How to Use the Jservice MCP in LlamaIndex

Q: Can a LlamaIndex agent search Jservice categories semantically?

Yes, by using getcategories to pull category metadata and indexing those results. The LlamaIndex agent can search your local vector index to find the right category ID before calling getcategory.

Q: Can I limit which Jservice tools my LlamaIndex agent accesses on the MCP Server?

Yes, you can use the allowedtools filter when converting the MCP spec to LlamaIndex tools. This lets you restrict your agent to only getclues while blocking access to category tools.

Index real Jeopardy! clues into your LlamaIndex vector store.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jservice MCP to LlamaIndex

Create your Vinkius account to connect Jservice 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 Jservice with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live Jservice MCP Server data for RAG

Right. So. The `get_category` tool fetches complete trivia categories that your LlamaIndex pipeline instantly converts into document nodes. Instead of just reading the clues, your agent indexes this structured data directly into a vector store for semantic search. This setup means your agent queries past trivia sessions using natural language rather than raw database IDs. You combine historical Jeopardy! data with real-time API lookups in one unified index.

Query filtered trivia directly in LlamaIndex

The `get_clues` tool lets your LlamaIndex agent pull questions matching specific point values or air dates to ground its answers. The agent queries the API, stores the raw text, and uses it to answer user questions without hallucinating dates or categories. By feeding these clues into your index, you build a self-correcting trivia engine. The agent checks its own vector database before pulling new questions via the API — and this matters — to avoid stale data.

Feed random clues into LlamaIndex memory

The `get_random_clues` tool injects unpredictable trivia sets directly into your agent's active memory buffer. LlamaIndex parses these random payloads and uses them to generate dynamic quiz matches on the fly. You can also run `get_categories` first to build a local index of available topics. This lets your agent suggest relevant categories to users based on their past search history — I'll take that for 200.

Setup guide

Set up Jservice 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 Jservice 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 Jservice tools.",
)
response = await agent.run("List recent Jservice 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 Jservice. 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 Jservice 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 Jservice MCP in LlamaIndex

Use llama-index-tools-mcp to connect to the server, then fetch raw clues using get_clues or get_category. Your pipeline can then parse these outputs into nodes and insert them into a vector index.

Yes, by using get_categories to pull category metadata and indexing those results. The LlamaIndex agent can search your local vector index to find the right category ID before calling get_category.

The server pulls verified facts directly from the Jeopardy! database via get_clues. This grounds your LlamaIndex agent's responses in real historical game data rather than letting it guess trivia answers.

Yes, you can use the allowed_tools filter when converting the MCP spec to LlamaIndex tools. This lets you restrict your agent to only get_clues while blocking access to category tools.

No, the server only handles requests for specific trivia categories and clues. Your private vector indices and search queries remain entirely local to your LlamaIndex application.

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