--- title: "OpenAI Platform MCP server for AI agents - actionlake" description: "Give Claude 186 OpenAI Platform actions through one MCP server: videos, webhook endpoints. Your agent never holds the credential. 100,000 calls a month free." canonical: https://actionlake.com/connectors/openai-platform updated: 2026-10-01 --- 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 free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/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 ``` - 186 actions in one signed file - 85 read look, never change - 61 write create and update - 40 wait for a yes destructive, 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_key` OpenAI 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 call check { 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 2026[OpenAPI spec (GitHub)](https://raw.githubusercontent.com/openai/openai-openapi/main/openapi.json) **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. - **85** read look, never change - **61** write create and update - **40** destructive wait 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. | Action | What it does | Effect | Same name in | | --- | --- | --- | --- | | `openai.files.list` List files | Returns a list of files. | read | `content.file.list` 77 connectors | | `openai.container_files.list` List container files | List Container files | read | `content.file.list` 77 connectors | | `openai.conversation_items.list` List conversation items | List all items for a conversation with the given ID. | read | `comm.message.list` 42 connectors | | `openai.chatkit_thread_items.list` List ChatKit thread items | List items that belong to a ChatKit thread. | read | `comm.message.list` 42 connectors | | `openai.live_sessions.fork` Fork a stored Live session onto a new connection | Fork a stored Live session onto a new WebRTC connection. | write | `comm.call.create` 38 connectors | | `openai.live_sessions.create` Create a Live session or place an outbound SIP call | Create a Live WebRTC session or place an outbound SIP call. | write | `comm.call.create` 38 connectors | | `openai.conversations.create` Create a conversation | Create a conversation. | write | `comm.chat.create` 15 connectors | | `openai.files.delete` Delete file | Delete a file and remove it from all vector stores. | destructive | `content.file.delete` 68 connectors | | `openai.realtime_sessions.create` Create a Realtime session and its client secret | Create an ephemeral API token for use in client-side applications with the Realtime API. | write | `identity.api_key.create` 100 connectors | | `openai.realtime_client_secrets.create` Create a Realtime client secret | Create a Realtime client secret with an associated session configuration. | write | `identity.api_key.create` 100 connectors | | `openai.graders.run` Run grader | Run a grader. | write | `analytics.inference.create` 17 connectors | | `openai.images.edit` Edit or extend images from a prompt | Creates edited or extended images from source images (by URL or file id) and a prompt. | write | `analytics.inference.create` 17 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. Read read Which OpenAI Platform files changed this week, and who changed them? calls `openai.files.list` 2. Write write Fork a stored Live session onto a new connection in OpenAI Platform. Show me exactly what you will send before you save it. calls `openai.live_sessions.fork` Governance for OpenAI Platform ## Destructive actions wait for a yes. 40 OpenAI Platform actions are destructive. The first 10: - Delete file `openai.files.delete` - Delete a container file `openai.container_files.delete` - Delete an agent session artifact `openai.agent_session_artifacts.delete` - Delete a conversation item `openai.conversation_items.delete` - Delete a conversation `openai.conversations.delete` - Delete a ChatKit thread `openai.chatkit_threads.delete` - Delete Webhook Endpoint `openai.webhook_endpoints.delete` - Delete a vault credential `openai.vault_credentials.delete` - Hang up a Live session `openai.live_sessions.hangup` - Reject an incoming Live SIP call `openai.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. do openai.files.delete confirm_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: "lead@example.com" }, { match: "openai.container_files.delete", approver: "lead@example.com" }, { match: "openai.agent_session_artifacts.delete", approver: "lead@example.com" } ] } ``` 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. - 1 upstream call per action all 186 OpenAI Platform actions - 186 actions page each page of a long list is one call - 8 reads can be cached a cache hit costs nothing - 100,000 calls a month, free paid plans from US$49 a month for 250,000 [See pricing](https://actionlake.com/pricing) Action index ## Every OpenAI Platform action. 186 actions by area: the id your agent calls, what it does, and its effect. **Videos 7** - `openai.videos.create` Create a video write - `openai.videos.delete` Delete a video destructive - `openai.videos.edit` Create a video edit write - `openai.videos.extend` Create a video extension write - `openai.videos.get` Retrieve a video read - `openai.videos.list` List videos read - `openai.videos.remix` Create a video remix write **Webhook endpoints 7** - `openai.webhook_endpoints.create` Create Webhook Endpoint write - `openai.webhook_endpoints.delete` Delete Webhook Endpoint destructive - `openai.webhook_endpoints.get` Retrieve Webhook Endpoint read - `openai.webhook_endpoints.list` List Webhook Endpoints read - `openai.webhook_endpoints.rotate_secret` Rotate Webhook Endpoint Signing Secret destructive - `openai.webhook_endpoints.test` Test Webhook Endpoint write - `openai.webhook_endpoints.update` Update Webhook Endpoint write **Beta responses 6** - `openai.beta_responses.cancel` Beta: cancel a response destructive - `openai.beta_responses.compact` Beta: compact a conversation into a shorter context write - `openai.beta_responses.count_input_tokens` Beta: count a model response's input tokens read - `openai.beta_responses.create` Beta: create a model response write - `openai.beta_responses.delete` Beta: delete a model response destructive - `openai.beta_responses.get` Beta: get a model response read **Fine tuning jobs 6** - `openai.fine_tuning_jobs.cancel` Cancel a fine-tuning job destructive - `openai.fine_tuning_jobs.create` Create fine-tuning job write - `openai.fine_tuning_jobs.get` Retrieve fine-tuning job read - `openai.fine_tuning_jobs.list` List fine-tuning jobs read - `openai.fine_tuning_jobs.pause` Pause a fine-tuning job write - `openai.fine_tuning_jobs.resume` Resume a paused fine-tuning job write **Live sessions 6** - `openai.live_sessions.accept` Accept an incoming Live SIP call write - `openai.live_sessions.create` Create a Live session or place an outbound SIP call write - `openai.live_sessions.fork` Fork a stored Live session onto a new connection write - `openai.live_sessions.hangup` Hang up a Live session destructive - `openai.live_sessions.refer` Transfer a Live SIP call write - `openai.live_sessions.reject` Reject an incoming Live SIP call destructive **Responses 6** - `openai.responses.cancel` Cancel a response destructive - `openai.responses.compact` Compact a conversation into a shorter context write - `openai.responses.count_input_tokens` Count a model response's input tokens read - `openai.responses.create` Create a model response write - `openai.responses.delete` Delete a model response destructive - `openai.responses.get` Get a model response read **Vector store files 6** - `openai.vector_store_files.create` Create vector store file write - `openai.vector_store_files.delete` Delete vector store file destructive - `openai.vector_store_files.get` Retrieve vector store file read - `openai.vector_store_files.get_content` Retrieve vector store file content read - `openai.vector_store_files.list` List vector store files read - `openai.vector_store_files.update` Update vector store file attributes write **Vector stores 6** - `openai.vector_stores.create` Create vector store write - `openai.vector_stores.delete` Delete vector store destructive - `openai.vector_stores.get` Retrieve vector store read - `openai.vector_stores.list` List vector stores read - `openai.vector_stores.search` Search vector store read - `openai.vector_stores.update` Modify vector store write **Agent environment templates 5** - `openai.agent_environment_templates.create` Create an agent environment template write - `openai.agent_environment_templates.delete` Delete an agent environment template destructive - `openai.agent_environment_templates.get` Retrieve an agent environment template read - `openai.agent_environment_templates.list` List agent environment templates read - `openai.agent_environment_templates.update` Update an agent environment template write **Agent sessions 5** - `openai.agent_sessions.create` Create an agent session write - `openai.agent_sessions.delete` Delete an agent session destructive - `openai.agent_sessions.get` Retrieve an agent session read - `openai.agent_sessions.list` List agent sessions read - `openai.agent_sessions.update` Update an agent session write **Agents 5** - `openai.agents.create` Create an agent write - `openai.agents.delete` Delete an agent destructive - `openai.agents.get` Retrieve an agent read - `openai.agents.list` List agents read - `openai.agents.update` Update an agent write **Chat completions 5** - `openai.chat_completions.create` Create chat completion write - `openai.chat_completions.delete` Delete chat completion destructive - `openai.chat_completions.get` Get chat completion read - `openai.chat_completions.list` List Chat Completions read - `openai.chat_completions.update` Update chat completion write **Eval runs 5** - `openai.eval_runs.cancel` Cancel eval run destructive - `openai.eval_runs.create` Create eval run write - `openai.eval_runs.delete` Delete eval run destructive - `openai.eval_runs.get` Get an eval run read - `openai.eval_runs.list` Get eval runs read **Evals 5** - `openai.evals.create` Create eval write - `openai.evals.delete` Delete an eval destructive - `openai.evals.get` Get an eval read - `openai.evals.list` List evals read - `openai.evals.update` Update an eval write **Vault credentials 5** - `openai.vault_credentials.create` Create a vault credential write - `openai.vault_credentials.delete` Delete a vault credential destructive - `openai.vault_credentials.get` Retrieve a vault credential read - `openai.vault_credentials.list` List vault credentials read - `openai.vault_credentials.rotate` Rotate a vault credential's secret destructive **Batches 4** - `openai.batches.cancel` Cancel batch destructive - `openai.batches.create` Create batch write - `openai.batches.get` Retrieve batch read - `openai.batches.list` List batches read **Container files 4** - `openai.container_files.create` Create container file write - `openai.container_files.delete` Delete a container file destructive - `openai.container_files.get` Retrieve container file read - `openai.container_files.list` List container files read **Containers 4** - `openai.containers.create` Create container write - `openai.containers.delete` Delete a container destructive - `openai.containers.get` Retrieve container read - `openai.containers.list` List containers read **Conversation items 4** - `openai.conversation_items.create` Create conversation items write - `openai.conversation_items.delete` Delete a conversation item destructive - `openai.conversation_items.get` Retrieve a conversation item read - `openai.conversation_items.list` List conversation items read **Conversations 4** - `openai.conversations.create` Create a conversation write - `openai.conversations.delete` Delete a conversation destructive - `openai.conversations.get` Retrieve a conversation read - `openai.conversations.update` Update a conversation write **Realtime calls 4** - `openai.realtime_calls.accept` Accept an incoming Realtime SIP call write - `openai.realtime_calls.hangup` Hang up a Realtime call destructive - `openai.realtime_calls.refer` Transfer a Realtime SIP call write - `openai.realtime_calls.reject` Reject an incoming Realtime SIP call destructive **Skills 4** - `openai.skills.delete` Delete Skill destructive - `openai.skills.get` Get Skill read - `openai.skills.list` List Skills read - `openai.skills.set_default_version` Update Skill Default Version write **Vaults 4** - `openai.vaults.create` Create a vault write - `openai.vaults.delete` Delete a vault destructive - `openai.vaults.get` Retrieve a vault read - `openai.vaults.list` List vaults read **Vector store file batches 4** - `openai.vector_store_file_batches.cancel` Cancel vector store file batch destructive - `openai.vector_store_file_batches.create` Create vector store file batch write - `openai.vector_store_file_batches.get` Retrieve vector store file batch read - `openai.vector_store_file_batches.list_files` List vector store files in a batch read **Voice consents 4** - `openai.voice_consents.delete` Delete voice consent destructive - `openai.voice_consents.get` Retrieve voice consent read - `openai.voice_consents.list` List voice consents read - `openai.voice_consents.update` Update voice consent write **Agent session artifacts 3** - `openai.agent_session_artifacts.delete` Delete an agent session artifact destructive - `openai.agent_session_artifacts.get` Retrieve an agent session artifact read - `openai.agent_session_artifacts.list` List agent session artifacts read **Chatkit threads 3** - `openai.chatkit_threads.delete` Delete a ChatKit thread destructive - `openai.chatkit_threads.get` Retrieve a ChatKit thread read - `openai.chatkit_threads.list` List ChatKit threads read **Files 3** - `openai.files.delete` Delete file destructive - `openai.files.get` Retrieve file read - `openai.files.list` List files read **Fine tuning checkpoint permissions 3** - `openai.fine_tuning_checkpoint_permissions.create` Create checkpoint permissions write - `openai.fine_tuning_checkpoint_permissions.delete` Delete checkpoint permission destructive - `openai.fine_tuning_checkpoint_permissions.list` List checkpoint permissions read **Models 3** - `openai.models.delete` Delete a fine-tuned model destructive - `openai.models.get` Retrieve model read - `openai.models.list` List models read **Skill versions 3** - `openai.skill_versions.delete` Delete Skill Version destructive - `openai.skill_versions.get` Get Skill Version read - `openai.skill_versions.list` List Skill Versions read **Uploads 3** - `openai.uploads.cancel` Cancel upload destructive - `openai.uploads.complete` Complete upload write - `openai.uploads.create` Create upload write **Agent environment files 2** - `openai.agent_environment_files.create` Create an agent environment file write - `openai.agent_environment_files.list` List agent environment files read **Agent session subagent turns 2** - `openai.agent_session_subagent_turns.get` Retrieve a subagent turn read - `openai.agent_session_subagent_turns.list` List subagent turns read **Agent session subagents 2** - `openai.agent_session_subagents.get` Retrieve a session subagent read - `openai.agent_session_subagents.list` List session subagents read **Agent session turns 2** - `openai.agent_session_turns.get` Retrieve an agent session turn read - `openai.agent_session_turns.list` List agent session turns read **Chatkit sessions 2** - `openai.chatkit_sessions.cancel` Cancel a ChatKit session destructive - `openai.chatkit_sessions.create` Create a ChatKit session write **Eval run output items 2** - `openai.eval_run_output_items.get` Get an output item of an eval run read - `openai.eval_run_output_items.list` Get eval run output items read **Graders 2** - `openai.graders.run` Run grader write - `openai.graders.validate` Validate grader read **Images 2** - `openai.images.edit` Edit or extend images from a prompt write - `openai.images.generate` Generate an image from a prompt write **Agent environments 1** - `openai.agent_environments.get` Retrieve an agent environment read **Agent session events 1** - `openai.agent_session_events.send` Send input events to an agent session write **Agent session items 1** - `openai.agent_session_items.list` List agent session items read **Agent session subagent items 1** - `openai.agent_session_subagent_items.list` List subagent items read **Agent session subagent turn items 1** - `openai.agent_session_subagent_turn_items.list` List subagent turn items read **Agent session traces 1** - `openai.agent_session_traces.list` List agent session traces read **Beta response input items 1** - `openai.beta_response_input_items.list` Beta: list a model response's input items read **Chat completion messages 1** - `openai.chat_completion_messages.list` List a stored chat completion's messages read **Chatkit thread items 1** - `openai.chatkit_thread_items.list` List ChatKit thread items read **Completions 1** - `openai.completions.create` Create completion write **Embeddings 1** - `openai.embeddings.create` Create embeddings for text read **Fine tuning job checkpoints 1** - `openai.fine_tuning_job_checkpoints.list` List fine-tuning checkpoints read **Fine tuning job events 1** - `openai.fine_tuning_job_events.list` List fine-tuning events read **Moderations 1** - `openai.moderations.create` Classify text or images for harmful content (moderation) read **Realtime client secrets 1** - `openai.realtime_client_secrets.create` Create a Realtime client secret write **Realtime sessions 1** - `openai.realtime_sessions.create` Create a Realtime session and its client secret write **Realtime transcription sessions 1** - `openai.realtime_transcription_sessions.create` Create a Realtime transcription session write **Realtime translation client secrets 1** - `openai.realtime_translation_client_secrets.create` Create a Realtime translation client secret write **Response input items 1** - `openai.response_input_items.list` List a model response's input items read **Safety alerts 1** - `openai.safety_alerts.get` Get project safety alert read **Safety cases 1** - `openai.safety_cases.get` Get safety case read **Video characters 1** - `openai.video_characters.get` Retrieve a video character read **Voices 1** - `openai.voices.create` Create a custom voice write **Webhook event types 1** - `openai.webhook_event_types.list` List Webhook Event Types read 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 - [Google Gemini API (AI Studio) 21](https://actionlake.com/connectors/google-gemini-api-ai-studio) - [Claude API (Anthropic) 16](https://actionlake.com/connectors/anthropic-claude-api) - [OpenRouter 16](https://actionlake.com/connectors/openrouter) - [Mistral AI 14](https://actionlake.com/connectors/mistral-ai) - [Groq 10](https://actionlake.com/connectors/groq) - [Perplexity 9](https://actionlake.com/connectors/perplexity) Joins with, on shared entities - [Slack 1](https://actionlake.com/connectors/slack) - [Canvas LMS 1](https://actionlake.com/connectors/canvas-lms) - [Unified.to 1](https://actionlake.com/connectors/unified-to) - [Appwrite Cloud 1](https://actionlake.com/connectors/appwrite-cloud) - [Teamwork 1](https://actionlake.com/connectors/teamwork) - [ERPNext (Frappe) 1](https://actionlake.com/connectors/erpnext-frappe) Browse - [All AI connectors](https://actionlake.com/connectors/category/ai) - [All connectors](https://actionlake.com/connectors) - [How actionlake compares](https://actionlake.com/compare) 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 free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free. --- Source: https://actionlake.com/connectors/openai-platform More: https://actionlake.com/llms.txt