Sudoku MCP Server
A Cloudflare Worker-based MCP server for playing Sudoku, exposing five tools (start_game, get_game, play_move, check_game, reset_game) that let users start uniquely solvable puzzles, make moves, validate entries against a hidden solution, and reset games via a SQLite-backed Durable Object per game.
README
Sudoku MCP Server
A Cloudflare Worker exposing a small remote MCP server at /mcp. It implements
five gameplay tools: start_game, get_game, play_move, check_game, and
reset_game.
Local development
npm install
npm run types
npm test
npm run build
npm run dev
The root endpoint is a health response; MCP clients should use
http://localhost:8787/mcp.
Automatic deployment
.github/workflows/deploy.yml runs the tests and type-check on pull requests.
After a change reaches main, it deploys the Worker automatically. Configure
these GitHub Actions secrets before the first production deployment:
CLOUDFLARE_API_TOKEN: a Cloudflare API token permitted to deploy this Worker.CLOUDFLARE_ACCOUNT_ID: the Cloudflare account identifier for this Worker.
The token must be stored as a GitHub secret, never committed to the repository.
Authentication
Wrangler uses Cloudflare OAuth for local CLI operations:
npx wrangler login
npx wrangler whoami
This Worker intentionally has no application-level auth or user-account layer, as specified by the development plan. Add access control at the deployment boundary before exposing a production endpoint.
Game behavior
Puzzles are normalized to one 81-character row-major grid. Whitespace is
ignored, . and 0 mean empty, and digits 1-9 are givens. start_game
accepts only uniquely solvable puzzles and stores the solution privately inside
one SQLite-backed Durable Object per game ID. play_move enforces only visible
row/column/box conflicts; check_game is the tool that evaluates entries
against the hidden solution. Every state response includes the canonical
initial/current grids and a labeled board rendering.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.