Skip to content
actionlake
Start free

Connectors · AI

Portkey MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Portkey and the rest of your systems. It gives your agent 248 Portkey actions (121 reads, 88 writes and 39 that wait for a confirmation) and holds the Portkey credential itself, so the agent never does. It paces Portkey's limits and records every call.

Connect Portkey 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: "portkey.users.list_users",  intent: "check which Portkey account is connected"}# Get users · read · 1 upstream call
  • 248actionsin one signed file
  • 121readlook, never change
  • 88writecreate and update
  • 39wait for a yesdestructive, confirmed first

Set up

Connect Portkey 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 Portkey.

    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_keyPortkey API key
    account { op: "connections.requirements", service: "portkey" }
# 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: "portkey.users.list_users" }# get users · read · 1 upstream callcheck { action: "portkey.users.delete_user", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Portkey 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
600 calls a minute, per connection
API covered
Portkey API 2.0.0 (OpenAPI 3, api.portkey.ai/v1)api.portkey.ai/v1
Built from
Portkey's documentation, read 23 October 2026OpenAPI spec (GitHub)portkey.ai
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
112 of 121 reads, for up to 5 minutes; a write clears what it affects
Shared entities
3, so ask can line Portkey up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Portkey.

248 actions in 43 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 121readlook, never change
  • 88writecreate and update
  • 39destructivewait for a confirmation

  1. Assistants

    23

    9 read · 10 write · 4 destructive

    Create an assistant with a model and instructions · Create a message · Create a run · Create a thread

  2. Prompts

    18

    8 read · 8 write · 2 destructive

    Create a new prompt · Prompts Completions · Create a new prompt partial · Get all versions of a prompt partial

  3. Analytics graphs

    17

    17 read · 0 write · 0 destructive

    Get cache hit rate graph · Get cache hit latency graph · Get cost graph · Get errors graph

  4. Vector stores

    13

    6 read · 4 write · 3 destructive

    Create a vector store · Create a vector store file by attaching a [File](https://platform.openai.com/docs/api-reference/files) to a [vector store](https://platform.openai.com/docs/api-reference/vector-stores/object) · Create a vector store file batch · Returns a list of vector store files in a batch

  5. Inference

    9

    1 read · 8 write · 0 destructive

    Messages · Chat · Completions · Embeddings

  6. Logs

    9

    4 read · 4 write · 1 destructive

    Create log export · Insert New logs · Get all logs exports · Download log export

  7. Users

    9

    4 read · 3 write · 2 destructive

    Get users · Get user · Update user · Remove a user

  8. Guardrails

    8

    3 read · 4 write · 1 destructive

    Create a new guardrail · List MCP server mappings · List guardrails · Bulk sync MCP server mappings

35 more areas · 142 actions
  • Workspaces 8
  • Analytics groups 7
  • Usage limits policies 7
  • API keys 6
  • Configs 6
  • Deployments 6
  • Fine tuning 6
  • MCP servers 6
  • Access policies 5
  • Collections 5
  • Egress allowlist 5
  • Integrations 5
  • Labels 5
  • MCP integrations 5
  • Providers 5
  • Rate limits policies 5
  • Secret references 5
  • Virtual keys 5
  • Workspace members 5
  • Batches 4
  • Responses 4
  • Files 3
  • Integrations models 3
  • Models 3
  • Feedback 2
  • Integrations workspaces 2
  • MCP integrations capabilities 2
  • MCP integrations workspaces 2
  • MCP servers capabilities 2
  • MCP servers connections 2
  • MCP servers user access 2
  • Analytics summary 1
  • Audit logs 1
  • MCP integrations metadata 1
  • Model pricing 1

Top actions

The Portkey API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 17 of Portkey's 17 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
portkey.users.list_usersGet usersGet users.readidentity.user.list474 connectors
portkey.users.get_userGet userGet user.readidentity.user.get399 connectors
portkey.workspaces.list_workspacesGet All WorkspacesGet All Workspaces.readwork.workspace.list50 connectors
portkey.users.delete_userRemove a userRemove a user.destructiveidentity.user.delete253 connectors
portkey.workspace_members.list_membersGet workspace membersGet workspace members.readwork.workspace_member.list26 connectors
portkey.api_keys.create_api_keyCreate API KeysCreate API Keys.writeidentity.api_key.create100 connectors
portkey.api_keys.list_api_keysGet AllGet All.readidentity.api_key.list96 connectors
portkey.workspaces.create_workspaceCreate WorkspaceCreate Workspace.writework.workspace.create36 connectors
portkey.workspace_members.update_memberUpdate workspace memberUpdate workspace member.writework.workspace_member.update16 connectors
portkey.files.list_filesList FilesList Files.readthis connector
portkey.logs.insert_logsInsert New logsInsert New logs.writethis connector
portkey.labels.list_labelsList labelsList labels.readthis connector

Try it

Prompts to paste into Claude.

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

  1. Readread

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

    callsportkey.users.list_users

  2. Writewrite

    Create API Keys in Portkey. Show me exactly what you will send before you save it.

    callsportkey.api_keys.create_api_key

Governance for Portkey

Destructive actions wait for a yes.

39 Portkey actions are destructive. The first 10:

  • Remove a userportkey.users.delete_user
  • Remove an API Keyportkey.api_keys.delete_api_key
  • Delete a workspaceportkey.workspaces.delete_workspace
  • Delete Fileportkey.files.delete_file
  • Delete a labelportkey.labels.delete_label
  • Delete a fine-tuned model. You must have the Owner role in your organization to delete a modelportkey.models.delete_model
  • Delete Invite By IDportkey.users.delete_invite
  • Delete a configportkey.configs.delete_config
  • Delete a promptportkey.prompts.delete_prompt
  • Rotate API Keyportkey.api_keys.rotate_api_key

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.

doportkey.users.delete_userconfirm_policy: human

Remove a user?

intent: the user asked me to remove a user

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

Cost

What Portkey costs on actionlake.

Every Portkey action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Portkey 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 248 Portkey actions
  • 248actions pageeach page of a long list is one call
  • 112reads 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 Portkey action.

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

Assistants23
  • portkey.assistants.cancel_runCancels a run that is `in_progress`destructive
  • portkey.assistants.create_assistantCreate an assistant with a model and instructionswrite
  • portkey.assistants.create_messageCreate a messagewrite
  • portkey.assistants.create_runCreate a runwrite
  • portkey.assistants.create_threadCreate a threadwrite
  • portkey.assistants.create_thread_and_runCreate a thread and run it in one requestwrite
  • portkey.assistants.delete_assistantDelete an assistantdestructive
  • portkey.assistants.delete_messageDeletes a messagedestructive
  • portkey.assistants.delete_threadDelete a threaddestructive
  • portkey.assistants.get_assistantRetrieves an assistantread
  • portkey.assistants.get_messageRetrieve a messageread
  • portkey.assistants.get_runRetrieves a runread
  • portkey.assistants.get_run_stepRetrieves a run stepread
  • portkey.assistants.get_threadRetrieves a threadread
  • portkey.assistants.list_assistantsReturns a list of assistantsread
  • portkey.assistants.list_messagesReturns a list of messages for a given threadread
  • portkey.assistants.list_run_stepsReturns a list of run steps belonging to a runread
  • portkey.assistants.list_runsReturns a list of runs belonging to a threadread
  • portkey.assistants.modify_assistantModifies an assistantwrite
  • portkey.assistants.modify_messageModifies a messagewrite
  • portkey.assistants.modify_runModifies a runwrite
  • portkey.assistants.modify_threadModifies a threadwrite
  • portkey.assistants.submit_tool_ouputs_to_runWhen a run has the `status: "requires_action"` and `required_action.type` is `submit_tool_outputs`, this endpoint can be used to submit the outputs from the tool calls once they're all completed. All outputs must be submitted in a single requestwrite
Prompts18
  • portkey.prompts.create_promptCreate a new promptwrite
  • portkey.prompts.create_prompt_completionPrompts Completionswrite
  • portkey.prompts.create_prompt_partialCreate a new prompt partialwrite
  • portkey.prompts.create_prompt_renderPrompts Renderread
  • portkey.prompts.delete_promptDelete a promptdestructive
  • portkey.prompts.delete_prompt_partialDelete a prompt partialdestructive
  • portkey.prompts.get_promptGet a prompt by ID or slugread
  • portkey.prompts.get_prompt_by_versionGet a specific version of a promptread
  • portkey.prompts.get_prompt_partialGet a prompt partial by ID or slugread
  • portkey.prompts.get_prompt_partial_versionsGet all versions of a prompt partialread
  • portkey.prompts.get_prompt_versionsGet all versions of a promptread
  • portkey.prompts.list_prompt_partialsList prompt partialsread
  • portkey.prompts.list_promptsList promptsread
  • portkey.prompts.update_promptUpdate a promptwrite
  • portkey.prompts.update_prompt_defaultSet a version as the default for a promptwrite
  • portkey.prompts.update_prompt_partialUpdate a prompt partialwrite
  • portkey.prompts.update_prompt_partial_defaultSet a version as the default for a prompt partialwrite
  • portkey.prompts.update_prompt_versionUpdate a specific version of a promptwrite
Analytics graphs17
  • portkey.analytics_graphs.get_cache_hit_rateGet cache hit rate graphread
  • portkey.analytics_graphs.get_cache_latencyGet cache hit latency graphread
  • portkey.analytics_graphs.get_costGet cost graphread
  • portkey.analytics_graphs.get_errorsGet errors graphread
  • portkey.analytics_graphs.get_errors_rateGet percentage error rate graphread
  • portkey.analytics_graphs.get_errors_stacksGet status code wise stacked error graphread
  • portkey.analytics_graphs.get_errors_status_codesGet status code wise grouped error graphread
  • portkey.analytics_graphs.get_feedbacksGet feedbacks graphread
  • portkey.analytics_graphs.get_feedbacks_ai_modelsGet feedbacks per ai_models graphread
  • portkey.analytics_graphs.get_feedbacks_scoresGet score-wise feedbacks distribution graphread
  • portkey.analytics_graphs.get_feedbacks_weightedGet weighted feedbacks graph. Weighted feedback is (value * score)read
  • portkey.analytics_graphs.get_latencyGet latency graphread
  • portkey.analytics_graphs.get_requestsGet requests graphread
  • portkey.analytics_graphs.get_requests_rescuedGet retry and fallback rescued requests graphread
  • portkey.analytics_graphs.get_tokensGet tokens graphread
  • portkey.analytics_graphs.get_usersGet users graph. Returns unique user count across different time bucketsread
  • portkey.analytics_graphs.get_users_requestsGet users requests graph. Returns average requests per user across different time bucketsread
Vector stores13
  • portkey.vector_stores.cancel_vector_store_file_batchCancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possibledestructive
  • portkey.vector_stores.create_vector_storeCreate a vector storewrite
  • portkey.vector_stores.create_vector_store_fileCreate a vector store file by attaching a [File](https://platform.openai.com/docs/api-reference/files) to a [vector store](https://platform.openai.com/docs/api-reference/vector-stores/object)write
  • portkey.vector_stores.create_vector_store_file_batchCreate a vector store file batchwrite
  • portkey.vector_stores.delete_vector_storeDelete a vector storedestructive
  • portkey.vector_stores.delete_vector_store_fileDelete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the [delete file](https://platform.openai.com/docs/api-reference/files/delete) endpointdestructive
  • portkey.vector_stores.get_vector_storeRetrieves a vector storeread
  • portkey.vector_stores.get_vector_store_fileRetrieves a vector store fileread
  • portkey.vector_stores.get_vector_store_file_batchRetrieves a vector store file batchread
  • portkey.vector_stores.list_files_in_vector_store_batchReturns a list of vector store files in a batchread
  • portkey.vector_stores.list_vector_store_filesReturns a list of vector store filesread
  • portkey.vector_stores.list_vector_storesReturns a list of vector storesread
  • portkey.vector_stores.modify_vector_storeModifies a vector storewrite
Inference9
  • portkey.inference.count_anthropic_message_tokensCount Message Tokensread
  • portkey.inference.create_anthropic_messageMessageswrite
  • portkey.inference.create_chat_completionChatwrite
  • portkey.inference.create_completionCompletionswrite
  • portkey.inference.create_embeddingEmbeddingswrite
  • portkey.inference.create_imageCreate Imagewrite
  • portkey.inference.create_moderationIdentify potentially harmful content in text and images. **Only** works with [OpenAI's Moderations endpoint](https://platform.openai.com/docs/guides/moderation) currentlywrite
  • portkey.inference.create_ocrOCRwrite
  • portkey.inference.create_rerankRerankwrite
Logs9
  • portkey.logs.cancel_log_exportCancel log exportdestructive
  • portkey.logs.create_log_exportCreate log exportwrite
  • portkey.logs.download_log_exportDownload log exportread
  • portkey.logs.get_logGet a specific logread
  • portkey.logs.get_log_exportGet a specific logs exportread
  • portkey.logs.insert_logsInsert New logswrite
  • portkey.logs.list_log_exportsGet all logs exportsread
  • portkey.logs.start_log_exportStart log exportwrite
  • portkey.logs.update_log_exportUpdate a logs exportwrite
Users9
  • portkey.users.create_inviteInvite Userwrite
  • portkey.users.delete_inviteDelete Invite By IDdestructive
  • portkey.users.delete_userRemove a userdestructive
  • portkey.users.get_inviteGet Inviteread
  • portkey.users.get_userGet userread
  • portkey.users.list_invitesGet All Invitesread
  • portkey.users.list_usersGet usersread
  • portkey.users.resend_inviteResend Invitewrite
  • portkey.users.update_userUpdate userwrite
Guardrails8
  • portkey.guardrails.bulk_sync_guardrail_mcp_serversBulk sync MCP server mappingswrite
  • portkey.guardrails.create_guardrailCreate a new guardrailwrite
  • portkey.guardrails.delete_guardrailDelete a guardraildestructive
  • portkey.guardrails.get_guardrailGet a specific guardrailread
  • portkey.guardrails.list_guardrail_mcp_serversList MCP server mappingsread
  • portkey.guardrails.list_guardrailsList guardrailsread
  • portkey.guardrails.update_guardrailUpdate a guardrailwrite
  • portkey.guardrails.upsert_guardrail_mcp_serverUpsert single MCP server mappingwrite
Workspaces8
  • portkey.workspaces.create_scim_workspace_mappingCreate SCIM Group to Workspace Mappingwrite
  • portkey.workspaces.create_workspaceCreate Workspacewrite
  • portkey.workspaces.delete_scim_workspace_mappingDelete SCIM Group to Workspace Mappingdestructive
  • portkey.workspaces.delete_workspaceDelete a workspacedestructive
  • portkey.workspaces.get_workspaceGet workspaceread
  • portkey.workspaces.list_scim_workspace_mappingsList SCIM Group to Workspace Mappingsread
  • portkey.workspaces.list_workspacesGet All Workspacesread
  • portkey.workspaces.update_workspaceUpdate Workspacewrite
Analytics groups7
  • portkey.analytics_groups.list_a2aGet A2A (agent-to-agent) grouped dataread
  • portkey.analytics_groups.list_ai_modelsGet ai model grouped dataread
  • portkey.analytics_groups.list_mcpGet MCP server grouped dataread
  • portkey.analytics_groups.list_metadataGet metadata key based grouped dataread
  • portkey.analytics_groups.list_providerGet provider grouped dataread
  • portkey.analytics_groups.list_usersGet metadata users grouped dataread
  • portkey.analytics_groups.list_workspacesGet workspace grouped dataread
Usage limits policies7
  • portkey.usage_limits_policies.create_usage_limits_policyCreate Usage Limits Policywrite
  • portkey.usage_limits_policies.delete_usage_limits_policyDelete Usage Limits Policydestructive
  • portkey.usage_limits_policies.get_usage_limits_policyGet Usage Limits Policyread
  • portkey.usage_limits_policies.list_usage_limits_policiesList Usage Limits Policiesread
  • portkey.usage_limits_policies.list_usage_limits_policy_entitiesList Usage Limits Policy Entitiesread
  • portkey.usage_limits_policies.reset_usage_limits_policy_entityReset Usage Limits Policy Entitywrite
  • portkey.usage_limits_policies.update_usage_limits_policyUpdate Usage Limits Policywrite
API keys6
  • portkey.api_keys.create_api_keyCreate API Keyswrite
  • portkey.api_keys.delete_api_keyRemove an API Keydestructive
  • portkey.api_keys.get_api_keyGet API Keysread
  • portkey.api_keys.list_api_keysGet Allread
  • portkey.api_keys.rotate_api_keyRotate API Keydestructive
  • portkey.api_keys.update_api_keyUpdate API Keyswrite
Configs6
  • portkey.configs.create_configCreate a configwrite
  • portkey.configs.delete_configDelete a configdestructive
  • portkey.configs.get_configGet a configread
  • portkey.configs.list_config_versionsList versions for a configread
  • portkey.configs.list_configsList all configsread
  • portkey.configs.update_configUpdate a configwrite
Deployments6
  • portkey.deployments.create_deploymentRegister a Gateway Deploymentwrite
  • portkey.deployments.delete_deploymentDelete a Gateway Deploymentdestructive
  • portkey.deployments.get_deploymentGet a Gateway Deploymentread
  • portkey.deployments.list_deploymentsList All Gateway Deploymentsread
  • portkey.deployments.ping_deploymentPing a Gateway Deploymentread
  • portkey.deployments.update_deploymentUpdate a Gateway Deploymentwrite
Fine tuning6
  • portkey.fine_tuning.cancel_fine_tuning_jobImmediately cancel a fine-tune jobdestructive
  • portkey.fine_tuning.create_fine_tuning_jobCreate a Finetune Jobwrite
  • portkey.fine_tuning.list_fine_tuning_eventsGet status updates for a fine-tuning jobread
  • portkey.fine_tuning.list_fine_tuning_job_checkpointsList checkpoints for a fine-tuning jobread
  • portkey.fine_tuning.list_paginated_fine_tuning_jobsList your organization's fine-tuning jobsread
  • portkey.fine_tuning.retrieve_fine_tuning_jobGet info about a fine-tuning job. [Learn more about fine-tuning](https://platform.openai.com/docs/guides/fine-tuning)read
MCP servers6
  • portkey.mcp_servers.mcp_servers_createCreate MCP Serverwrite
  • portkey.mcp_servers.mcp_servers_deleteDelete MCP Serverdestructive
  • portkey.mcp_servers.mcp_servers_listList MCP Serversread
  • portkey.mcp_servers.mcp_servers_retrieveGet MCP Serverread
  • portkey.mcp_servers.mcp_servers_testTest MCP Server Connectionread
  • portkey.mcp_servers.mcp_servers_updateUpdate MCP Serverwrite
Access policies5
  • portkey.access_policies.create_access_policyCreate Access Policywrite
  • portkey.access_policies.delete_access_policyDelete Access Policydestructive
  • portkey.access_policies.get_access_policyGet Access Policyread
  • portkey.access_policies.list_access_policiesList Access Policiesread
  • portkey.access_policies.update_access_policyUpdate Access Policywrite
Collections5
  • portkey.collections.create_collectionCreate a new collectionwrite
  • portkey.collections.delete_collectionDelete collectiondestructive
  • portkey.collections.get_collectionGet collection detailsread
  • portkey.collections.list_collectionsList collectionsread
  • portkey.collections.update_collectionUpdate collectionwrite
Egress allowlist5
  • portkey.egress_allowlist.create_egress_allowlist_entryCreate an Egress Allowlist Entrywrite
  • portkey.egress_allowlist.delete_egress_allowlist_entryDelete an Egress Allowlist Entrydestructive
  • portkey.egress_allowlist.get_egress_allowlist_entryGet an Egress Allowlist Entryread
  • portkey.egress_allowlist.list_egress_allowlistList All Egress Allowlist Entriesread
  • portkey.egress_allowlist.update_egress_allowlist_entryUpdate an Egress Allowlist Entrywrite
Integrations5
  • portkey.integrations.create_integrationCreate an Integrationwrite
  • portkey.integrations.delete_integrationDelete an Integrationdestructive
  • portkey.integrations.get_integrationGet an Integrationread
  • portkey.integrations.list_integrationsList All Integrationsread
  • portkey.integrations.update_integrationUpdate an Integrationwrite
Labels5
  • portkey.labels.create_labelCreate a new labelwrite
  • portkey.labels.delete_labelDelete a labeldestructive
  • portkey.labels.get_labelGet a label by IDread
  • portkey.labels.list_labelsList labelsread
  • portkey.labels.update_labelUpdate a labelwrite
MCP integrations5
  • portkey.mcp_integrations.mcp_integrations_createCreate MCP Integrationwrite
  • portkey.mcp_integrations.mcp_integrations_deleteDelete MCP Integrationdestructive
  • portkey.mcp_integrations.mcp_integrations_listList MCP Integrationsread
  • portkey.mcp_integrations.mcp_integrations_retrieveGet MCP Integrationread
  • portkey.mcp_integrations.mcp_integrations_updateUpdate MCP Integrationwrite
Providers5
  • portkey.providers.create_providerCreate a Providerwrite
  • portkey.providers.delete_providerDelete a Providerdestructive
  • portkey.providers.get_providerGet a Providerread
  • portkey.providers.list_providersList All Providersread
  • portkey.providers.update_providerUpdate a Providerwrite
Rate limits policies5
  • portkey.rate_limits_policies.create_rate_limits_policyCreate Rate Limits Policywrite
  • portkey.rate_limits_policies.delete_rate_limits_policyDelete Rate Limits Policydestructive
  • portkey.rate_limits_policies.get_rate_limits_policyGet Rate Limits Policyread
  • portkey.rate_limits_policies.list_rate_limits_policiesList Rate Limits Policiesread
  • portkey.rate_limits_policies.update_rate_limits_policyUpdate Rate Limits Policywrite
Secret references5
  • portkey.secret_references.create_secret_referenceCreate a Secret Referencewrite
  • portkey.secret_references.delete_secret_referenceDelete a Secret Referencedestructive
  • portkey.secret_references.get_secret_referenceGet a Secret Referenceread
  • portkey.secret_references.list_secret_referencesList All Secret Referencesread
  • portkey.secret_references.update_secret_referenceUpdate a Secret Referencewrite
Virtual keys5
  • portkey.virtual_keys.create_virtual_keyCreate a Virtual Keywrite
  • portkey.virtual_keys.delete_virtual_keyDelete a Virtual Keydestructive
  • portkey.virtual_keys.get_virtual_keyGet a Virtual Keyread
  • portkey.virtual_keys.list_virtual_keysList All Virtual Keysread
  • portkey.virtual_keys.update_virtual_keyUpdate a Virtual Keywrite
Workspace members5
  • portkey.workspace_members.add_membersAdd workspace memberwrite
  • portkey.workspace_members.get_memberGet memberread
  • portkey.workspace_members.list_membersGet workspace membersread
  • portkey.workspace_members.remove_memberRemove workspace memberdestructive
  • portkey.workspace_members.update_memberUpdate workspace memberwrite
Batches4
  • portkey.batches.cancel_batchCancels an in-progress batch. The batch will be in status `cancelling` for up to 10 minutes, before changing to `cancelled`, where it will have partial results (if any) available in the output filedestructive
  • portkey.batches.create_batchCreates and executes a batch from an uploaded file of requestswrite
  • portkey.batches.list_batchesList your organization's batchesread
  • portkey.batches.retrieve_batchRetrieves a batchread
Responses4
  • portkey.responses.create_responseCreates a model responsewrite
  • portkey.responses.delete_responseDeletes a model response with the given IDdestructive
  • portkey.responses.get_responseRetrieves a model response with the given IDread
  • portkey.responses.list_input_itemsReturns a list of input items for a given responseread
Files3
  • portkey.files.delete_fileDelete Filedestructive
  • portkey.files.list_filesList Filesread
  • portkey.files.retrieve_fileReturns information about a specific fileread
Integrations models3
  • portkey.integrations_models.delete_integration_modelsBulk delete integration custom modelsdestructive
  • portkey.integrations_models.list_integration_modelsList integration modelsread
  • portkey.integrations_models.update_integration_modelsBulk update integration modelswrite
Models3
  • portkey.models.delete_modelDelete a fine-tuned model. You must have the Owner role in your organization to delete a modeldestructive
  • portkey.models.list_modelsList Available Modelsread
  • portkey.models.retrieve_modelRetrieves a model instance, providing basic information about the model such as the owner and permissioningread
Feedback2
  • portkey.feedback.create_feedbackCreate new feedbackwrite
  • portkey.feedback.update_feedbackUpdates existing feedbackwrite
Integrations workspaces2
  • portkey.integrations_workspaces.list_integration_workspacesList integration workspace accessread
  • portkey.integrations_workspaces.update_integration_workspacesBulk update workspace accesswrite
MCP integrations capabilities2
  • portkey.mcp_integrations_capabilities.mcp_integration_capabilities_bulk_updateBulk Update MCP Integration Capabilitieswrite
  • portkey.mcp_integrations_capabilities.mcp_integration_capabilities_listList MCP Integration Capabilitiesread
MCP integrations workspaces2
  • portkey.mcp_integrations_workspaces.mcp_integration_workspaces_bulk_updateBulk Update MCP Integration Workspaceswrite
  • portkey.mcp_integrations_workspaces.mcp_integration_workspaces_listList MCP Integration Workspacesread
MCP servers capabilities2
  • portkey.mcp_servers_capabilities.mcp_server_capabilities_bulk_updateBulk Update MCP Server Capabilitieswrite
  • portkey.mcp_servers_capabilities.mcp_server_capabilities_listList MCP Server Capabilitiesread
MCP servers connections2
  • portkey.mcp_servers_connections.mcp_server_connections_deleteDelete MCP Server Connectiondestructive
  • portkey.mcp_servers_connections.mcp_server_connections_listList MCP Server Connectionsread
MCP servers user access2
  • portkey.mcp_servers_user_access.list_mcp_server_user_accessList MCP Server User Accessread
  • portkey.mcp_servers_user_access.update_mcp_server_user_accessBulk Update MCP Server User Accesswrite
Analytics summary1
  • portkey.analytics_summary.get_cacheGet cache summary data for the selected time periodread
Audit logs1
  • portkey.audit_logs.list_audit_logsGet Audit Logsread
MCP integrations metadata1
  • portkey.mcp_integrations_metadata.mcp_integration_metadata_retrieveGet MCP Integration Metadataread
Model pricing1
  • portkey.model_pricing.get_model_pricingGet Model Pricingread

Questions

The Portkey MCP server, answered.

Is there a Portkey MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 248 Portkey actions across assistants, prompts, analytics graphs and vector stores, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Portkey.

What do I need to connect Portkey?

Portkey API key. The free call account { op: "connections.requirements", service: "portkey" } lists exactly what to paste.

Can an AI agent delete or change things in Portkey?

Only if its key allows it, and only with an explicit confirmation. 39 Portkey actions are destructive, including remove a user, remove an API Key and delete a workspace. 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 Portkey API limit?

actionlake paces every call to the limits in the Portkey service file: 600 calls a minute per connection. Repeated reads are answered from cache (112 Portkey actions can be), which never reaches Portkey.

What does a Portkey action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (248 Portkey actions page). Cache hits, searches, dry runs and calls Portkey 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 Portkey API does it cover?

The Portkey API 2.0.0 (OpenAPI 3, api.portkey.ai/v1) at api.portkey.ai/v1. It is built from Portkey's documentation as read on 23 October 2026. 248 actions in 43 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Portkey 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 Portkey 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 Portkey

Shares the most action names with

Joins with, on shared entities

Browse

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

Give your agent Portkey today.

Connect Portkey freeSee pricing

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