agentgateway
Next Generation Agentic Proxy for AI Agents and MCP servers
Agentgateway is an open-source proxy server built on AI-native protocols including MCP (Model Context Protocol) that provides connectivity infrastructure for agentic AI systems. It functions as a unified gateway handling agent-to-LLM, agent-to-tool, and agent-to-agent communication with built-in security, observability, and governance features. The platform supports multiple protocols including MCP and A2A, offering tool federation, multiple transport options (stdio, HTTP, SSE), and integration with major LLM providers through an OpenAI-compatible API.
Key Features
Use Cases
- 01Routing AI agent requests to multiple LLM providers with automatic failover and load balancing
- 02Connecting language models to external tools and data sources via MCP protocol
- 03Implementing content filtering and safety guardrails across agent interactions
- 04Monitoring and observing agent-to-tool communication with detailed telemetry
- 05Enabling secure communication between multiple AI agents using A2A protocol
- 06Managing budget controls and spend limits across LLM API usage
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
agentgateway — FAQ
What is agentgateway MCP server?+
Agentgateway is a proxy server that implements the Model Context Protocol (MCP) to provide connectivity between AI agents, LLMs, and external tools. It acts as a gateway offering security, observability, and governance for agentic AI systems across multiple protocols including MCP and A2A.
How do I install agentgateway?+
Agentgateway can be deployed standalone using YAML configuration files or on Kubernetes using the built-in controller and Gateway API. For standalone deployment, follow the quickstart guide at agentgateway.dev/docs/standalone/latest/quickstart to get started in minutes.
Which AI clients work with agentgateway?+
Agentgateway works with any client that supports MCP protocol or the OpenAI-compatible API format. It can route requests to major LLM providers including OpenAI, Anthropic, Gemini, and AWS Bedrock.
Do I need API keys to use agentgateway?+
You'll need API keys for the specific LLM providers you want to route traffic to (OpenAI, Anthropic, etc.). Agentgateway itself supports multiple authentication methods including JWT, API keys, and OAuth for securing access to the gateway.
Is agentgateway free and open source?+
Yes, agentgateway is open source and licensed under Apache 2.0. It's a Linux Foundation project and available for free on GitHub.
What transport protocols does the MCP Gateway support?+
The MCP Gateway in agentgateway supports stdio, HTTP, SSE (Server-Sent Events), and Streamable HTTP transports. It also includes OpenAPI integration and OAuth authentication for connecting to external tools.
How do I install agentgateway?+
Open the source repository on GitHub and follow its README. agentgateway is a mcp server — MCP Agents Market links you directly to the official repo.
Is agentgateway free?+
agentgateway is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.