Azure API Management AI gateway
Microsoft
AI gateway policies in Azure API Management for LLM, MCP and A2A APIs: token limits, semantic caching, content safety and load balancing.
Gateways that route and govern LLM calls and agent access to MCP tools.
An AI gateway sits between applications and model providers to centralise keys, quotas, cost tracking, caching, and guardrails; an MCP gateway does the same for the tools agents call. Compare them on deployment ownership and license terms.
Tools from the major platform vendors are listed first; independent and open-source options follow below.
Microsoft
AI gateway policies in Azure API Management for LLM, MCP and A2A APIs: token limits, semantic caching, content safety and load balancing.
Cloudflare
Edge-hosted AI gateway adding analytics, logging, caching, rate limiting, model fallback, DLP and guardrails in front of LLM providers.
5 matching non-vendor tools in this filtered view.
Linux Foundation
Rust proxy for agent traffic that governs MCP, A2A and LLM calls with CEL-based RBAC, budgets and guardrails; runs standalone or on Kubernetes.
Docker
Open-source docker mcp CLI plugin that proxies MCP servers run in isolated containers, with central secrets, OAuth and call tracing.
Kong
AI and MCP governance layer on Kong Gateway: multi-LLM routing, semantic caching, prompt guards, PII redaction and MCP OAuth.
BerriAI
Self-hostable AI gateway and Python SDK that calls 100+ LLM APIs in OpenAI format with virtual keys, spend tracking and guardrails.
Portkey (Palo Alto Networks)
Open-source AI gateway that routes to 250+ LLMs with fallbacks, caching and 50+ guardrails; managed SaaS and private-cloud options.
agentgateway 1.5.0 added API-key-scoped LLM budgets, native Gemini APIs, and guardrails on tool calls, with breaking JWT and token-count changes.
SourceIt is a proxy between applications and model providers that centralises API keys, routing and fallback across models, rate limits and budgets, caching, logging, and guardrail checks, so every team does not reimplement them. Many now also expose or govern MCP tool traffic.
A gateway for the Model Context Protocol: agents connect to one endpoint, and the gateway decides which MCP servers and tools each agent may use, injects credentials, and logs every tool call. It is the control point for agent tool access in the same way an API gateway is for APIs.
If an API management platform is already the enterprise standard, its AI features keep one policy surface. Dedicated AI gateways usually move faster on model and provider support. Check licensing carefully: several open-source gateways keep enterprise features under a commercial license.
Compare the active category against the platform foundation layer, the cross-category updates feed, and the sourcing/contribution guide.
Review Microsoft Foundry, Amazon Bedrock, and Gemini Enterprise Agent Platform as the foundation layer behind this category.
Check the market-intelligence feed for high-impact moves, plus the expandable full log for releases, deprecations, acquisitions, and other notable changes.
See sourcing standards, contribution rules, and project scope before adding or updating tracked tools.