LibreAgent AI Server for AI Agent Services
@LibreAgent
LibreAgent AI Server for AI Agent Services について
LibreAgent AI Server is an Agentic Accessible Server for API communication with AI Service Providers and AI Services. It supports Google's new Agent 2 Agent (A2A) protocol as well as the MCP protocol. An API gateway is provided in the system for agentic ops.
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"a2ahub": {
"command": "docker",
"args": [
"run",
"-d",
"--name",
"mcpo-time",
"--network",
"a2ahub",
"-p",
"8001:8000",
"--rm",
"ghcr.io/open-webui/mcpo:main",
"--host",
"0.0.0.0",
"--port",
"8000",
"--",
"uvx",
"mcp-server-time"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is LibreAgent AI Server for AI Agent Services?
LibreAgent AI Server for AI Agent Services is a cloud‑native AI gateway built on Apache APISIX that routes traffic to AI agents, including private/public LLMs, MCP servers, and Google A2A agents. It is designed for developers and teams building scalable, secure AI agent infrastructure.
How to use LibreAgent AI Server for AI Agent Services?
Deploy via Docker using the provided docker-compose.yml (etcd, APISIX, APISIX Dashboard). Quick start: copy env.example to .env, then run docker-compose up -d. Manage routes via the APISIX Admin API (port 9180) or the APISIX Dashboard (port 9000).
Key features of LibreAgent AI Server for AI Agent Services
- Routes AI agent traffic to LLMs, MCPs, and A2A agents
- Built on Apache APISIX in traditional mode with etcd
- Supports event streaming (SSE, WebSockets)
- Includes APISIX Dashboard for configuration management
- Optional Keycloak OIDC authentication for the Dashboard
Use cases of LibreAgent AI Server for AI Agent Services
- Securely route requests to private LLMs behind a gateway
- Expose MCP tools via HTTP using the
mcpoproxy - Chain Google A2A agent workflows across multiple services
- Publish and monetize AI agent services with API management
FAQ from LibreAgent AI Server for AI Agent Services
What is the architecture?
LibreAgent AI Server for AI Agent Services uses Apache APISIX as the API gateway, etcd for configuration storage, and an AI Service Provider Router to forward traffic to upstream AI services.
What transports are supported?
The gateway supports SSE, WebSockets, and standard HTTP for agent communication.
How do I authenticate to the APISIX Dashboard?
By default, login with username admin and password admin. Optionally, you can enable Keycloak for OIDC‑based authentication by uncommenting the relevant blocks in docker-compose.yml and conf.yaml.
Where are configuration files stored?
They are local files mounted into Docker containers: apisix_conf/config.yaml for APISIX and apisix_dashboard_conf/conf.yaml for the Dashboard. The runtime configuration is persisted in etcd.
Does the server require a specific runtime environment?
Yes, it requires Docker and a shared Docker network (named a2ahub in the default setup). The provided docker-compose.yml launches all components (etcd, APISIX, Dashboard) as containers.
「AI とエージェント」の他のコンテンツ
MCP Manager for Claude Desktop
zueaisimple web ui to manage mcp (model context protocol) servers in the claude app
Open Multi-Agent Canvas
CopilotKitThe open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research
Just Prompt - A lightweight MCP server for LLM providers
dislerjust-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)
🛡️ A.I.G(AI-Infra-Guard)
TencentA full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
MCP Server - Remote MacOs Use
baryhuangThe only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App
コメント