What dependencies does ollama-mcpo-adapter require?
Python 3.8+ and the `ollama` Python package for sending tool-calling requests.
@tappi287
基本信息
Adapter to expose MCPO, the MCP-to-OpenAPI proxy server, tools in Ollama-compatible format
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"ollama-mcpo-adapter": {
"command": "uvx",
"args": [
"mcpo",
"--port",
"5090",
"--config",
"/path/to/mcp_config.json"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
ollama-mcpo-adapter is a Python package that connects to a MCPO (MCP-to-OpenAPI proxy) server and lists its exposed MCP tools as Ollama-compatible function definitions, enabling tool calling from Ollama models.
Install with pip install ollama-mcpo-adapter. Then create an OllamaMCPOAdapter instance pointing to a running MCPO server (or launch one with MCPOService) and call list_tools_ollama() to get tool definitions. Pass these tools to an Ollama chat request and use call_tools_from_response() to execute tool calls.
MCPOServiceWIN_NODEJS_NPX_PATH environment variablePython 3.8+ and the `ollama` Python package for sending tool-calling requests.
You provide the MCP config as a JSON dictionary or file path when using `MCPOService`; the `OllamaMCPOAdapter` also accepts an optional `config_path` for reliable server name discovery.
Set the environment variable `WIN_NODEJS_NPX_PATH` to the full path of `npx.cmd` if the default npx path is not found.
Yes, point the adapter to an already running MCPO instance by specifying its host and port.
It communicates with MCPO over HTTP; consider network security and authentication if MCPO is exposed publicly (not detailed in the README).
Official MCP server for BlazingCDN - AI agents (Claude, Cursor, Windsurf) manage CDN resources, purge cache, query metrics, domains, Anycast CDN, Video CDN and Media CDN

Discover flat-rate DeepSeek plans, model limits, API-key instructions, and coding-client setup

Build and edit landing pages and websites from your AI assistant, and pull how they are performing.
AON MCP connects AI agents to real, buyable products and services with live pricing and tracked links—enabling builders to earn developer revenue share from attributed clicks and conversions.

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
评论