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., "@Pokemon MCP Server Check my current party and tell me their HP levels"
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.
An MCP server that connects to AI agents and gives them capabilities to play Pokémon games.
uv venv
source .venv/bin/activateIf the project uses pyproject.toml:
uv pip install .If the project uses requirements.txt:
uv pip install -r requirements.txtRelated MCP server: MCP Pokemon Server
Add the following to your MCP client configuration JSON:
Go to cursor settings > Tools & MCP > New MCP Server
{
"mcpServers": {
"pokemon": {
"command": "uv",
"args": [
"uv",
"--directory",
"path_to_root_directory",
"run",
"main.py"
],
}
}
}In .config/opencode/config.json or ~/.config/opencode/opencode.json
{
"mcp": {
"pokemon": {
"type": "local",
"command": [
"uv",
"--directory",
"path_to_root_directory",
"run",
"main.py"
],
"enabled": true,
"timeout": 30000
}
}
}In .gemini/antigravity/mcp_config.json
{
"mcpServers": {
"pokemon": {
"command": "uv",
"args": [
"--directory",
"path_to_root_directory",
"run",
"main.py"
]
}
}
}Replace path_to_root_directory with the absolute path to the project root.
This server cannot be deployed
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
MCP server for AI dialogue using various LLM models via AceDataCloud
One connector for 15,000+ MCP servers plus your team's private MCPs, from any AI client.
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
