Where does the configuration go?
langchain-mcp-adapters, with no nofeb-specific package.
pip install langchain-mcp-adapters How do I connect LangChain and LangGraph?
- pip install langchain-mcp-adapters (and langchain for create_agent).
- Create the client with the nofeb server below; only the sse and http transports carry headers.
- Load the tools with await client.get_tools() and pass them to your agent or LangGraph node.
import os
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
client = MultiServerMCPClient(
{
"nofeb": {
"transport": "http",
"url": "https://api.nofeb.com/mcp",
"headers": {
"Authorization": f"Bearer {os.environ['NOFEB_API_KEY']}",
},
}
}
)
tools = await client.get_tools()
agent = create_agent("openai:gpt-4.1", tools) Checked against LangChain and LangGraph's documentation on . source: github.com
What should I know about LangChain and LangGraph's setup?
- create_agent comes from langchain v1; older LangGraph code uses create_react_agent from langgraph.prebuilt.
- Only the sse and http transports carry headers.
What can I ask it to do?
"Sign up for the vendor portal with a fresh inbox and return the verification code." The agent calls create_inbox, then wait_for_email with has_otp.
117 tools are available, including create_inbox, wait_for_email, reply_to_message, get_thread_context, set_thread_state and get_dns_setup. Whether a send goes out at once or waits for a person is decided by the inbox's autonomy tier on the server, not by LangChain and LangGraph.
Frequently asked questions
Is there a nofeb package for LangChain?
No dedicated package is needed: the MCP adapter turns nofeb's tools into LangChain tools, and the Python SDK (nofeb) is there when you want to wrap a call yourself.
Which transport name should I use?
The docs use "http"; the adapter also accepts "streamable_http".
Status of everything on this page
Every capability named above, with its status as reconciled against the engine.
| Capability | What it does | Status |
|---|---|---|
| MCP server | A remote MCP server over streamable HTTP whose tools are generated from the same operation table as the REST API and dispatched through the same router, so a tool cannot behave differently from its endpoint. | Shipped |
| Scoped API keys | Keys bound to the organization, one pod or one inbox, holding only the scopes they are given. A key cannot mint a key wider than itself. | Shipped |
| Autonomy tiers enforced by the server | Every inbox carries a sending policy, from read-only to autonomous, enforced on the server for every surface that sends, so switching from the API to MCP cannot bypass it. | Shipped |
| Wait for an email | Long-poll an inbox for up to a minute until a message matching sender, subject or has-a-code arrives. | Shipped |
| TypeScript and Python SDKs | Official clients generated from the OpenAPI document: @nofeb/sdk for Node, Deno, Bun and edge runtimes, and nofeb for Python with sync and asyncio clients. Both chain long polls for waitForEmail, retry idempotent requests, page through lists and verify webhook signatures. | Shipped |
| MCP sign-in with OAuth | MCP clients connect by signing in instead of pasting a key: OAuth 2.1 with discovery, dynamic client registration, client ID metadata documents, PKCE, tokens bound to the MCP server, refresh-token rotation and immediate revocation. A person approves the scopes, and optionally one inbox, in the console, and can disconnect the app at any time. API keys keep working beside it. | Shipped |