How to Use the Zealy MCP in LlamaIndex

Q: How does Zealy and LlamaIndex help with leaderboard tracking?

When using getleaderboard, the resulting data (sprint or all-time) is indexed. This means you can ask natural language questions like, 'What was the top performance in Q3?' and get an answer grounded in historical API results.

Q: Can I check user status with Zealy and LlamaIndex?

Yes. The output from getuser is added to your knowledge store. You can then run queries against past user records, making it easier to track trends across multiple sessions.

Q: What tools does Zealy and LlamaIndex provide for moderation?

After a review submission using reviewsubmission, the outcome is indexed. If you need to audit past disciplinary actions, querying the records associated with user IDs will pull up that specific historical data.

Q: How do I list available Zealy content with LlamaIndex?

You can index all possible quest details by calling listquests. This creates a searchable catalog, allowing you to combine the descriptions of quests and modules into one unified knowledge base.

Q: What kind of data privacy does Zealy and LlamaIndex handle?

The server handles user details fetched via getuser. Because this output is indexed, you must ensure that your retrieval applications only query the necessary fields to maintain strict data governance.

Build knowledge-augmented AI for Zealy using LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zealy MCP to LlamaIndex

Create your Vinkius account to connect Zealy 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 Zealy with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing Community Data Streams

The `get_leaderboard` tool output becomes searchable knowledge. You can query past rankings and combine that data with current documents to answer complex questions. Similarly, when you retrieve a review using `get_review`, the full content gets indexed. This means your RAG application won't just *call* the API—it will use the API result as grounded context.

Mapping Community Structure and Assets

You can build an index of all available resources by listing modules with `list_modules` or checking out every quest using `list_quests`. This allows your agent to answer, 'What kind of quests are possible here?' Listing secrets via `list_secrets` means you can create a comprehensive knowledge base about the community's hidden features for future queries.

Auditing User and System Interactions

When tracking submissions, calling `list_reviews` allows your agent to build an index of all claimed quests waiting for review. You can then query this history semantically. System changes are also indexed; fetching a user with `get_user` or listing webhooks via `list_webhooks` means you'll always have historical context on who was involved and what the setup was.

Setup guide

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

When using `get_leaderboard`, the resulting data (sprint or all-time) is indexed. This means you can ask natural language questions like, 'What was the top performance in Q3?' and get an answer grounded in historical API results.

Yes. The output from `get_user` is added to your knowledge store. You can then run queries against past user records, making it easier to track trends across multiple sessions.

After a review submission using `review_submission`, the outcome is indexed. If you need to audit past disciplinary actions, querying the records associated with user IDs will pull up that specific historical data.

You can index all possible quest details by calling `list_quests`. This creates a searchable catalog, allowing you to combine the descriptions of quests and modules into one unified knowledge base.

The server handles user details fetched via `get_user`. Because this output is indexed, you must ensure that your retrieval applications only query the necessary fields to maintain strict data governance.

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