How to Use the Cadmium Harvester MCP in LlamaIndex

Q: How do I connect the Cadmium Harvester MCP Server to a LlamaIndex agent?

Install the adapter using pip install llama-index-tools-mcp and initialize BasicMCPClient. Convert the server tools using McpToolSpec and pass them to your FunctionAgent.

Q: Can LlamaIndex search through speaker bios fetched by Cadmium Harvester?

Yes, the agent uses listpresenters to retrieve the bios and indexes them into your vector store. Users can then run semantic queries against the speaker profiles.

Q: Does Cadmium Harvester support selective MCP tool loading in LlamaIndex?

Yes, you can use the allowedtools filter in the client setup to only expose tools like getpresenterdetails while hiding administrative tools.

Q: How do I handle large file lists from Cadmium Harvester in LlamaIndex?

The agent calls listpresentationassets to get the file metadata, then indexes the text fields. This keeps your vector store light while preserving searchability.

Q: Where does Cadmium Harvester store our presenter contact details during indexing?

All presenter details fetched via getpresenterdetails stay within your local LlamaIndex memory or vector store. The Vinkius runtime acts as a stateless bridge and never logs or caches this personal information.

Index speaker bios and presentation files from Cadmium Harvester into LlamaIndex for hallucination-free retrieval.

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 LlamaIndex

Create your Vinkius account to connect Cadmium Harvester to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index event assets directly into LlamaIndex

Your agent uses the `list_presentation_assets` tool to retrieve actual file links and metadata for a local vector index. Your LlamaIndex agent queries this index instead of guessing what files exist. By calling `get_presentation_count`, the system verifies that the index matches the actual event structure. This prevents your RAG pipeline from serving outdated search results to users.

Ground RAG queries with this MCP Server

To enrich your document vectors, the `get_presenter_details` tool provides live speaker bios. The agent combines this live API data with static PDFs to build a unified query engine. You configure the `BasicMCPClient` to fetch fresh data every time a user asks about a speaker. This ensures the output reflects recent updates made in the Cadmium dashboard.

Build queryable speaker profiles

With the `list_presenters` tool, your agent extracts the full roster of speakers to feed your semantic search index. Your agent uses this structured list to map presenters to their respective sessions. Running `get_event_details` allows the agent to tag every indexed document with the correct event metadata. This makes filtering by event ID fast and accurate during complex vector searches.

Setup guide

Set up Cadmium Harvester MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Cadmium Harvester MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Cadmium Harvester tools.",
)
response = await agent.run("List recent Cadmium Harvester data")

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 LlamaIndex

Install the adapter using `pip install llama-index-tools-mcp` and initialize `BasicMCPClient`. Convert the server tools using `McpToolSpec` and pass them to your `FunctionAgent`.

Yes, the agent uses `list_presenters` to retrieve the bios and indexes them into your vector store. Users can then run semantic queries against the speaker profiles.

Yes, you can use the `allowed_tools` filter in the client setup to only expose tools like `get_presenter_details` while hiding administrative tools.

The agent calls `list_presentation_assets` to get the file metadata, then indexes the text fields. This keeps your vector store light while preserving searchability.

All presenter details fetched via `get_presenter_details` stay within your local LlamaIndex memory or vector store. The Vinkius runtime acts as a stateless bridge and never logs or caches this personal information.

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