How to Use the Collect MCP in LangChain

Q: Can I track Collect request history using LangChain?

Yes, you use listrequests to pull data into your agent's memory. It logs the output to your tracing backend for full visibility.

Q: Will Collect data sync with my LangChain state?

You can store the output of getrequest or getcampaign in your agent's persistent state. This ensures the Collect data is available for multi-step reasoning.

Chain your data requests directly into LangChain workflows for automated collection management.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Collect MCP to LangChain

Create your Vinkius account to connect Collect 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 Collect with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Triggering collection workflows in LangChain

Trigger `create_request` calls within your chains to initiate data collection tasks. Your LangChain agent handles the logic, pulling IDs from previous steps to populate new requests. This keeps your pipeline moving without manual intervention. Each tool call links perfectly into your LangSmith traces for debugging.

Managing data collection with an MCP Server

Feed `list_campaigns` results directly into a LangGraph node to audit active projects. Your agent parses the response to decide which campaign needs immediate attention. It removes the need to switch tabs. You get a clear view of your operations through the agent's reasoning process.

Automating communication with LangChain

Use `send_message` to notify recipients about missing documents during a chain execution. Your agent detects the status gap and reaches out immediately. This closes the loop on data requests. Your chain remains the single source of truth for all project communication.

Setup guide

Set up Collect 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 Collect 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({
    "collect-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 Collect 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 Collect. 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 Collect 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 Collect MCP in LangChain

You connect via the MultiServerMCPClient and pass the tool definitions into your agent's tool list. This allows the agent to trigger Collect functions as part of its standard reasoning loop.

Yes, you use `list_requests` to pull data into your agent's memory. It logs the output to your tracing backend for full visibility.

You can store the output of `get_request` or `get_campaign` in your agent's persistent state. This ensures the Collect data is available for multi-step reasoning.

You define your tool logic within the agent's system prompt. This acts as a gatekeeper for which arguments get passed to the API.

We isolate your Collect data within a V8 sandbox during execution. Only the specific request details you authorize are transmitted, and no persistent storage exists outside your session.

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