How does Hebline decide which service to use?
It uses a weighted scoring engine that considers cost, latency, and service scores. Free services are preferred when constraints allow.
@Hebline
基本情報
Intelligent API routing and cost-visibility layer for AI agents via MCP
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": {
"hebline": {
"command": "npx",
"args": [
"-y",
"-p",
"@hebline.ai/mcp-server",
"hebline-mcp"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
Hebline MCP Server is an API routing broker that connects AI agents to the best available API services—free or paid—based on cost, latency, and capability. It abstracts away provider selection, routes free services first, and logs all calls for transparency.
Install the package globally (npm install -g @hebline.ai/mcp-server) or add it to your MCP client configuration (e.g., Claude Desktop, Cursor, VS Code) via the provided JSON config. Then, use MCP tools like execute, compare, or categories to route API calls. Optionally set environment variables for paid API keys.
It uses a weighted scoring engine that considers cost, latency, and service scores. Free services are preferred when constraints allow.
No problem—Hebline routes to free alternatives automatically. Paid services are excluded from routing unless keys are provided.
Call metadata (timestamp, capability, service, latency, cost) is logged to `~/.hebline/calls.jsonl`. No API call content is stored.
Yes. Only anonymized metadata is logged. A self-hosted option is available for zero data leaving your network.
Currently, stdio transport is supported. SSE transport is on the roadmap. No authentication is required for the open-source server.
Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app

Multi-zone MCP server for GKE/EKS/AKS: Python tools from git, NeMo guardrails, SSO, autoscaling.
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

コメント