PICO-8 MCP Server
An MCP server for analyzing, manipulating, and documenting PICO-8 game carts using the shrinko8 toolkit. It enables users to count tokens, minify code, validate carts, and access API documentation through natural language commands.
README
PICO-8 MCP Server
An MCP server for working with PICO-8 game carts, built on top of shrinko8.
Features
Code Analysis Tools
- count_tokens - Count tokens, characters, and compressed size
- analyze_cart - List functions, globals, and code metrics
- validate_cart - Validate cart with token limits and linting
- search_code - Search for code patterns across carts
- compare_carts - Compare two cart versions with diff
Cart Manipulation
- read_cart - Read cart sections (code, gfx, map, sfx, music)
- minify_cart - Minify carts to reduce token count
- list_carts - List all carts in a directory with metadata
Documentation Resources
- add_documentation - Fetch and save PICO-8 documentation from URLs
- Resources - Saved documentation is available as MCP resources (e.g.,
pico8://docs/api)
Installation
Prerequisites
- Python 3.8+
- uv package manager
Setup
- Clone the repository:
git clone https://github.com/YOUR_USERNAME/pico8-mcp-server.git
cd pico8-mcp-server
- Initialize the shrinko8 submodule:
git submodule update --init --recursive
- Install dependencies:
uv sync
For Claude Code (VSCode)
Add the server using the Claude CLI:
cd /Users/ebonura/Desktop/repos/pico8-mcp-server
claude mcp add pico8 --scope project -- uv run server.py
Or manually create a .mcp.json in your project root:
{
"mcpServers": {
"pico8": {
"command": "uv",
"args": ["run", "/Users/ebonura/Desktop/repos/pico8-mcp-server/server.py"]
}
}
}
For Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"pico8": {
"command": "uv",
"args": ["--directory", "/Users/ebonura/Desktop/repos/pico8-mcp-server", "run", "server.py"]
}
}
}
Usage Examples
Once configured, you can ask Claude:
- "Count the tokens in my horizon-glide cart"
- "Analyze the code structure of v0.16.p8"
- "Search for all uses of 'terrain' in my carts"
- "Compare v0.15.p8 and v0.16.p8"
- "List all carts in the horizon-glide directory"
- "Validate my cart and show any errors"
Adding Documentation
You can fetch and save PICO-8 documentation:
"Fetch the PICO-8 API reference from https://pico-8.fandom.com/wiki/APIReference
and save it as 'api'"
Once saved, Claude can automatically reference the documentation when helping with PICO-8 code.
License
MIT (inherits from shrinko8)
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.