184 docs tagged with "cloud"

Attach, configure, and deploy policies on API proxies running on the API Platform Self-Hosted Gateway.

Add supporting documentation, usage guides, and version history to an API proxy before publishing it to the Developer Portal.

Configure PII masking on AI API proxies in WSO2 API Platform using a Guardrails AI fine-tuned model to detect and mask sensitive data.

Expose published APIs and workflows through llms.txt and machine-readable Markdown endpoints so AI agents can discover and invoke them.

Connect AI service providers like OpenAI, Azure OpenAI, Anthropic, Mistral, and AWS Bedrock as API proxies in WSO2 API Platform AI Gateway.

Create an AI Gateway and configure an LLM provider through the AI Workspace UI, then send your first request through the gateway.

Create an AI Gateway and connect an MCP proxy through the AI Workspace UI, then reach it from an MCP client.

Route, secure, and observe LLM and MCP traffic through the AI Gateway, deployable standalone or managed by the AI Workspace control plane.

Overview of basic, advanced, and third-party AI guardrails available in WSO2 API Platform to secure and govern AI API proxies.

Detect unsafe content, mask sensitive data, and enforce content limits on LLM traffic using guardrails configured in AI Workspace.

Centrally manage AI Gateway runtimes, LLM providers, App LLM proxies, MCP proxies, and AI policies from the AI Workspace control plane.

Apply built-in guardrail, rate-limiting, and traffic-management policies to LLM providers and App LLM proxies in AI Workspace.

Control which request and response headers are included in AI Gateway analytics data using allow or deny modes.

Understand WSO2 API Platform's governance concepts: rulesets, policies, and documents for enforcing API compliance at scale.

Browse, filter, and deploy sample API proxies to explore core API Platform functionality.

Check the real-time operational health, active incidents, and scheduled maintenance for WSO2 API Platform Cloud.

Manage the lifecycle states of an API proxy in WSO2 API Platform: created, pre-released, published, deprecated, and retired.

Reference for WSO2 API Platform inbuilt API- and resource-level mediation policies: OAuth2, rate limiting, CORS, and payload transforms.

Add an application-facing endpoint on top of an LLM provider for app- or agent-specific authentication, guardrails, and access controls.

Sync a custom policy from your Self-Hosted Gateway to your organization and apply it to API proxies.

Apply access control, authorization, and rewrite policies to MCP proxies using the Policy Hub.

Assign existing subscription plans to an API proxy in WSO2 API Platform to control access levels and pricing tiers for consumers.

Attach, rearrange, and refresh mediation policies on API proxies in WSO2 API Platform, and implement custom policies as Ballerina projects.

View organization-level audit logs and grant other members access to audit log data in API Platform.

Validate LLM request and response content against AWS Bedrock Guardrails for content filtering, topic detection, and PII masking.

Integrate AWS Bedrock Guardrails with AI API proxies in WSO2 API Platform for real-time content safety validation and PII protection.

Integrate Azure Content Safety with AI API proxies in WSO2 API Platform to filter hate speech, sexual content, self-harm, and violence.

Moderate LLM content with Azure Content Safety, detecting hate speech, sexual content, self-harm, and violence with configurable severity thresholds.

Filter hate speech, sexual content, self-harm, and violence in LLM traffic using Azure Content Safety, configured in AI Workspace.

Explore MCP servers registered in your organization's MCP Hub and view their tools, resources, and prompts.

Install the AP CLI, configure build.yaml, and build a custom Self-Hosted Gateway image that includes your custom policies.

Monitor governance policy compliance and run AI compliance analysis for your API proxies, projects, and organization.

Add a custom domain for your organization and use it to configure custom URLs for your API proxies.

Integrate any OIDC/OAuth2-compliant identity provider with API Platform as a custom external key manager.

Create an App LLM proxy, optionally attach guardrails, and deploy it to a gateway.

Add an LLM provider in AI Workspace, configure authentication and guardrails, and deploy it to an AI Gateway.

Create an MCP proxy from an upstream MCP server URL and deploy it to a gateway.

Connect your Asgardeo identity provider to API Platform and the Developer Portal to manage API access control with scopes.

Connect Microsoft Azure Active Directory (Azure AD) to API Platform and the Developer Portal to manage API access control with scopes.

Enable enterprise login and role-based access control so users from an external identity provider can sign in to API Platform.

Control where and under what name client applications send their API key when calling a deployed LLM provider or App LLM proxy.

Give AI agents portal-level context, conventions, and recommended workflows by publishing LLM instructions to llms.txt.

Use a Tailscale-powered forward proxy to securely connect API Platform cloud data plane projects to your private networks.

Set up approval processes for environment promotion and URL customization workflows in API Platform.

Generate an API key for a subscribed API and use it to authenticate requests in the api-key header.

Generate an OAuth2 access token from an application's consumer key and secret, then use it to invoke a subscribed API.

Discover and follow published API workflows as a developer or AI agent using the Developer Portal UI, llms.txt, and Arazzo specifications.

Validate the byte length of LLM request or response content against configurable minimum and maximum thresholds.

Configure a content-length guardrail on AI API proxies in WSO2 API Platform to enforce minimum and maximum byte-size limits on content.

Create an application in the Developer Portal to subscribe to APIs and generate access credentials.

Create and deploy an API proxy for the Anthropic Claude provider in WSO2 API Platform, configure backend authentication, and publish it.

Create and deploy an API proxy for the AWS Bedrock provider in WSO2 API Platform, configure backend authentication, and publish it.

Create and deploy an API proxy for the Azure OpenAI provider in WSO2 API Platform, configure backend authentication, and publish it.

Create and deploy an API proxy for the Mistral AI provider in WSO2 API Platform, configure backend authentication, and publish it.

Create and deploy an API proxy for the OpenAI provider in WSO2 API Platform, configure backend authentication, and publish it for consumers.

Create and publish an API proxy for a third-party API available in the WSO2 API Platform Marketplace.

Learn the ways to create an API proxy in WSO2 API Platform: front your own APIs (ingress) or third-party APIs (egress) using several methods.

Define rate limits, burst control, and pricing models for organization-level API subscription plans in API Platform.

Create a GraphQL API proxy from an endpoint URL in WSO2 API Platform using schema introspection, then configure, deploy, and test it.

Create a REST API proxy by specifying a backend endpoint URL directly in WSO2 API Platform, then configure, deploy, and test it.

Create and auto-build a REST API proxy from a GitHub repository using a component.yaml file in WSO2 API Platform.

Create a REST API proxy from scratch by manually specifying API proxy details in WSO2 API Platform, then configure, deploy, and test it.

Create a REST API proxy using GenAI prompts in WSO2 API Platform, then configure, deploy, test, and publish it to the Developer Portal.

Create a WebSocket API proxy by specifying a backend endpoint URL directly in WSO2 API Platform, then configure, deploy, and test it.

Create a WebSocket API proxy from scratch by manually specifying API proxy details in WSO2 API Platform, then configure, deploy, and test it.

Create a WebSocket API proxy using GenAI prompts in WSO2 API Platform, then configure, deploy, test, and publish it to the Developer Portal.

Switch the WSO2 API Platform Developer Portal to MCP Hub mode for a streamlined, MCP-only browsing and theming experience.

Override Developer Portal CSS and customize the API landing page content for a specific API.

Manually customize Developer Portal colors, typography, HTML, CSS, and logo at the organization level.

Learn about API Platform's control plane and data plane architecture, including cloud and private data plane deployment models.

Customize an API proxy in WSO2 API Platform's interactive UI: add or remove resources, map resources, and manage policies.

Create an MCP Server from an HTTP backend or existing API proxy in WSO2 API Platform, customize tools, test, and publish it.

Configure the Developer Portal to show API proxies only, MCP servers only, or both, using API Portal, MCP Hub, and API & MCP Portal modes.

Connect an AWS API Gateway account to API Platform and federate discovered REST APIs into your organization.

Learn how the Event Gateway performs protocol mediation between web-friendly protocols and message brokers such as Kafka, MQTT, and Solace.

Create, deploy, test, promote, and publish an API proxy in API Platform, then invoke it from the Developer Portal.

Discover, govern, and publish APIs deployed on external gateways through API Platform's unified control plane.

Collect and visualize AI Gateway component logs using the demonstration Fluent Bit, OpenSearch, and OpenSearch Dashboards stack, or your own logging solution.

Configure distributed tracing for AI Gateway components using OpenTelemetry and the demonstration Jaeger stack, or export to your own OTLP backend.

Group API keys under a named GenAI application for application-level usage visibility, analytics, and governance.

Generate a custom SDK and sample application code from your subscribed APIs using AI-assisted SDK generation in the Developer Portal.

Create an AI Gateway, configure an LLM provider, and deploy it through the AI Workspace control plane.

Connect an AI Gateway to AI Workspace, configure an LLM provider and an MCP proxy, and call both through the AI Gateway.

Create an Event Gateway in the API Platform Console, deploy a WebSub API proxy, and test it end to end.

Set up an API Platform Self-Hosted Gateway in your own infrastructure and connect it to the API Platform Cloud control plane.

Create rulesets and policies, upload governance documents, and monitor API proxy compliance in WSO2 API Platform.

Deploy multiple Gateway Controller and Gateway Runtime replicas with a shared PostgreSQL database for high availability.

Create a GraphQL API proxy by importing a schema definition URL in WSO2 API Platform, then configure, deploy, test, and publish it.

Create a REST API proxy by importing an OpenAPI contract URL in WSO2 API Platform, then configure, deploy, test, and publish it.

Create an API proxy for a third-party API not in the WSO2 API Platform Marketplace by importing its API contract.

Create a WebSocket API proxy by importing an AsyncAPI contract URL in WSO2 API Platform, then configure, deploy, and test it.

Monitor API, LLM, and MCP traffic, errors, and platform health using the Insights dashboards in API Platform.

Connect your API Platform organization to Moesif to generate an API key, configure the integration, and view usage insights on the Moesif dashboard.

Call a deployed LLM provider or App LLM proxy using the OpenAI, Anthropic, Gemini, Mistral, Azure OpenAI, or LangChain SDKs.

Validate LLM request or response JSON payloads against a JSON Schema Draft 7 definition.

Calculate the USD cost of each LLM call from token usage and pricing tier, for use with LLM cost-based rate limiting.

Enforce monetary spending budgets on LLM traffic using the cost calculated by the LLM Cost policy.

Use built-in LLM provider templates for OpenAI, Azure OpenAI, Anthropic, Gemini, Mistral AI, AWS Bedrock, and Azure AI Foundry, or create custom templates.

Connect AI service platforms such as OpenAI, Anthropic, Azure OpenAI, Gemini, and Mistral AI as reusable LLM providers in AI Workspace.

View runtime and audit logs in API Platform to monitor API proxy activity and user actions while preserving data privacy.

Write clear descriptions, structure OpenAPI specs, add documents, and control agent visibility so AI agents can discover and use your API.

Configure provider settings, resources, security, and guardrails for a deployed App LLM proxy, then save, redeploy, or delete it.

Configure connection, access control, security, rate limiting, guardrails, and models for a deployed LLM provider, then redeploy or delete it.

Move an API proxy through its lifecycle states on the Event Gateway: created, pre-released, published, deprecated, and retired.

Move an API proxy through its lifecycle states on the Self-Hosted Gateway: created, pre-released, published, deprecated, and retired.

Create, edit, publish, and control the visibility of API workflows for human users and AI agents.

Create, edit, and assign continuous deployment pipelines to control the environment promotion order for your projects.

Create and delete development and production environments for your organization's data planes in API Platform.

Control access to MCP tools, resources, and prompts using an allow/deny mode with exceptions.

Secure MCP server traffic by validating JWT access tokens and serving protected resource metadata.

Define fine-grained authorization rules for MCP tools, resources, prompts, and methods based on JWT claims and scopes.

Connect the AI Gateway to upstream MCP servers and apply security, policy, and observability controls through an MCP proxy.

Expose user-facing names for MCP tools, resources, and prompts while mapping them to different backend capability names.

Learn how WSO2 API Platform turns existing APIs into MCP servers with a centralized control plane, tool generation, and OAuth2 security.

Distribute LLM requests evenly across multiple AI models in a cyclic pattern, with automatic suspension of failing models.

Distribute LLM requests across multiple models in round-robin order, with automatic suspension of failing models, configured in AI Workspace.

Distribute LLM requests across AI models proportionally by weight, giving higher-capacity models a larger share of traffic.

Capture and publish AI Gateway API request and response data to Moesif for observability and business insights.

Understand organizations in API Platform: structure, groups, roles, and how to find your Organization ID and Handle.

Mask or redact personally identifiable information in LLM request and response content using configurable regex patterns.

Detect and mask personally identifiable information in LLM requests and responses using regex patterns, configured in AI Workspace.

Understand projects in API Platform: structure, components, and how components are deployed within a project's namespace.

Prepend or append custom text or system messages to LLM prompts before they reach the upstream AI provider.

Prepend or append system instructions or context to every LLM request, configured in AI Workspace.

Replace template:// URI patterns in LLM payloads with predefined, parameterized prompt templates.

Apply reusable, parameterized prompt templates to LLM requests using template:// references, configured in AI Workspace.

Secure and manage an existing remote MCP server by proxying it through WSO2 API Platform with rate limiting and tool management.

Compare subscription-based and subscription-less approaches for publishing APIs deployed on the Event Gateway.

Compare subscription-based and subscription-less approaches for publishing APIs deployed on the API Platform Self-Hosted Gateway.

Publish a deployed MCP proxy from AI Workspace to make it discoverable through the MCP Hub and MCP Registry API.

Assign subscription plans, attach the Subscription Validation policy, and publish a subscription-based API on the Event Gateway.

Assign subscription plans, attach the Subscription Validation policy, and publish a subscription-based API on the Self-Hosted Gateway.

Publish an API on the Event Gateway without subscription plans so consumers can invoke it without subscribing.

Publish an API on the Self-Hosted Gateway without subscription plans so consumers can invoke it without subscribing.

Expose a service as an API proxy with WSO2 API Platform and publish it to the Developer Portal for application developers to consume.

Create an MCP Server from an API contract, test it in the MCP Playground, and publish it for AI agents to discover and consume with WSO2 API Platform.

Validate LLM request or response content against regular expression patterns to enforce formats or block prohibited content.

Configure a regex-based guardrail on AI API proxies in WSO2 API Platform to validate or block payload content using configurable patterns.

Configure a regex-based PII masking guardrail on AI API proxies in WSO2 API Platform to detect and mask sensitive data using custom patterns.

View and respond to pending workflow approval requests assigned to you as an authorized reviewer.

Access and search application, gateway, and system logs for your API proxies using text and regex-based filters.

Search published APIs in the Developer Portal by name, type, version, or description.

Implement RBAC for an API proxy by defining permissions, roles, and groups, then verify scope-based access with Asgardeo.

Configure WSO2 API Platform to authenticate API requests through a custom external key manager, then test the secured API.

Authenticate API invocations using WSO2 API Platform's built-in Secure Token Service (STS) for client credential-based access.

Configure WSO2 API Platform to authenticate API requests through Asgardeo as an external key manager, then test the secured API.

Configure WSO2 API Platform to authenticate API requests through Microsoft Azure AD as an external key manager with scoped access.

Configure mutual TLS between the WSO2 API Platform Gateway and your backend by exchanging client and server certificates.

Configure the Outbound OAuth2 policy so the WSO2 API Platform Gateway obtains and forwards access tokens to your backend.

Learn how the Self-Hosted Gateway connects to the API Platform control plane through the Gateway Controller and Gateway Runtime components.

Cache LLM responses using vector embeddings and cosine similarity to serve semantically similar future requests without calling the upstream LLM.

Cache LLM responses using vector similarity search to reduce cost and latency for semantically similar requests.

Configure semantic caching on AI API proxies in WSO2 API Platform to reuse responses to similar requests and reduce latency and cost.

Block or allow LLM prompts using semantic similarity matching against configured allow and deny phrase lists.

Dynamically filter the tools in an LLM request based on their semantic relevance to the user query to reduce tokens and improve response quality.

Validate the sentence count of LLM request or response content against configurable minimum and maximum thresholds.

Configure a sentence-count guardrail on AI API proxies in WSO2 API Platform to enforce minimum and maximum sentence limits on content.

Enforce minimum and maximum sentence count limits on LLM prompts or responses, configured in AI Workspace.

Register an AI Gateway in AI Workspace, connect the runtime with a registration token, and manage existing gateways.

Deploy the API Platform Event Gateway in production using a virtual machine, Docker, or Kubernetes.

Deploy the API Platform Self-Hosted Gateway in production using a virtual machine, Docker, or Kubernetes.

Request approval to promote an API proxy or configure a custom URL when a workflow approval is required.

Subscribe an application to a published API in the Developer Portal to generate credentials and invoke the API.

Test REST API proxies in WSO2 API Platform using natural-language queries via API Chat, without writing JSON payloads or scripts.

Generate a ready-to-use cURL command for an API proxy method in WSO2 API Platform to test it from any cURL client.

Test GraphQL API proxy operations in WSO2 API Platform using the built-in GraphQL Console with auto-generated test keys.

Test REST API proxy endpoints in WSO2 API Platform using the built-in OpenAPI Console with auto-generated test keys.

Test WebSocket API proxy endpoints in WSO2 API Platform using the built-in WebSocket Console with auto-generated test keys.

Generate a Developer Portal theme automatically from your organization's website using AI-powered branding.

Limit LLM traffic by prompt, completion, or total token consumption within a configurable time window.

Configure token-based rate limiting on AI API proxies in WSO2 API Platform to control usage and cost per prompt, completion, and total tokens.

Diagnose and resolve common Event Gateway issues, including connection failures, registration errors, TLS problems, and performance issues.

Validate URLs in LLM request or response content by checking reachability via DNS resolution or HTTP HEAD requests.

Configure a URL guardrail on AI API proxies in WSO2 API Platform to validate embedded URLs via DNS lookup or connection checks.

Query the public MCP Registry API to list MCP servers, server versions, and connection details for your organization.

View endpoint, schema, security, and base URL details for a published API's documentation in the Developer Portal.

Reference for WebSocket API proxy limits in WSO2 API Platform: maximum connections, maximum connection duration, and idle timeout.

Understand how the API Platform MCP registry catalogs published MCP proxies and surfaces them through the MCP Hub and MCP Registry API.

AI-native SaaS solution for full-lifecycle API management: design, secure, govern, and monitor APIs across hybrid and multi-cloud environments.

Validate the word count of LLM request or response content against configurable minimum and maximum thresholds.

Configure a word-count guardrail on AI API proxies in WSO2 API Platform to enforce minimum and maximum word limits on payload content.

Enforce minimum and maximum word count limits on LLM prompts or responses, configured in AI Workspace.

Build a custom policy for the API Platform Self-Hosted Gateway using the Go-based policy SDK, including streaming support.

Implement a custom AI policy that handles both streaming (SSE) and non-streaming LLM request and response bodies.