How to Use the Faceit MCP in LangChain

Q: How do I pass game IDs from Faceit to LangChain vector stores?

You query game data using getgames and pass the returned IDs and player counts as documents into your LangChain vector store. This lets your agent query game-specific metadata during active conversational sessions.

Build LangChain agents that chain Faceit match stats and player ELO directly into your live esports broadcast pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Faceit MCP to LangChain

Create your Vinkius account to connect Faceit 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 Faceit with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain player lookups with LangChain agents

Your LangChain agent can now run multi-step scouting by passing player IDs from `search_players` directly into `get_player_stats` without hardcoded glue code. It checks the player's current win streak and CS2 headshot percentage, then decides whether to pull their full match history. By linking these tools, your agent inspects historical ELO swings using `get_player_history` to flag smurfs or high-momentum players automatically. This MCP Server turns raw endpoint data into structured inputs for your next analytical chain step.

Feed live match data to your LangChain chains

Feed live match data into your LangChain pipelines by calling `get_hub_matches` to filter ongoing or upcoming tournament fixtures. The agent parses the match IDs, then triggers `get_match` to pull active team rosters and bracket positions instantly. It calculates tournament difficulty by checking `get_hub_leaderboard` to weight the average ELO of active participants. This setup lets you build autonomous esports scouts that monitor competitive hubs without manual oversight.

Extract post-game telemetry using this MCP Server

This MCP Server lets your LangChain agent pull detailed performance metrics like K/D/A and MVP rounds using `get_match_stats` right after a match ends. The agent evaluates player impact, comparing raw headshot ratios against the lobby average. It pipes these metrics directly into LangSmith for tracing, giving you full visibility into how your agent processes competitive gaming stats. You get clean, verifiable data pipelines that don't hallucinate player performance.

Setup guide

Set up Faceit 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 Faceit 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({
    "faceit-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 Faceit 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 Faceit. 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 Faceit 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 Faceit MCP in LangChain

LangChain manages rate limits by wrapping the MCP Server tools in standard runnables that support custom retry logic. If `get_match_stats` hits Faceit limits during a live tournament, your chain pauses and retries based on your backoff configuration.

Yes, you can construct a ReAct agent that dynamically decides when to use `search_players` versus `get_player_bans`. The agent analyzes the user's prompt, searches for the player, checks their ban history, and outputs a clean profile.

You query game data using `get_games` and pass the returned IDs and player counts as documents into your LangChain vector store. This lets your agent query game-specific metadata during active conversational sessions.

Absolutely, you can run parallel chains where each chain queries a different hub ID using `get_hub`. The LangChain client aggregates these details, letting you compare rules and player counts across different competitive hubs.

Your API key and player profile data stay inside the Vinkius V8 sandbox, meaning LangChain never exposes your credentials. The adapter only passes the clean JSON outputs from tools like `get_player` to your local execution chain.

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