> ## Documentation Index > Fetch the complete documentation index at: https://docs.mka1.com/llms.txt > Use this file to discover all available pages before exploring further. # Update the cluster default guardrails > Replace the default guardrails enforced on every enrolled organization, and switch them on or off for the whole cluster. Organization admins can add rules on top of the cluster default but cannot weaken or remove it. Classifier models must be active in the cluster organization's registry; their calls run and are metered as the cluster organization, so tenants need no access to the model and their budgets are not charged. ## OpenAPI ````yaml https://apigw.mka1.com/speakeasy.json put /api/v1/llm/guardrails/cluster-default openapi: 3.1.1 info: title: MKA1 API version: 1.1.0 description: >- The MKA1 API is a RESTful API that provides access to the MKA1 platform. Learn how to get started with the API and the TypeScript SDK [here](https://mka1.apidocumentation.com/guides/getting-started). license: name: Proprietary servers: - url: https://apigw.mka1.com description: MKA1 API Gateway - url: / description: Relative server URL (configurable via SDK constructor) security: [] tags: - name: Resource Authorization description: >- Manage permissions for LLM resources. Create resources, grant/revoke permissions, and delete resources. Only resource owners can grant, revoke, or delete permissions. x-displayName: Resource Authorization - name: Embeddings description: >- Text embedding API endpoints for generating vector representations of text. Create semantic embeddings for search, clustering, and similarity matching using various embedding models. x-displayName: Embeddings - name: Feedback description: >- User feedback API for rating and commenting on chat completions. Collect thumbs up/down ratings and detailed feedback to improve model responses and track user satisfaction. x-displayName: Feedback - name: Images description: >- Image generation API endpoints for creating images from text descriptions. Generate images with control over size, quality, and style. x-displayName: Images - name: MCP Vault description: >- MCP vault API for storing user-owned MCP server configurations and encrypted credentials. Agents reference vault IDs so secrets are resolved only at tool execution time. x-displayName: MCP Vault - name: Speech description: >- Speech API endpoints for audio processing. Convert text to natural-sounding speech (TTS) or transcribe speech to text (STT) in different languages. x-displayName: Speech - name: Usage description: >- Usage tracking and analytics API for monitoring token consumption, request counts, and cost analysis. View detailed statistics per user, model, and time period. x-displayName: Usage - name: Extract description: >- Structured data extraction API for extracting information from files. Define JSON schemas to extract structured data from images, PDFs, and documents. Supports reusable schema templates. x-displayName: Extract - name: Text Classification description: >- Text classification API for categorizing text into predefined labels. Use AI models to classify text content for sentiment analysis, topic categorization, and content moderation. x-displayName: Text Classification - name: Responses description: >- Agent-powered responses API for creating AI agents with autonomous tool usage. Build conversational assistants that can use web search, file operations, image generation, code execution, and MCP integrations. Supports background processing, streaming, and real-time status tracking. x-displayName: Responses - name: Files description: >- File management API for uploading, storing, and managing files with automatic expiration and S3 integration. Upload files that can be used with Assistants, Vector Stores, and other features. Files are stored in S3 with metadata tracked in PostgreSQL. Supports automatic cleanup of expired files. x-displayName: Files - name: Vector Stores description: >- Vector store API for storing and searching documents using embeddings. Create vector stores, upload files with automatic chunking and embedding generation, and perform semantic search. Files are processed asynchronously using Temporal workflows for durability. Supports automatic cleanup of expired stores and LanceDB for efficient vector storage. x-displayName: Vector Stores - name: Conversations description: >- Conversation management API for storing and retrieving conversation state across Response API calls. Create conversations, add items (user messages, assistant messages, system messages), and maintain conversation history. Supports metadata tracking and multi-turn dialogue state management. x-displayName: Conversations - name: Guardrails description: >- AI safety guardrails API for configuring content moderation and security policies. Set up ban word lists, prompt injection detection, and system prompt leakage prevention. Guardrails apply to all requests from an account and can be tested before deployment. x-displayName: Guardrails - name: Models description: >- Model listing API for discovering available models. Returns model IDs, ownership, and metadata for all registered models in the gateway. x-displayName: Models - name: Skills description: >- Skills API for managing versioned bundles of instructions and files following the Agent Skills standard. Create, version, and download reusable skill packages that include SKILL.md manifests for agent environments. x-displayName: Skills - name: Chat Completions description: >- **Deprecated: Use the Responses API (`/api/v1/llm/responses`) instead.** Chat completion endpoints with support for streaming, tool calls, and multiple providers. x-deprecated: true x-displayName: Chat Completions - name: Batches x-displayName: Batches - name: Evals x-displayName: Evals - name: Fine-Tuning x-displayName: Fine-Tuning - name: Memory Stores x-displayName: Memory Stores - name: Prompts x-displayName: Prompts - name: API Key x-displayName: API Key - name: Session x-displayName: Session - name: Organization x-displayName: Organization - name: Cluster Admin x-displayName: Cluster Admin - name: Sessions description: Create, inspect, access, and terminate sandbox sessions. x-displayName: Sessions - name: Browser description: >- Connect to browser sessions through the gateway port proxy. Browser sessions expose a Chrome DevTools Protocol endpoint on port 9222. x-displayName: Browser - name: Execution description: Run shell commands and code inside an existing sandbox session. x-displayName: Execution - name: Workspace description: >- Inspect the workspace manifest, transfer files or archives, and download generated artifacts. x-displayName: Workspace - name: Sandbox Usage description: >- Aggregate sandbox usage statistics across sessions, execution, and workspace operations. x-displayName: Sandbox Usage - name: Sandbox Pricing description: >- Cluster-admin management of the sandbox compute rate card used for budgeted spend. x-displayName: Sandbox Pricing - name: Sandbox GitHub description: >- Connect a GitHub account, clone its repositories into sandbox sessions, and push branches and open pull requests from a session. The GitHub token stays in the sandbox service and never enters a session. x-displayName: Sandbox GitHub - name: Sandbox Environments description: >- Save reusable session configuration (repositories, environment variables, network access, and a setup script) and run the setup script in a session. x-displayName: Sandbox Environments - name: Sandbox Connectors description: >- Connect remote MCP servers (Linear, Notion, Sentry and others) to your account so Coding Harness sessions started from an environment that lists them can call their tools. The sandbox service keeps each connector's credential and never puts it in a session. x-displayName: Sandbox Connectors - name: Agents description: Create and manage reusable agent definitions. x-displayName: Agents - name: Agent Versions description: Inspect an agent's configuration history and roll back to a prior version. x-displayName: Agent Versions - name: Agent Runs description: Execute saved agents and inspect persisted run results. x-displayName: Agent Runs - name: Agent Connectors description: >- Connect saved agents to external messaging channels such as Telegram, including text, photo, and supported document exchange. x-displayName: Agent Connectors - name: Agent Schedules description: Create and manage scheduled or recurring saved agent runs. x-displayName: Agent Schedules - name: schema-4_other x-displayName: other - name: Billing x-displayName: Billing - name: Budgets x-displayName: Budgets - name: Settings x-displayName: Settings - name: Compute Jobs x-displayName: Compute Jobs - name: Compute Services x-displayName: Compute Services - name: Compute Catalog x-displayName: Compute Catalog - name: Compute Volumes x-displayName: Compute Volumes - name: Compute Pricing x-displayName: Compute Pricing - name: Compute Secrets x-displayName: Compute Secrets - name: Compute Usage x-displayName: Compute Usage - name: Compute Tenants x-displayName: Compute Tenants - description: Create, list, read, update, and delete repositories. name: Repositories x-displayName: Repositories - name: Tracking Experiments description: Create and query tenant experiments. x-displayName: Tracking Experiments - name: Tracking Runs description: Record and retrieve run parameters, metrics, and tags. x-displayName: Tracking Runs - name: analytics.projects x-displayName: Projects description: Create, list, rename, and archive analytics projects. - name: analytics.keys x-displayName: Capture keys description: Create and revoke project keys for sending events. - name: analytics x-displayName: Events description: Send events and query event counts or unique visitors. - name: analytics.events x-displayName: Event search description: List individual events with their properties, newest first. - name: analytics.visitors x-displayName: Visitor search description: List visitors by their latest activity, with first and last seen times. - name: generators x-displayName: generators - name: generations x-displayName: generations - name: formats x-displayName: formats - description: >- Flags, environments, evaluation, and the audit log. Administrative operations require a cluster administrator; evaluation uses an environment-specific evaluation key. name: Feature Flags x-displayName: Feature Flags paths: /api/v1/llm/guardrails/cluster-default: put: tags: - Guardrails summary: Update the cluster default guardrails description: >- Replace the default guardrails enforced on every enrolled organization, and switch them on or off for the whole cluster. Organization admins can add rules on top of the cluster default but cannot weaken or remove it. Classifier models must be active in the cluster organization's registry; their calls run and are metered as the cluster organization, so tenants need no access to the model and their budgets are not charged. operationId: updateClusterDefaultGuardrails requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/UpdateClusterDefaultGuardrailsRequest' example: enabled: true guardrails: - mode: prompt_injection enabled: true config: threshold: 0.7 - mode: leakage enabled: true config: threshold: 0.7 - mode: classifier enabled: true config: model: meetkai:custom-classifier prompt: >- Block content that expresses hate toward people based on a protected characteristic, threatens or glorifies violence, is sexually explicit or sexualizes minors, or encourages or instructs self-harm. Allow neutral educational, news, medical and support discussion of these topics. on_error: fail_closed rejection_message: >- This request is not allowed by your organization's content policy. responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/ClusterDefaultGuardrailsResponse' example: object: guardrails_cluster_default enabled: true guardrails: - mode: prompt_injection enabled: true config: threshold: 0.7 - mode: leakage enabled: true config: threshold: 0.7 - mode: classifier enabled: true config: model: meetkai:custom-classifier prompt: >- Block content that expresses hate toward people based on a protected characteristic, threatens or glorifies violence, is sexually explicit or sexualizes minors, or encourages or instructs self-harm. Allow neutral educational, news, medical and support discussion of these topics. on_error: fail_closed rejection_message: >- This request is not allowed by your organization's content policy. built_in: false settings_unreadable: false updated_by: user-cluster-admin-1 updated_at: '2026-10-16T12:00:00.000Z' security: - bearerAuth: [] x-codeSamples: - lang: python label: Python (SDK) source: |- from meetkai_mka1 import SDK with SDK( bearer_auth="", ) as sdk: res = sdk.guardrails.update_cluster_default_guardrails(enabled=True, guardrails=[ { "mode": "prompt_injection", "enabled": True, "config": { "threshold": 0.7, }, }, { "mode": "leakage", "enabled": True, "config": { "threshold": 0.7, }, }, { "mode": "classifier", "enabled": True, "config": { "model": "meetkai:custom-classifier", "prompt": "Block content that expresses hate toward people based on a protected characteristic, threatens or glorifies violence, is sexually explicit or sexualizes minors, or encourages or instructs self-harm. Allow neutral educational, news, medical and support discussion of these topics.", "on_error": "fail_closed", "rejection_message": "This request is not allowed by your organization's content policy.", }, }, ]) # Handle response print(res) - lang: typescript label: Typescript (SDK) source: |- import { SDK } from "@meetkai/mka1"; const sdk = new SDK({ bearerAuth: "", }); async function run() { const result = await sdk.guardrails.updateClusterDefaultGuardrails({ enabled: true, guardrails: [ { mode: "prompt_injection", enabled: true, config: { threshold: 0.7, }, }, { mode: "leakage", enabled: true, config: { threshold: 0.7, }, }, { mode: "classifier", enabled: true, config: { model: "meetkai:custom-classifier", prompt: "Block content that expresses hate toward people based on a protected characteristic, threatens or glorifies violence, is sexually explicit or sexualizes minors, or encourages or instructs self-harm. Allow neutral educational, news, medical and support discussion of these topics.", onError: "fail_closed", rejectionMessage: "This request is not allowed by your organization's content policy.", }, }, ], }); console.log(result); } run(); - lang: csharp label: CSharp (SDK) source: >- using MeetKai.MKA1; using MeetKai.MKA1.Types.Components; using System.Collections.Generic; var sdk = new SDK(bearerAuth: ""); UpdateClusterDefaultGuardrailsRequest req = new UpdateClusterDefaultGuardrailsRequest() { Enabled = true, Guardrails = new List() { GuardrailConfig.CreatePromptInjection( new PromptInjectionGuardrail() { Config = new PromptInjectionConfig() {}, } ), GuardrailConfig.CreateLeakage( new LeakageGuardrail() { Config = new LeakageConfig() {}, } ), GuardrailConfig.CreateClassifier( new ClassifierGuardrail() { Config = new ClassifierConfig() { Model = "meetkai:custom-classifier", Prompt = "Block content that expresses hate toward people based on a protected characteristic, threatens or glorifies violence, is sexually explicit or sexualizes minors, or encourages or instructs self-harm. Allow neutral educational, news, medical and support discussion of these topics.", }, } ), }, }; var res = await sdk.Guardrails.UpdateClusterDefaultGuardrailsAsync(req); // handle response components: schemas: UpdateClusterDefaultGuardrailsRequest: type: object properties: enabled: type: boolean description: >- Cluster switch. When false, the cluster default applies to no organization. guardrails: type: array items: $ref: '#/components/schemas/GuardrailConfig' description: >- Guardrails enforced on every enrolled organization. Classifier models are resolved in the cluster organization's registry and metered to it. required: - enabled - guardrails ClusterDefaultGuardrailsResponse: type: object properties: object: const: guardrails_cluster_default enabled: type: boolean description: >- Cluster switch. When false, the cluster default applies to no organization. guardrails: type: array items: $ref: '#/components/schemas/GuardrailConfig' description: Guardrails enforced on every enrolled organization built_in: type: boolean description: >- True while the cluster runs the built-in default (prompt injection and leakage detection) because no operator has saved one settings_unreadable: type: boolean description: >- True when the saved cluster default cannot be read: the built-in rules shown here are enforced in its place. Save a policy to replace it; do not save these rules back unless that is intended updated_by: anyOf: - type: string - type: 'null' description: >- User who last changed the cluster default; null while the built-in default applies updated_at: anyOf: - type: string format: date-time - type: 'null' description: >- When the cluster default was last changed; null while the built-in default applies required: - object - enabled - guardrails - built_in - settings_unreadable - updated_by - updated_at GuardrailConfig: anyOf: - $ref: '#/components/schemas/BanWordsGuardrail' - $ref: '#/components/schemas/PromptInjectionGuardrail' - $ref: '#/components/schemas/LeakageGuardrail' - $ref: '#/components/schemas/ClassifierGuardrail' discriminator: propertyName: mode mapping: ban_words: '#/components/schemas/BanWordsGuardrail' prompt_injection: '#/components/schemas/PromptInjectionGuardrail' leakage: '#/components/schemas/LeakageGuardrail' classifier: '#/components/schemas/ClassifierGuardrail' BanWordsGuardrail: type: object properties: mode: const: ban_words enabled: type: boolean default: true description: Whether this guardrail is enabled check_output: type: boolean description: Also apply this guardrail to model output, not just the request config: $ref: '#/components/schemas/BanWordsConfig' description: Banned words configuration required: - mode description: Banned words guardrail PromptInjectionGuardrail: type: object properties: mode: const: prompt_injection enabled: type: boolean default: true description: Whether this guardrail is enabled check_output: type: boolean description: Also apply this guardrail to model output, not just the request config: $ref: '#/components/schemas/PromptInjectionConfig' description: Prompt injection configuration required: - mode description: Prompt injection guardrail LeakageGuardrail: type: object properties: mode: const: leakage enabled: type: boolean default: true description: Whether this guardrail is enabled check_output: type: boolean description: Also apply this guardrail to model output, not just the request config: $ref: '#/components/schemas/LeakageConfig' description: Leakage configuration required: - mode description: Leakage guardrail ClassifierGuardrail: type: object properties: mode: const: classifier enabled: type: boolean default: true description: Whether this guardrail is enabled check_output: type: boolean description: Also apply this guardrail to model output, not just the request config: $ref: '#/components/schemas/ClassifierConfig' required: - mode - config BanWordsConfig: type: object properties: words: type: array items: type: string default: [] description: List of banned words or phrases rejection_message: type: string default: >- I'm sorry, but I can't process this request as it contains content that isn't allowed. Please rephrase your message. description: The message to return when this guardrail is triggered description: Configuration for banned words guardrail PromptInjectionConfig: type: object properties: threshold: type: number minimum: 0 maximum: 1 default: 0.7 description: Detection threshold (0-1) rejection_message: type: string default: >- I'm sorry, but I can't process this request. Please rephrase your message in a different way. description: The message to return when this guardrail is triggered description: Configuration for prompt injection detection guardrail LeakageConfig: type: object properties: threshold: type: number minimum: 0 maximum: 1 default: 0.7 description: Detection threshold (0-1) rejection_message: type: string default: >- I'm sorry, but I can't help with that type of request. Please ask me something else. description: The message to return when this guardrail is triggered description: Configuration for system prompt leakage detection guardrail ClassifierConfig: type: object properties: model: type: string minLength: 1 description: Exact model ID available in the caller's organization registry prompt: type: string minLength: 1 maxLength: 16000 description: >- Instructions defining when to block or allow content; content is supplied separately on_error: enum: - fail_closed - fail_open type: string default: fail_closed description: Stop the request or skip this classifier when evaluation fails rejection_message: type: string default: This request is not allowed by your organization's content policy. description: Message returned when classification blocks content required: - model - prompt securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key description: >- Gateway auth: send `Authorization: Bearer `. For multi-user server-side integrations, you can also send `X-On-Behalf-Of: `. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.