PICO-8 MCP Server
Allows fetching and saving PICO-8 documentation from sources like the PICO-8 Fandom wiki to be used as local MCP resources for game development and code reference.
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., "@PICO-8 MCP ServerCount the tokens in game.p8 and check for errors"
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.
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)
Related MCP server: mcp-markdown-tools
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-serverInitialize the shrinko8 submodule:
git submodule update --init --recursiveInstall dependencies:
uv syncFor 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.pyOr 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)
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for developer documentation, generated by doc2mcp.
MCP server for dev documentation, generated by doc2mcp.
MCP server for doc2mcp documentation, generated by doc2mcp.
Related MCP Servers
- AlicenseAqualityCmaintenanceAn MCP server designed for developers to build and manage Minestom-based Minecraft servers by inspecting project environments, build configurations, and API documentation. It enables users to plan features, review design patterns, and discover libraries within the Minestom ecosystem.95 npm6Apache 2.0
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides tools for analyzing, linting, formatting, and generating Markdown content. It enables users to programmatically manage Markdown files through features like table of contents generation, statistics calculation, and JSON-to-table conversion.22 npm1MIT
- AlicenseNot gradedqualityDmaintenanceAn intelligent MCP server that provides tools for code analysis using OpenAI API, code collection, and documentation generation.58 npmMIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server that provides ultra-efficient code exploration through AST analysis, reducing LLM token usage by up to 95% while enabling instant call graph generation and dependency analysis for massive codebases.MIT