How to Use the FreeScout MCP in LangChain

Q: How do I connect the FreeScout MCP Server to my LangChain agents?

Install the langchain-mcp-adapters package and initialize the MultiServerMCPClient with your Vinkius endpoint. You then fetch the tools using client.gettools() and pass them directly into your agent constructor to let it call tools like listmailboxes.

Run multi-step support chains that read mailboxes and send customer replies using LangChain and the FreeScout 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 FreeScout MCP to LangChain

Create your Vinkius account to connect FreeScout 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 FreeScout with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-step triage with LangChain and FreeScout

FreeScout MCP Server tools let your LangChain agents fetch open tickets and route them to the correct department without manual sorting. The agent starts by calling `list_conversations` to pull unassigned threads from a specific inbox. It evaluates the content of those threads, then calls `update_conversation` to assign the ticket to the right agent group based on historical load. You trace the entire execution path in LangSmith to see exactly why an agent chose a specific route. If a ticket requires immediate escalations, the chain automatically runs `add_note` to flag the issue for senior staff before writing back.

Build self-correcting response chains

FreeScout ticket resolution works by feeding raw API data into your ReAct agents to draft precise customer replies. The agent calls `get_conversation` and `list_threads` to pull the complete message history of an active ticket. It analyzes the historical context, checks customer details via `get_customer`, and drafts a contextual response. Before sending anything, the chain evaluates the draft against your internal guidelines. If it passes, the agent runs `add_reply` to send the message to the customer and immediately uses `update_conversation` to mark the status as pending.

Map support directories on the fly

FreeScout directory mapping allows your LangChain agent to cross-reference customer profiles with active agent rosters. The agent calls `list_customers` to locate the user's account ID and runs `list_users` to see which agents are currently active. This ensures that incoming tickets get routed to people who actually have the capacity to handle them. Once the agent matches the customer record via `get_customer`, it updates the ticket. It executes `update_customer` to append new metadata directly to the user profile, keeping your database clean without manual input.

Setup guide

Set up FreeScout 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 FreeScout 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({
    "freescout-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 FreeScout 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 FreeScout. 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 FreeScout 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 FreeScout MCP in LangChain

Install the `langchain-mcp-adapters` package and initialize the `MultiServerMCPClient` with your Vinkius endpoint. You then fetch the tools using `client.get_tools()` and pass them directly into your agent constructor to let it call tools like `list_mailboxes`.

Yes, by chaining multiple tool calls together in a LangGraph workflow. Your agent can call `get_conversation` to check a ticket's status, decide if it needs attention, and then run `add_note` or `add_reply` based on the thread history.

You configure rate-limiting middleware or retry logic directly in your LangChain runnable configuration. When tools like `list_conversations` hit API limits, the chain backs off and retries the call automatically.

Yes, the MCP adapter is stateless by default, but you can use `client.session()` to persist context across multiple runs. This is useful when your agent needs to track conversation states across several `update_conversation` calls.

The MCP server runs inside a zero-trust V8 Isolate sandbox on Vinkius, meaning your customer messages and ticket threads are never stored. All communication between LangChain and the FreeScout API is encrypted transit-only, and your API token is isolated from the agent runtime.

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