Omnicall
@ColinHughes2121
Omnicall について
Omnicall is a keyless, pay-per-call AI gateway for agents and OpenClaw. One OpenAI-compatible endpoint gives access to 248 LLMs (GPT, Claude, Gemini, Grok, DeepSeek, Llama, Qwen, Mistral) plus image, video, voice and music generation, and live crypto, DeFi, markets, web-search an
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": {
"omnicall": {
"command": "npx",
"args": [
"-y",
"omnicall-mcp"
]
}
}
}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 Omnicall?
Omnicall is an MCP server that provides agents with access to 248 LLMs (GPT, Claude, Gemini, Grok, DeepSeek, Llama, Qwen, Mistral) plus image, video, voice, and music generation, live crypto / DEX / DeFi / prediction-market data, web search, multi-platform research, X profiles, and on-chain reads — all through a single keyless endpoint. It is designed for developers using Claude Code, Cursor, Cline, Claude Desktop, or any MCP client.
How to use Omnicall?
Install Omnicall with a single command: for Claude Code, run claude mcp add omnicall npx -y omnicall-mcp. For Cursor, Cline, Claude Desktop, or Windsurf, add the corresponding JSON entry to your MCP config. Once installed, call the free list_endpoints tool to see all available tools. No API key or subscription is required; you pay per call in USDC on Base or Solana via x402, or pass a funded gck_ credit key.
Key features of Omnicall
- 248 models — access every major frontier LLM in one connection
- Keyless & pay-per-call — pay USDC on Base or Solana, no account or monthly fee
- Beyond LLMs — generate images, video, voice, and music from the same endpoint
- Live crypto & DeFi data — includes DEX, prediction markets, and on-chain reads
- Web search & multi-platform research — built-in for agent workflows
- Free tier available — try before funding any balance
Use cases of Omnicall
- Build an AI agent that seamlessly switches between 248 different LLMs for varied tasks
- Generate images, video, or music alongside text responses in a single conversation
- Access live cryptocurrency prices, DeFi positions, and prediction-market odds without extra APIs
- Perform multi-platform research and web searches directly within an MCP client
- Create an agent that reads on-chain data and X profiles in one unified interface
FAQ from Omnicall
Do I need an API key or signup to use Omnicall?
No. Omnicall is keyless — you pay per call in USDC on Base or Solana via x402, or you can pass a funded gck_ credit key. There is no signup or subscription.
How do I pay for usage?
Pay per call in USDC on Base or Solana using the x402 protocol. A free tier is available to try the service without funding anything.
What tools are available after installation?
Call the free list_endpoints tool to see every Omnicall tool your agent has access to.
What runtime does Omnicall require?
Omnicall is distributed as an npm package. To install it you need Node.js (the npx command). The README does not specify a minimum Node version.
Where does data live, and what transports does Omnicall use?
Data is processed on Omnicall’s servers. The server uses a remote MCP transport (built on mcp-remote). The endpoint URL can be overridden via the OMNICALL_MCP_URL environment variable (default https://omnicall.gocreativeai.com/mcp).
「AI とエージェント」の他のコンテンツ
LinkedIn MCP Server
stickerdanielOpen-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.
21st.dev Magic AI Agent
21st-devIt's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic
mcp-hfspace MCP Server 🤗
evalstateMCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.
Perplexity Ask MCP Server
ppl-aiThe official MCP server implementation for the Perplexity API Platform
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
コメント