Mcp Dynamic Discovery logo

Mcp Dynamic Discovery

Organization
UitbreidenOS
mcp-dynamic-discovery

Claude Code MCP Dynamic Discovery: zero-config external tool integration. Automatically scans system configuration directories for active Model Context Protocol (MCP) servers and configures them locally

Overview

PublisherUitbreidenOS
RepositoryUitKit
Skill namemcp-dynamic-discovery
Stars
14
Forks
5
Bundled files
Instructions only
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 UitbreidenOS on GitHub. Read the source before you install it.

Installation

Install the Mcp Dynamic Discovery 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/UitbreidenOS/UitKit/tree/main/plugins/uitkit-ai-engineering/skills/mcp-dynamic-discovery
  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/UitbreidenOS/UitKit.git /tmp/UitKit
mkdir -p .claude/skills
cp -r /tmp/UitKit/plugins/uitkit-ai-engineering/skills/mcp-dynamic-discovery .claude/skills/mcp-dynamic-discovery
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mcp Dynamic Discovery 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 Dynamic Discovery 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 Dynamic Discovery 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.

MCP Dynamic Discovery — Zero-Config Tool Integration

When to activate

  • Integrating with external tools (Slack, Jira, GitHub, Figma, Linear, databases) in a new workspace.
  • When you want to reuse existing MCP configurations from Claude Desktop, Cursor, or other IDEs without manual copying.
  • Connecting to local services (PostgreSQL, Redis, Docker) that expose MCP endpoints.
  • Minimizing setup friction for team members checking out a repository.

When NOT to use

  • Purely offline coding sessions with no external APIs or integrations.
  • High-security environments where dynamic discovery of local configs or outbound network connections is restricted.
  • Shared systems where other users' configs shouldn't be read.

Instructions

The MCP Dynamic Discovery skill automates the detection, import, and wiring of Model Context Protocol (MCP) servers located on the user's system into the active Claude Code CLI session.

       Local Configuration Directories (Desktop, Cursor, Windsurf)
                               │
                               ▼
               ┌───────────────────────────────┐
               │    1. Scan Configuration      │
               │ (Search configs/SQLite DBs)   │
               └───────────────┬───────────────┘
                               │
                               ▼
               ┌───────────────────────────────┐
               │  2. Extract Servers & Tools   │
               │ (Parse commands/envs/tokens)  │
               └───────────────┬───────────────┘
                               │
                               ▼
               ┌───────────────────────────────┐
               │      3. Dynamic Injector      │
               │ (Merge into .claude/settings) │
               └───────────────────────────────┘

1. Config Directories to Scan

Scan the standard operating system paths where AI clients store MCP server configurations:

  • Mac OS:
    • Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Cursor global storage: ~/Library/Application Support/Cursor/User/globalStorage/saantiagoo.mcp-connector/mcp-servers.json
  • Windows:
    • Claude Desktop: %APPDATA%\Claude\claude_desktop_config.json
    • Cursor global storage: %APPDATA%\Cursor\User\globalStorage\saantiagoo.mcp-connector\mcp-servers.json
  • Linux:
    • Claude Desktop: ~/.config/Claude/claude_desktop_config.json

2. Auto-Discovery Script

To discover and list servers, run this quick check command:

bash
# Locate and view server configurations
if [ -f "$HOME/Library/Application Support/Claude/claude_desktop_config.json" ]; then
  echo "Found Claude Desktop MCP configs:"
  cat "$HOME/Library/Application Support/Claude/claude_desktop_config.json" | grep -A 5 -B 1 '"mcpServers"'
fi

3. Merging Settings

Once target server definitions are extracted, write/merge them directly into the current repository's .claude/settings.json:

json
{
  "mcpServers": {
    "discovered-postgres": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-postgres", "postgresql://localhost:5432/my_db"]
    },
    "discovered-slack": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-slack"],
      "env": {
        "SLACK_BOT_TOKEN": "xoxb-xxxx-xxxx"
      }
    }
  }
}

4. Connection Verification

Run /mcp in Claude Code to verify that the newly wired servers are alive, their connection statuses are green, and their schemas are successfully exposed.


Example

Claude Code dynamically configuring Slack and Figma tools during a session:

  1. Prompt: "Connect to my Slack and Figma tools so I can send the QA report."
  2. Action: Claude searches typical system locations and detects a configured Slack token and command inside the Claude Desktop config.
  3. Result: Claude Code merges the server definitions into .claude/settings.json and prompts the user to refresh the session:
    ✅ Dynamically discovered 2 MCP servers from Claude Desktop:
       - 'slack-server'
       - 'figma-server'
    
    Writing configurations to local .claude/settings.json...
    Run '/mcp reload' to activate the new tools.
  4. Verification: The user runs /mcp list and sees Slack channels and Figma file inspection tools ready to use.

Frequently asked questions

What does the Mcp Dynamic Discovery AI skill do?

Claude Code MCP Dynamic Discovery: zero-config external tool integration. Automatically scans system configuration directories for active Model Context Protocol (MCP) servers and configures them locally

Why use Mcp Dynamic Discovery on TypingMind?

Because you install it once and use it with any model. Mcp Dynamic Discovery 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 Dynamic Discovery in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/UitbreidenOS/UitKit/tree/main/plugins/uitkit-ai-engineering/skills/mcp-dynamic-discovery. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Mcp Dynamic Discovery?

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 Dynamic Discovery?

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

Is the Mcp Dynamic Discovery AI skill free?

It is published on GitHub by UitbreidenOS. Check the repository for licensing terms. 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 👇