# Gym MCP

> Use this tool when you need to train AI agents to play and learn from various games, such as Tic-Tac-Toe, through a standardized interface. It solves problems related to environment integration and game discovery, allowing agents to interact with multiple games using a single interface. The tool takes game environments as input and outputs agent performance and learning outcomes, making it ideal for reinforcement learning and game-playing AI applications.

Canonical page: https://skillsregistry.net/skills/ishantiwari0112-gym-mcp  
JSON: https://api.skillsregistry.net/v1/skills/ishantiwari0112-gym-mcp

## Description

Enables AI agents to discover and play games like Tic-Tac-Toe through a standardized interface, with plans to integrate more environments.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/hak7h1l29x)
- **Repository:** <https://github.com/IshanTiwari0112/gym-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "ishantiwari0112-gym-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ishantiwari0112-gym-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ishantiwari0112-gym-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt