How to Use the CurseForge MCP in LangChain

Q: How do I handle CurseForge mod dependency loops in LangChain?

Use a recursive LangChain agent that calls getmod to check dependencies. The agent inspects the returned metadata, identifies required files, and loops back to fetch those IDs until the dependency tree is fully resolved.

Q: How do I handle batch mod lookups?

Use getmodsbatch to query multiple mod IDs in a single agent step. This reduces chain latency by avoiding sequential network requests for every single mod in a pack.

Q: Does this setup expose my local Minecraft or WoW directory data?

No. When your agent calls getfingerprintsmatches, only the hashed file fingerprints are sent to the CurseForge API through Vinkius's secure MCP sandbox. Your actual local game files and directory paths never leave your local environment.

Build multi-step modding pipelines using LangChain to search, select, and fetch CurseForge files in a single run.

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 LangChain

Create your Vinkius account to connect CurseForge to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build chained mod dependency graphs in LangChain

The `get_mod` tool retrieves metadata for individual game modifications. You can feed this data right into your next chain link to automatically resolve complex mod dependencies. By feeding these outputs into `list_mod_files`, your LangChain agent maps out every file version without manual steps. It handles the entire recursive lookup so you don't have to write custom loop logic.

Trace CurseForge file downloads with LangSmith

The `get_mod_file_download_url` tool generates signed URLs for direct file retrieval. When integrated with LangChain via MCP, you can trace every single download request to monitor performance and debug broken links. Adding `get_mod_file_changelog` lets your agent verify update logs before passing the final URL to your deployment pipeline. You get full visibility into what your agent is pulling and why.

Run multi-server lookups with this CurseForge MCP Server

This CurseForge MCP Server connects your LangChain agent directly to the live gaming database. It lets you run parallel searches across thousands of listings instantly. Combine it with `get_fingerprints_matches` to match local client files against the remote repository. Your agent makes real-time decisions on which files to update based on trace data.

Setup guide

Set up CurseForge MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes CurseForge tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "curseforge-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent CurseForge transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Use a recursive LangChain agent that calls `get_mod` to check dependencies. The agent inspects the returned metadata, identifies required files, and loops back to fetch those IDs until the dependency tree is fully resolved.

Yes, by using LangSmith tracing on your agent. Every time the agent runs `search_mods` or `get_files_batch`, LangSmith logs the exact execution time, token count, and raw payload returned from the server.

You initialize the MultiServerMCPClient with the CurseForge endpoint alongside your other server URLs. LangChain treats all exposed tools as a single pool, allowing your agent to query game versions via `list_game_versions_v2` and cross-reference them with external databases.

Use `get_mods_batch` to query multiple mod IDs in a single agent step. This reduces chain latency by avoiding sequential network requests for every single mod in a pack.

No. When your agent calls `get_fingerprints_matches`, only the hashed file fingerprints are sent to the CurseForge API through Vinkius's secure MCP sandbox. Your actual local game files and directory paths never leave your local environment.

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