beekmarks/ollama-api-compatible-server
This project provides an Ollama API-compatible server that uses the `llama-cpp-python` library to run local LLM inference. It allows you to use your own GGUF models with an API that's compatible with Ollama's endpoints, making it easy to integrate with existing tools and applications designed to work with Ollama.
Platform-specific configuration:
{
"mcpServers": {
"ollama-api-compatible-server": {
"command": "npx",
"args": [
"-y",
"ollama-api-compatible-server"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
Loading reviews...