Skip to content
mcp/harbor
LangChain

OP Inference for LangChain

com.opinference/op

OP tasks, your presets and the public workflow gallery, billed to your API key.

client:LangChain transport:streamable-http

Install OP Inference in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "op": {
            "transport": "streamable_http",
            "url": "https://api.opinference.com/v1/mcp",
        }
})

tools = await client.get_tools()

get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs

OP Inference in other clients

OP Inference MCP server