How to Use the Modrinth MCP in LlamaIndex

Q: How do I load Modrinth tool outputs into a LlamaIndex vector store?

You use searchprojects to pull the mod data, wrap the JSON in LlamaIndex Document objects, and insert them into your VectorStoreIndex. This makes the live Modrinth data searchable via semantic queries.

Q: Can LlamaIndex use the Modrinth MCP Server to find compatible plugins?

Yes, your LlamaIndex agent calls getproject and inspects the compatibility fields. It indexes these specifications so you can query for plugins matching your exact server software.

Q: How do I prevent hallucinations when asking LlamaIndex about Modrinth mods?

By forcing the agent to use getversion before answering, you ground its responses in verified API data. The agent relies on the indexed tool output instead of its pre-trained weights.

Q: Can I index Modrinth dependency lists for offline analysis?

You can run getprojectdependencies and store the resulting JSON structure directly in your LlamaIndex storage context. This lets you analyze modpack compatibility offline.

Index Minecraft mod metadata and query Modrinth project data using LlamaIndex RAG pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Modrinth MCP to LlamaIndex

Create your Vinkius account to connect Modrinth 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 Modrinth with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Modrinth project data in LlamaIndex

`search_projects` retrieves raw project data from Modrinth and formats it so LlamaIndex can index it into a vector store. Your agent queries this local index to find mods based on conceptual descriptions rather than exact keyword matches. This approach grounds your agent's recommendations in actual, current platform data. You eliminate hallucinated mod names because the system queries your freshly indexed vector store.

Query Minecraft version details via LlamaIndex

`list_versions` feeds the complete version history of any Minecraft project directly into your LlamaIndex document store. Your query engine parses these versions to answer complex compatibility questions about specific game updates. By combining this with `get_version`, the system builds a searchable knowledge base of file hashes and changelogs. You can ask your agent which specific file version fixed a known bug, and it will pull the exact release notes.

Map Modrinth developer networks using this MCP Server

`get_user_profile` extracts detailed creator information to build a local knowledge graph of Minecraft developers inside LlamaIndex. The agent connects authors to their work by linking this profile data with `list_user_projects`. This structure lets you run complex queries about the ecosystem, like finding all active projects maintained by a specific team. Your agent navigates these relationships locally without hitting rate limits on every question.

Setup guide

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

You use `search_projects` to pull the mod data, wrap the JSON in LlamaIndex Document objects, and insert them into your VectorStoreIndex. This makes the live Modrinth data searchable via semantic queries.

Yes, your LlamaIndex agent calls `get_project` and inspects the compatibility fields. It indexes these specifications so you can query for plugins matching your exact server software.

By forcing the agent to use `get_version` before answering, you ground its responses in verified API data. The agent relies on the indexed tool output instead of its pre-trained weights.

You can run `get_project_dependencies` and store the resulting JSON structure directly in your LlamaIndex storage context. This lets you analyze modpack compatibility offline.

The server only accesses public Minecraft mod metadata, download links, and user profiles. Because Vinkius hosts the server in a zero-trust sandbox, your LlamaIndex queries and access keys are never exposed or stored.

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