Using Amazon Bedrock as an LLM Provider and Bedrock Guardrails with WSO2 AI Gateway
A full walkthrough registering Amazon Bedrock as a provider and attaching its native guardrail to a WSO2 AI Gateway, with both requests and responses validated.
OpenAPI for AI Agents: Write Specs Agents Can Use
Learn how to write OpenAPI specs that AI agents can use, with clear descriptions, unique operationIds, complete schemas, and agent metadata extensions.
Building and Managing an API Catalog
Learn what an API catalog is, how it differs from an API portal and an API registry, and how to build one that serves both developers and AI agents.
Multi-Step MCP Tools: How to Order API Calls with Arazzo
Learn how the Arazzo specification describes multi-step API workflows and how to turn one into a single MCP tool for AI agents, governed by the WSO2 AI Gateway.
WebSocket APIs: How to Build a Real-Time Notification System
Learn how to build a real-time notification system with WebSocket APIs. Import an AsyncAPI definition and deploy a WebSocket API proxy on WSO2 API Platform.
AI Gateway Guardrails for LLMs: Block Prompt Injection and Unsafe Requests
Block prompt injection and unsafe LLM requests before they reach the model. Chain content length, word count, regex, and semantic prompt guard on the WSO2 AI Gateway.
MCP Registry: How to Build a Governed Catalog for MCP Servers
Learn what an MCP registry is and how to build one. Publish MCP servers to a governed catalog with WSO2, then discover and connect to them from Claude Desktop.
Managing API Breaking Changes: Detect, Version, Deprecate
Learn how to catch breaking API changes with diff tooling, version them with semver, and communicate deprecations using sunset headers.
Self-Hosted LLM Gateway: Open-source options and how to deploy one
Why and how to run a self-hosted LLM gateway: open-source options, deployment (Docker/Kubernetes), data control, and SaaS vs self-hosted trade-offs.
MCP Server Authentication: OAuth 2.1 Guide
How MCP server authentication works: OAuth 2.1 with PKCE, token validation, the confused-deputy problem, and delegating auth to an identity provider. With examples.
PII Redaction for LLMs: How to Do It Right
How to redact PII before it reaches an LLM: detection with regex and NER, gateway-level filtering of prompts and responses, and compliance with GDPR, HIPAA, and PCI. Includes a complete, end-to-end WSO2 AI Workspace tutorial.
MCP Implementations: How to Implement MCP
A practical guide to MCP implementations: architecture, official SDKs, reference/example servers, a step-by-step build, and a hands-on walkthrough governing an existing server with WSO2 AI Workspace.
Semantic Caching for LLMs: Cut Cost & Latency
What semantic caching is, how it works (embeddings + similarity), and how it cuts LLM cost and latency, plus best practices and gateway-level implementation.
Govern write-capable MCP tools at the gateway in WSO2 API Platform
Secure write-capable MCP tools at the gateway using access control, scope authorization, rate limiting, and Moesif analytics.
Controlling Claude Code AI Costs Across a Large Engineering Team with the AI Gateway and AI Workspace
Route every developer's Claude Code traffic through the WSO2 AI Gateway so you can track, throttle, and cap AI spend for your whole engineering org from one dashboard.
The open, universal platform for managing every API and AI service at scale. 100% open source.