Mcp Source logo

Mcp Source

OrganizationPopular
CoplayDev
mcp-source

Switch MCP for Unity package source in connected Unity projects. Use /mcp-source [main|beta|branch|local] to swap between upstream releases, your remote branch, or local dev checkout.

Overview

PublisherCoplayDev
Repositoryunity-mcp
Skill namemcp-source
Stars
15.3K
Forks
1.6K
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by CoplayDev on GitHub. Read the source before you install it.

Installation

Install the Mcp Source AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/CoplayDev/unity-mcp/tree/beta/.claude/skills/mcp-source
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/CoplayDev/unity-mcp.git /tmp/unity-mcp
mkdir -p .claude/skills
cp -r /tmp/unity-mcp/.claude/skills/mcp-source .claude/skills/mcp-source
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mcp Source in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mcp Source on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mcp Source is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Switch MCP for Unity Package Source

You are switching the com.coplaydev.unity-mcp package source in one or more Unity projects.

allowed-tools

Bash, Read, Edit, ReadMcpResourceTool, ListMcpResourcesTool

Instructions

1. Parse arguments

The user's argument is: $ARGUMENTS

Valid values: main, beta, branch, local, or empty.

If empty or not one of the four valid values, ask the user to choose:

  • main — upstream main branch (stable releases)
  • beta — upstream beta branch (pre-release)
  • branch — your current remote branch (for testing a PR)
  • local — local file reference to your checkout (for live dev iteration)

2. Detect repo context

Run these git commands from the current working directory to find the unity-mcp repo:

bash
git rev-parse --show-toplevel    # → repo_root
git rev-parse --abbrev-ref HEAD  # → branch_name
git remote get-url origin        # → origin_url

Convert SSH origins to HTTPS: if origin_url starts with git@github.com:, transform it to https://github.com/{owner}/{repo}.git.

3. Discover target Unity projects

Try two approaches to find Packages/manifest.json files to update:

Approach A — MCP resources (preferred): Read mcpforunity://project/info for each connected Unity instance (use ListMcpResourcesTool to find available instances). Extract projectRoot and use {projectRoot}/Packages/manifest.json.

Approach B — filesystem fallback: If no MCP instances are connected, search upward from the current working directory for Packages/manifest.json files using Bash:

bash
find "$(pwd)" -maxdepth 3 -name "manifest.json" -path "*/Packages/manifest.json" 2>/dev/null

If multiple manifests are found, update all of them (confirming with the user first).

4. Build the package URL

Based on the user's selection, construct the dependency value:

SelectionURL
mainhttps://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#main
betahttps://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#beta
branch{origin_https}?path=/MCPForUnity#{branch_name}
localfile:{repo_root}/MCPForUnity

For branch: use the HTTPS-normalized origin URL and current git branch name. For local: use the absolute path to the repo root with file: prefix (no //), e.g. file:/Users/davidsarno/unity-mcp/MCPForUnity.

5. Update each manifest

For each discovered manifest.json:

  1. Read the file with the Read tool
  2. Find the "com.coplaydev.unity-mcp" dependency line
  3. Use the Edit tool to replace the old value with the new URL
  4. Report what was changed: old value → new value, file path

6. Report results

After updating, tell the user:

  • Which manifests were updated
  • The old and new package source values
  • Remind them: "Unity will re-resolve the package automatically. If it doesn't, open Package Manager and click Refresh."

Frequently asked questions

What does the Mcp Source AI skill do?

Switch MCP for Unity package source in connected Unity projects. Use /mcp-source [main|beta|branch|local] to swap between upstream releases, your remote branch, or local dev checkout.

Why use Mcp Source on TypingMind?

Because you install it once and use it with any model. Mcp Source is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mcp Source in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/CoplayDev/unity-mcp/tree/beta/.claude/skills/mcp-source. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Mcp Source?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mcp Source?

As many as you like. As long as a model supports skills, you can use Mcp Source with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mcp Source AI skill free?

Yes. It is published on GitHub by CoplayDev under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇