Connect LangChain / LangGraph to Willder

A Python agent framework; langchain-mcp-adapters turns MCP tools into LangChain tools.

Transport: Streamable HTTP · Auth: Authorization: Bearer <capability token> · Endpoint: https://willder.ai/api/mcp

Verified end to end on 2026-10-05, against https://willder.ai/api/mcp on deployed commit 2eed3f05. Both of the client matrix's claims hold for this row: the server answered the transport and authentication shape this page configures, and LangChain itself connected, listed all ten Willder tools and answered one scoped memory_query.

See the index for what every other row says.

Get a token

Open Access → Tokens in your Willder workspace and issue a capability token for the narrowest scope that answers your questions. The value is shown once; only its hash is stored. Keep it in the client's secret storage or an environment variable — never in a committed file, a prompt or a screenshot.

Terminal

export WILLDER_TOKEN='<your capability token>'

Config file

Your own code — no config file.

Python

import os
from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
    "willder": {
        "transport": "http",
        "url": "https://willder.ai/api/mcp",
        "headers": {"Authorization": f"Bearer {os.environ['WILLDER_TOKEN']}"},
    }
})
tools = await client.get_tools()

Verify the connection

[t.name for t in tools] includes memory_query, memory_entity and memory_ingest.

See the index for the other clients and mcp/README.md for the tool surface and the token rules.