Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

Enables AI assistants to interact with the Footics World Cup 2026 prediction game, reading matches, standings, predictions, and optionally submitting predictions.

README.md

Footics MCP

A remote MCP server for Footics, a World Cup 2026 prediction game. A user connects their AI assistant (Claude, ChatGPT, Cursor…) to https://mcp.footics.app/mcp, signs in with their Footics account, and the assistant can read their matches, standings and predictions — and, optionally, submit them. Inference runs on the user's side; Footics only pays for hosting.

Written in Go (cmd/mcp) with the official modelcontextprotocol/go-sdk. The server is a thin authenticated client of the Footics REST API (/v1): it holds no database connection and no service-role key — every read and write is forwarded to the API with the calling user's token, so the API stays the single source of truth and the single write point.

Architecture

AI assistant (Claude / ChatGPT)  ──MCP/HTTP──►  cmd/mcp        (/mcp)
                                                 │ internal/auth      verify user JWT (JWKS or HS256)
                                                 │ internal/tools  →  internal/apiclient  (calls /v1 with the user token)
                                                 ▼
                                          Footics API (api.footics.app) ──► Postgres
  • internal/auth — verifies Supabase-issued user JWTs (JWKS asymmetric in

prod, HS256 for local dev), same JWKS cache + refresh cooldown as the API.

  • internal/apiclient — forwards each tool call to the Footics /v1 API

with the user's bearer token (no privileged credentials here).

  • internal/tools — the MCP tool definitions + per-user rate limiting.

Tools

whoami · list_matches · get_match · get_my_standing · get_my_predictions · get_leaderboard · list_my_groups · get_joker_status · search · submit_prediction (gated by MCP_ENABLE_WRITES)

Configuration

| Variable | Default | Effect | |---|---|---| | FOOTICS_API_URL | — | base URL of the Footics REST API | | AUTH_JWKS_URL | — | JWKS URL(s) for asymmetric token verification (prod) | | AUTH_JWT_SECRET | — | HS256 secret (local dev alternative to JWKS) | | MCP_ENABLED | true | false/mcp returns 503 without verifying tokens (kill switch) | | MCP_REQUIRE_AUTH | true | require a valid bearer token (401 otherwise) | | MCP_ENABLE_WRITES | false | allow submit_prediction | | MCP_RATE_LIMIT_PER_MIN | 30 | tool calls per minute per user (0 = off) |

See .env.example for the full list.

Development

cp .env.example .env    # point AUTH at a local/staging GoTrue, not production
go run ./cmd/mcp        # serves on $HTTP_ADDR (default :8080), /mcp

Without an Authorization: Bearer <token> header the endpoint returns 401 (unless MCP_REQUIRE_AUTH=false). Build a static binary with go build ./cmd/mcp; the container image is the multi-stage Dockerfile (distroless).

Deployment

Runs on the Footics VPS as a Dokploy service (footics-mcp), build-from-git via deploy/compose.dokploy.yml → published at mcp.footics.app. Runbook lives in the private infra repo.

Security

Auth is required and writes are off by default. See SECURITY.md for the model and how to report a vulnerability.

License

MIT © 2026 Tom Cardoen

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use AI & ML servers.