Tool KitCAUTION
Agentic abstraction layer for building high precision vertical AI agents written in python for Model Context Protocol.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A comprehensive toolkit for the Model Context Protocol (MCP) with automatic tool discovery and multiple transport options.
[](https://pypi.org/project/mcptoolkit/) [](https://pypi.org/project/mcptoolkit/) [](https://github.com/getfounded/mcp-tool-kit/blob/main/LICENSE)
📚 [Official Documentation](https://docs.mcp-tool-kit.com) | 🌐 [Website](https://mcp-tool-kit.com) | 💬 [Community](https://github.com/getfounded/mcp-tool-kit/discussions)
🚀 Built by [UsefulAI](https://usefulai.ai) | 📖 [From GitHub to Commercial Success](https://usefulai.ai/blog/articles/from-github-to-commercial-success)
🚀 Quick Install - No Git Required!
Choose your platform and run ONE command:
🖥️ Windows (PowerShell)
irm https://raw.githubusercontent.com/getfounded/mcp-tool-kit/main/install.ps1 | iex
🍎 macOS (Terminal)
bash <(curl -s https://raw.githubusercontent.com/getfounded/mcp-tool-kit/main/install.sh)
🐧 Linux (Terminal)
bash <(wget -qO- https://raw.githubusercontent.com/getfounded/mcp-tool-kit/main/install.sh)
That's it! The installer will:
- ✅ Download MCP Tool Kit (no Git needed!)
- ✅ Check for Docker (helps install if missing)
- ✅ Create desktop shortcuts
- ✅ Set up everything automatically
📦 Alternative Installation Methods
Manual Download
- Download the latest release:
- Windows: MCP-Tool-Kit-Windows.zip
- Mac/Linux: MCP-Tool-Kit-Unix.tar.gz
- Extract and run:
- Windows: Run
install.bat - Mac/Linux: Run
./install.sh
Git Installation (for developers)
df89d07b4aaeOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-tool-kit-docs --env BRAVE_API_KEY=${BRAVE_API_KEY} --env FRED_API_KEY=${FRED_API_KEY} --env NEWS_API_KEY=${NEWS_API_KEY} --env SHOPIFY_ACCESS_TOKEN=${SHOPIFY_ACCESS_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"mcp-tool-kit-docs": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"BRAVE_API_KEY": "${BRAVE_API_KEY}",
"FRED_API_KEY": "${FRED_API_KEY}",
"NEWS_API_KEY": "${NEWS_API_KEY}",
"SHOPIFY_ACCESS_TOKEN": "${SHOPIFY_ACCESS_TOKEN}"
}
}
}
}Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
health_check | read | Check the health status of the MCP server. |
initialize | read | Return initialization information including available tools. |
list_tools | read | List all registered tools and their status. |
Trust audit
CAUTIONgrade B · trust 81/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (9 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (9)
__init__.cpython-312.pyc
sdk.cpython-312.pyc
toolkit_client.cpython-312.pyc
__import__(dep)
module = importlib.import_module(f"app.tools.{module_name}")test_sdk.cpython-312.pyc
.env.template
@mdx-js/react, clsx, prism-react-renderer, react, react-dom
mcp, newsapi-python, python-dotenv, httpx, pillow, pydantic, pandas, requests
Gates applied: no_behavioural_pass.
df89d07b4aaefull audit observations/trust-audit/mcp-server/getfounded__tool-kit.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | df89d07b4aae | CAUTION | B | 81 | first audit |
Questions
What is the Tool Kit MCP server?
Agentic abstraction layer for building high precision vertical AI agents written in python for Model Context Protocol.
What tools does Tool Kit expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Tool Kit safe to connect to an agent?
With care. The audit graded it B (81/100) and found 9 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Tool Kit need?
It reads BRAVE_API_KEY, FRED_API_KEY, NEWS_API_KEY, SHOPIFY_ACCESS_TOKEN, SHOPIFY_API_KEY, SHOPIFY_API_PASSWORD and VAPI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Tool Kit run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as mcp-tool-kit-docs at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (df89d07b4aae), read on 2026-10-07. The repository is watched and re-audited when it changes.