Evernotemcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Evernotemcp (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.
An MCP (Model Context Protocol) server that connects Claude Desktop to Evernote, enabling you to list notebooks/notes and create new notes directly from conversations.
Copy .env.example to .env and fill in your credentials:
cp .env.example .envEdit .env:
EVERNOTE_ACCESS_TOKEN=your-access-token-here
EVERNOTE_ENVIRONMENT=production # or "sandbox" for testing
EVERNOTE_USE_MOCK=falsedocker build -t evernote-mcp .Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"evernote": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "EVERNOTE_ACCESS_TOKEN",
"-e", "EVERNOTE_ENVIRONMENT",
"evernote-mcp"
],
"env": {
"EVERNOTE_ACCESS_TOKEN": "your-access-token-here",
"EVERNOTE_ENVIRONMENT": "production"
}
}
}
}After configuring, restart Claude Desktop. You should see Evernote tools available.
For development without Evernote credentials, use the mock client:
EVERNOTE_USE_MOCK=true python -m evernote_mcp.serverEVERNOTE_USE_MOCK=true mcp dev src/evernote_mcp/server.pypip install -e ".[dev]"
pytestOnce configured, you can ask Claude:
evernote-mcp/
├── src/evernote_mcp/
│ ├── server.py # MCP server (FastMCP)
│ ├── client_base.py # Abstract client interface
│ ├── client_mock.py # Mock client for testing
│ ├── client_evernote.py # Real Evernote API client
│ ├── models.py # Data models
│ └── enml.py # Markdown → ENML conversion
├── Dockerfile
└── pyproject.tomlMIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.