Skip to content
mcp/harbor
LangChain

semanticscholar for LangChain

io.github.smaboundless/semanticscholar

Search 200M+ papers, authors, citations, and recommendations via Semantic Scholar

client:LangChain transport:stdio runtime:npm

Install semanticscholar in LangChain

pip install langchain-mcp-adapters 

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "semanticscholar": {
            "transport": "stdio",
            "command": "npx",
            "args": ["-y", "semanticscholar-mcp-server"],
        }
})

tools = await client.get_tools()

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

semanticscholar in other clients

semanticscholar MCP server