How to Use the CurseForge MCP in LlamaIndex

Q: How do I avoid hallucinated mod recommendations in LlamaIndex?

Ground your agent by indexing the live output of searchmods. LlamaIndex uses this fresh data to answer queries, ensuring every recommended mod exists and is active.

Q: Can LlamaIndex cache CurseForge file details locally?

Yes, you can index the metadata returned by getfilesbatch into a local vector store. Your system then queries this local index first, caching the results of your MCP tool calls before hitting the live API for repeated requests.

Q: How does LlamaIndex handle CurseForge game categories?

The agent calls listcategories to fetch the taxonomy of a specific game. LlamaIndex indexes these categories as metadata tags, allowing you to filter your vector searches by specific game genres or mod types.

Q: How do I structure the index for mod changelogs?

Fetch the changelog using getmodfilechangelog and load it as a document node. LlamaIndex indexes the text so users can query what changed in specific releases.

Index CurseForge mod metadata directly into LlamaIndex vector stores to query game files without hallucinations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CurseForge MCP to LlamaIndex

Create your Vinkius account to connect CurseForge 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 CurseForge with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a searchable index of CurseForge mod descriptions

The `get_mod_description` tool fetches the raw HTML description of any game mod. LlamaIndex parses this text and stores it as document nodes in your vector database. Once indexed, you can run semantic search queries across thousands of mods. Your RAG pipeline finds matches based on actual feature descriptions rather than simple keyword matches.

Ground your LlamaIndex queries in live mod files

The `list_mod_files` tool retrieves the complete file history for a specific mod through this MCP connection. Your LlamaIndex agent indexes these version lists to answer precise questions about file compatibility. By combining this with `get_mod_file`, your system checks specific file details. It prevents your agent from recommending outdated or incompatible file versions to users.

Query game versions with this CurseForge MCP Server

This CurseForge MCP Server exposes game version structures directly to your LlamaIndex query engine. It provides the exact schema needed to understand complex game updates. Using `list_game_versions_v2`, the agent populates its local context with valid game environments. This ensures your search index always aligns with actual release cycles.

Setup guide

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

Ground your agent by indexing the live output of `search_mods`. LlamaIndex uses this fresh data to answer queries, ensuring every recommended mod exists and is active.

Yes, you can index the metadata returned by `get_files_batch` into a local vector store. Your system then queries this local index first, caching the results of your MCP tool calls before hitting the live API for repeated requests.

The agent calls `list_categories` to fetch the taxonomy of a specific game. LlamaIndex indexes these categories as metadata tags, allowing you to filter your vector searches by specific game genres or mod types.

Fetch the changelog using `get_mod_file_changelog` and load it as a document node. LlamaIndex indexes the text so users can query what changed in specific releases.

No. The Vinkius MCP Server handles all authentication tokens securely within an isolated sandbox. Your search queries and retrieved mod metadata are processed locally in your memory space, keeping your setup private.

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