How to Use the Moxie MCP in LangChain

Q: How do I pass Moxie tools to a LangChain agent?

You install the MCP adapter, call client.gettools() to fetch the 12 Moxie tools, and pass them directly to your agent constructor. LangChain handles the tool schemas automatically, allowing your agent to call createclient or createinvoice on the fly.

Q: Can I trace Moxie tool execution latency in LangChain?

Yes, every time your LangChain agent calls a tool like createtimeentry or searchprojects, LangSmith logs the exact latency and token usage. This gives you deep observability into your automated agency operations.

Run your entire freelance agency operations through multi-step LangChain reasoning loops using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Moxie MCP to LangChain

Create your Vinkius account to connect Moxie to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Moxie with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run autonomous billing chains in LangChain

The `search_invoices` tool lets your agent find unpaid bills and feed them directly into the next step of your chain. When a client misses a deadline, LangChain traces the delay through LangSmith, then triggers `create_invoice` to apply late fees without manual intervention. This MCP Server connection means your multi-step pipelines can query the workspace using `list_clients` to audit accounts. If a client is missing, the agent branches the logic to run `create_client` and set up their portal instantly.

Track project progress with LangChain

The `search_projects` tool exposes active agency work directly to your LangChain decision-making pipelines via MCP. Your agent checks project velocity, compares it against logged hours from `create_time_entry`, and decides whether to alert a project manager. Every single tool call gets logged in LangSmith so you can trace exactly why your agent decided to invoke `create_task` or `create_ticket`. You get complete visibility into the token costs and latency of managing your team.

Link client setups with multi-agent chains

The `create_project` tool allows LangChain agents to spin up new workspaces the second a contract is signed. By linking this tool with `search_contacts`, your pipeline pulls the right stakeholder info and assigns tasks automatically. If a client files a complaint, the agent runs `create_ticket` to flag the issue, then looks up active team members with `list_users` to assign a resolver. This turns static agency workflows into active, self-correcting loops.

Setup guide

Set up Moxie MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Moxie tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "moxie-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Moxie transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Moxie. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Moxie now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Moxie MCP in LangChain

You install the MCP adapter, call client.get_tools() to fetch the 12 Moxie tools, and pass them directly to your agent constructor. LangChain handles the tool schemas automatically, allowing your agent to call `create_client` or `create_invoice` on the fly.

Yes, every time your LangChain agent calls a tool like `create_time_entry` or `search_projects`, LangSmith logs the exact latency and token usage. This gives you deep observability into your automated agency operations.

You use the MultiServerMCPClient to combine the Moxie MCP server with other tools in a single chain. Your LangChain agent can then query a database and immediately use `create_expense` to log costs based on that data.

LangChain catch-and-retry mechanisms handle the failure gracefully. If `create_ticket` fails due to a network blip, the agent detects the error and retries the call.

We run this server inside a zero-trust, ephemeral V8 Isolate sandbox that isolates your invoice and expense data. Your credentials never leak to the LLM or external logs during execution.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript