Rmv Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Rmv Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A simple MCP (Model Context Protocol) server with two functions to call RMV APIs for information about nearby stations and departure boards.
This project uses uv, an extremely fast Python package installer and resolver which creates and manages virtual environments (like venv). If you don't have it, see the official uv documentation to install it.
uv initBy using uv, there is no need to explicetily create a venv and install requirements. All information about the uv project is in the file pyproject.toml. Consequently, there is no requirements.txt in this repo.
.env file in the project root.ACCESS_ID to it: ACCESS_ID="your-rmv-api-access-id"ACCESS_ID from the RMV open data platform.Go and find the file .gemini/settings.json in your home directory. Add the following block:
"mcpServers": {
"rmvServer": {
"command": "uv",
"args": [
"run",
"--project",
"/YOURPATH/rmv_mcp/",
"/YOURPATH/rmv_mcp/rmv_server.py"
]
}
},
In Gemini CLI check with /mcp the new MCP server:
rmvServer - Ready (2 tools)
Tools:
- get_departureboard
- get_nearbystations~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.