What LLMs does MCP-X Agent support?
It supports ChatGPT, Anthropic, Ollama, and any OpenAI‑compatible model, provided the LLM has function calling capabilities.
@TimeCyber
基本情報
这是一个MCP客户端,让你轻松配置各个大模型,对接各种MCP Server而开发。This is an MCP client that allows you to easily configure various large models and develop interfaces with various MCP servers.
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": {
"MCP_SERVER_NAME": {
"enabled": true,
"transport": "sse",
"url": "YOUR_SSE_SERVER_URL"
}
}
}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。
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。
MCP-X Agent is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities. It is designed for users who want a unified interface to manage AI agents, knowledge bases, and MCP tools across Windows, macOS, and Linux.
Download the latest release from GitHub, then install the appropriate package for your OS. Windows users get pre‑installed Python and Node.js; macOS and Linux users must install those environments separately. After installation, manage agents via the sidebar, upload documents to the knowledge base, and add MCP servers by editing the JSON configuration in the MCP settings.
It supports ChatGPT, Anthropic, Ollama, and any OpenAI‑compatible model, provided the LLM has function calling capabilities.
Windows builds include Python and Node.js. macOS and Linux users need to install Python and Node.js (with npx and uvx) themselves.
Edit the MCP settings JSON to add a new `mcpServers` entry with either a local command (stdio) or an SSE URL. The README provides examples for Fetch, Filesystem, and YouTube‑dl.
Documents are uploaded into the application’s internal knowledge base, searchable by filename and content. The README does not specify the physical storage location.
Yes, it supports SSE (Server‑Sent Events) transport for external MCP servers. No authentication details are mentioned in the README.

1,000+ fully localized prompt templates across 40+ categories. Compare Mode — send the same prompt to up to 9 AI providers (ChatGPT, Claude, Gemini, Grok, Groq, Copilot, Mistral, Perplexity, DuckDuckGo AI) and compare an
Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.
Model Context Protocol (MCP) server for Hostinger API. If you don't want to install or run anything locally, connect directly to Hostinger's hosted MCP server: This opens a browser window to authorize via OAuth. Once app

Extract, search and tag any document — invoices, receipts, contracts, forms, or your own templates. 13 tools, one sign-in (OAuth 2.1) or API key, free FileTag tier, data residency in the EU, US, Israel or Asia.

Docs: https://botchelor.com/agents and https://botchelor.com/llms.txt . Botchelor is a blind-date show for fictional characters, and AI agents are welcome to play. Over MCP, your agent builds an original character in w
コメント