGet Skillread
  • openai.skills.listList Skillsread
  • openai.skills.set_default_versionUpdate Skill Default Versionwrite
Vaults4
  • openai.vaults.createCreate a vaultwrite
  • openai.vaults.deleteDelete a vaultdestructive
  • openai.vaults.getRetrieve a vaultread
  • openai.vaults.listList vaultsread
Vector store file batches4
  • openai.vector_store_file_batches.cancelCancel vector store file batchdestructive
  • openai.vector_store_file_batches.createCreate vector store file batchwrite
  • openai.vector_store_file_batches.getRetrieve vector store file batchread
  • openai.vector_store_file_batches.list_filesList vector store files in a batchread
Voice consents4
  • openai.voice_consents.deleteDelete voice consentdestructive
  • openai.voice_consents.getRetrieve voice consentread
  • openai.voice_consents.listList voice consentsread
  • openai.voice_consents.updateUpdate voice consentwrite
Agent session artifacts3
  • openai.agent_session_artifacts.deleteDelete an agent session artifactdestructive
  • openai.agent_session_artifacts.getRetrieve an agent session artifactread
  • openai.agent_session_artifacts.listList agent session artifactsread
Chatkit threads3
  • openai.chatkit_threads.deleteDelete a ChatKit threaddestructive
  • openai.chatkit_threads.getRetrieve a ChatKit threadread
  • openai.chatkit_threads.listList ChatKit threadsread
Files3
  • openai.files.deleteDelete filedestructive
  • openai.files.getRetrieve fileread
  • openai.files.listList filesread
Fine tuning checkpoint permissions3
  • openai.fine_tuning_checkpoint_permissions.createCreate checkpoint permissionswrite
  • openai.fine_tuning_checkpoint_permissions.deleteDelete checkpoint permissiondestructive
  • openai.fine_tuning_checkpoint_permissions.listList checkpoint permissionsread
Models3
  • openai.models.deleteDelete a fine-tuned modeldestructive
  • openai.models.getRetrieve modelread
  • openai.models.listList modelsread
Skill versions3
  • openai.skill_versions.deleteDelete Skill Versiondestructive
  • openai.skill_versions.getGet Skill Versionread
  • openai.skill_versions.listList Skill Versionsread
Uploads3
  • openai.uploads.cancelCancel uploaddestructive
  • openai.uploads.completeComplete uploadwrite
  • openai.uploads.createCreate uploadwrite
Agent environment files2
  • openai.agent_environment_files.createCreate an agent environment filewrite
  • openai.agent_environment_files.listList agent environment filesread
Agent session subagent turns2
  • openai.agent_session_subagent_turns.getRetrieve a subagent turnread
  • openai.agent_session_subagent_turns.listList subagent turnsread
Agent session subagents2
  • openai.agent_session_subagents.getRetrieve a session subagentread
  • openai.agent_session_subagents.listList session subagentsread
Agent session turns2
  • openai.agent_session_turns.getRetrieve an agent session turnread
  • openai.agent_session_turns.listList agent session turnsread
Chatkit sessions2
  • openai.chatkit_sessions.cancelCancel a ChatKit sessiondestructive
  • openai.chatkit_sessions.createCreate a ChatKit sessionwrite
Eval run output items2
  • openai.eval_run_output_items.getGet an output item of an eval runread
  • openai.eval_run_output_items.listGet eval run output itemsread
Graders2
  • openai.graders.runRun graderwrite
  • openai.graders.validateValidate graderread
Images2
  • openai.images.editEdit or extend images from a promptwrite
  • openai.images.generateGenerate an image from a promptwrite
Agent environments1
  • openai.agent_environments.getRetrieve an agent environmentread
Agent session events1
  • openai.agent_session_events.sendSend input events to an agent sessionwrite
Agent session items1
  • openai.agent_session_items.listList agent session itemsread
Agent session subagent items1
  • openai.agent_session_subagent_items.listList subagent itemsread
Agent session subagent turn items1
  • openai.agent_session_subagent_turn_items.listList subagent turn itemsread
Agent session traces1
  • openai.agent_session_traces.listList agent session tracesread
Beta response input items1
  • openai.beta_response_input_items.listBeta: list a model response's input itemsread
Chat completion messages1
  • openai.chat_completion_messages.listList a stored chat completion's messagesread
Chatkit thread items1
  • openai.chatkit_thread_items.listList ChatKit thread itemsread
Completions1
  • openai.completions.createCreate completionwrite
Embeddings1
  • openai.embeddings.createCreate embeddings for textread
Fine tuning job checkpoints1
  • openai.fine_tuning_job_checkpoints.listList fine-tuning checkpointsread
Fine tuning job events1
  • openai.fine_tuning_job_events.listList fine-tuning eventsread
Moderations1
  • openai.moderations.createClassify text or images for harmful content (moderation)read
Realtime client secrets1
  • openai.realtime_client_secrets.createCreate a Realtime client secretwrite
Realtime sessions1
  • openai.realtime_sessions.createCreate a Realtime session and its client secretwrite
Realtime transcription sessions1
  • openai.realtime_transcription_sessions.createCreate a Realtime transcription sessionwrite
Realtime translation client secrets1
  • openai.realtime_translation_client_secrets.createCreate a Realtime translation client secretwrite
Response input items1
  • openai.response_input_items.listList a model response's input itemsread
Safety alerts1
  • openai.safety_alerts.getGet project safety alertread
Safety cases1
  • openai.safety_cases.getGet safety caseread
Video characters1
  • openai.video_characters.getRetrieve a video characterread
Voices1
  • openai.voices.createCreate a custom voicewrite
Webhook event types1
  • openai.webhook_event_types.listList Webhook Event Typesread

Questions

The OpenAI Platform MCP server, answered.

Is there an OpenAI Platform MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 186 OpenAI Platform actions across videos, webhook endpoints, beta responses and fine tuning jobs, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by OpenAI Platform.

What do I need to connect OpenAI Platform?

OpenAI API key (sk-proj-… project key or sk-svcacct-… service account key). The free call account { op: "connections.requirements", service: "openai" } lists exactly what to paste.

Can an AI agent delete or change things in OpenAI Platform?

Only if its key allows it, and only with an explicit confirmation. 40 OpenAI Platform actions are destructive, including delete file, delete a container file and delete an agent session artifact. 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 OpenAI Platform API limit?

actionlake paces every call to the limits in the OpenAI Platform service file: 3,000 calls a minute per connection. Repeated reads are answered from cache (8 OpenAI Platform actions can be), which never reaches OpenAI Platform.

What does an OpenAI Platform action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (186 OpenAI Platform actions page). Cache hits, searches, dry runs and calls OpenAI Platform 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 OpenAI Platform API does it cover?

The OpenAI Platform API OpenAPI 2.3.0 (openai/openai-openapi main @ 40496db (2026-10-01T05:02:17Z)) at api.openai.com/v1. It is built from OpenAI Platform's documentation as read on 1 October 2026. 186 actions in 64 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my OpenAI Platform 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 OpenAI Platform 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.

More connectors like OpenAI Platform

Shares the most action names with

Joins with, on shared entities

Browse

actionlake is independent. It is not made or endorsed by OpenAI Platform; the name is the vendor's own. Counts are from the OpenAI Platform service file, version 1.0.0.

Give your agent OpenAI Platform today.

Connect OpenAI Platform freeSee pricing

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