Install
$ agentstack add mcp-opengerwin-mcp ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
🧩 OpenGerwin MCP Servers
Open-source MCP (Model Context Protocol) servers that give AI agents superpowers.
Each server is a standalone package — install only what you need.
Available Servers
| Server | Description | Status | Install | |---|---|---|---| | 🔍 Google Agent Platform Docs | Search & read Google AI platform documentation (GEAP + Vertex AI). 3400+ pages. | ✅ Ready | pip install mcp-google-agent-platform-docs | | 🚧 More coming soon | Bitrix24, WordPress, and others | Planned | — |
What is MCP?
Model Context Protocol is an open standard that lets AI assistants (Claude, Cursor, VS Code Copilot, etc.) connect to external tools and data sources.
Instead of hallucinating API details, your AI can look up the real documentation in real-time.
┌─────────────────┐ MCP ┌──────────────────────┐
│ AI Assistant │◄────────────►│ MCP Server │
│ (Claude, etc.) │ (stdio) │ (your tools + data) │
└─────────────────┘ └──────────────────────┘
Quick Start
1. Pick a server from the table above
2. Install it
pip install mcp-google-agent-platform-docs
3. Connect to your AI client
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"google-agent-platform-docs": {
"command": "mcp-google-agent-platform-docs"
}
}
}
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"google-agent-platform-docs": {
"command": "mcp-google-agent-platform-docs",
"transport": "stdio"
}
}
}
VS Code
Add to .vscode/mcp.json:
{
"mcpServers": {
"google-agent-platform-docs": {
"command": "mcp-google-agent-platform-docs",
"transport": "stdio"
}
}
}
Antigravity (Google)
Add to ~/.gemini/antigravity/mcp_config.json:
{
"mcpServers": {
"google-agent-platform-docs": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-google-agent-platform-docs",
"run",
"mcp-google-agent-platform-docs"
]
}
}
}
Server Details
🔍 Google Agent Platform Docs
> Repo: OpenGerwin/mcp-google-agent-platform-docs > PyPI: pip install mcp-google-agent-platform-docs
MCP server providing real-time access to Google's AI platform documentation:
- Gemini Enterprise Agent Platform (GEAP) — 2300+ pages (current platform)
- Vertex AI Generative AI — 1100+ pages (legacy archive)
Tools: | Tool | Description | |---|---| | search_docs | Full-text search across documentation | | get_doc | Read any documentation page | | list_sections | Browse documentation structure | | list_models | Reference of all available AI models |
Contributing
We welcome contributions! Whether it's:
- 🐛 Bug reports and fixes
- ✨ New MCP server ideas
- 📖 Documentation improvements
Each server has its own repo — please open issues and PRs there.
For general questions or ideas about new servers, use Discussions in this repo.
License
All servers are released under the [MIT License](LICENSE).
OpenGerwin — Open-source tools for AI agents
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: OpenGerwin
- Source: OpenGerwin/mcp
- License: MIT
- Homepage: https://gerwin.io
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.