Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Chess MCP Server make a move for me as white: e4"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
To run the MCP server using the provided configuration, follow these steps:
Install prerequisites
Ensure you have uvx installed on your system.
Clone and start the server
The configuration below will start the MCP server from a GitHub repository using uvx.
The command pulls the server code and launches the mcp-server entry point.
{
"mcpServers": {
"GithubHostedExample": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/bkoseda/mcpchesssampleserver.git",
"chess"
]
}
}
}Run the server
Execute the following command in your terminal:
uvx --from git+https://github.com/bkoseda/mcpserverexample.git mcp-serverThis will download the MCP server from the specified GitHub repository and start it locally.
Refer to the repository's documentation for additional configuration or usage details.
Get the public profile for a Chess.com player by username.
Inputs: username (required).
Get the stats for a Chess.com player by username.
Inputs: username (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have clearly distinct purposes: one retrieves a player's public profile, the other retrieves their stats. There is no overlap or ambiguity.
Both tools follow the exact same pattern: get_chess_player_ followed by a specific noun (profile, stats). This is consistent and predictable.
With only two tools, the server feels thin. While they cover a focused player-info domain, the broader chess context suggests more tools could be expected, making the count borderline.
The tools cover the main player profile and stats endpoints, but the server is named 'Chess MCP Server,' implying a wider scope. Missing tools for games, tournaments, or other chess data create notable gaps.
MCP server for AI dialogue using various LLM models via AceDataCloud
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Manage Superlist tasks and lists in plain language from any MCP-compatible AI agent.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.