How to Use the Cadmium Harvester MCP in LangChain

Q: How do I install the Cadmium Harvester MCP Server in LangChain?

Run pip install langchain-mcp-adapters langgraph in your environment. Initialize the MultiServerMCPClient with the Vinkius endpoint URL to expose the event tools to your agent.

Q: Can LangChain agents automatically download speaker slides using Cadmium Harvester?

Yes, the agent calls listpresentationassets to find the file URLs. It then passes those URLs to your download chain in the same execution loop.

Q: How does LangSmith trace LangChain calls made to Cadmium Harvester?

Every execution of getpresenterdetails or other tools appears as a distinct run in your LangSmith dashboard. You can inspect the exact input parameters and JSON outputs returned from the server.

Q: Can I run the Cadmium Harvester MCP Server alongside database tools in a single LangChain agent?

Yes, you pass the tools array from client.gettools() into your agent constructor alongside your custom database tools. The agent decides when to query Cadmium and when to write to your database.

Get your LangChain agents pulling event assets and presenter lists directly from Cadmium without leaving your Python pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cadmium Harvester MCP to LangChain

Create your Vinkius account to connect Cadmium Harvester 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 Cadmium Harvester with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Cadmium data into LangChain pipelines

The `list_presentations` tool feeds raw event data directly into your active ReAct agent loop. Your agent grabs the list, identifies missing assets via `list_presentation_assets`, and schedules follow-up tasks in a single run. LangSmith tracks the latency of these calls to ensure your event-management chains don't stall. You see every payload passing through `get_presentation_count` in your tracing logs.

Multi-server aggregation with this MCP Server

With the `list_presenters` tool, you expose speaker schedules directly to your multi-step LangGraph workflows. By combining this with other API tools, your agent validates speaker bios against external databases. You initialize the connection using `MultiServerMCPClient` to pull from both Cadmium and your CRM simultaneously. The agent resolves conflicts by querying `get_presenter_details` before updating external records.

Track presenter assets in active agent sessions

By calling `get_event_details`, you establish the baseline context for your LangChain decision chains. From there, the agent loops through each presentation to verify that files are uploaded. Using a stateless session, the agent calls `get_account_info` to verify permissions before running heavy batch downloads. This prevents unauthorized calls from wasting your token budget during long runs.

Setup guide

Set up Cadmium Harvester 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 Cadmium Harvester 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({
    "cadmium-harvester-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 Cadmium Harvester 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 Cadmium Harvester. 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 Cadmium Harvester 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 Cadmium Harvester MCP in LangChain

Run `pip install langchain-mcp-adapters langgraph` in your environment. Initialize the `MultiServerMCPClient` with the Vinkius endpoint URL to expose the event tools to your agent.

Yes, the agent calls `list_presentation_assets` to find the file URLs. It then passes those URLs to your download chain in the same execution loop.

Every execution of `get_presenter_details` or other tools appears as a distinct run in your LangSmith dashboard. You can inspect the exact input parameters and JSON outputs returned from the server.

Yes, you pass the tools array from `client.get_tools()` into your agent constructor alongside your custom database tools. The agent decides when to query Cadmium and when to write to your database.

Vinkius runs this tool in an isolated sandbox where your Cadmium API keys are never exposed to the LLM. The agent only receives the specific file URLs and presenter metadata returned by `list_presentation_assets`.

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