Glasir for LangChain
io.github.attackwave/glasir
A queryable graph of a codebase: impact, callers, tests to run, history. No model, no network.
client:LangChain
transport:stdio
runtime:oci
Install Glasir in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"glasir": {
"transport": "stdio",
"command": "docker",
"args": ["run", "-i", "--rm", "ghcr.io/attackwave/glasir:v0.13.2"],
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs