Mcp Doc Server — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mcp Doc Server (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.
Example Model Context Protocol (MCP) servers from the Medium article The Model Context Protocol (MCP): Fundamentals, Real-World Applications, and Building AI Agent Integrations.
Two self-contained MCP servers that any compatible AI host (Claude Desktop, Cursor, or a custom agent) can discover and use automatically.
`server.py` -- Document database with three tools:
search_documents(query) -- search documents by titleget_document(doc_id) -- retrieve a document by IDcreate_document(title, content, author) -- create a new document`task_server.py` -- Task tracker with two tools:
search_tasks(query) -- search tasks by title keywordget_tasks_by_status(status) -- get tasks by status (todo, in_progress, done)# Clone the repo
git clone https://github.com/deepujain/mcp-doc-server.git
cd mcp-doc-server
# Create virtual environment and install dependencies
uv venv
source .venv/bin/activate
uv sync# Document server
mcp dev server.py
# Task tracker (in a separate terminal)
mcp dev task_server.pyThe Inspector opens in your browser. Click Tools > List Tools, select a tool, fill in the input, and hit Run Tool.
Add to .cursor/mcp.json in your project root:
{
"mcpServers": {
"document-db": {
"command": "uv",
"args": ["--directory", "/path/to/mcp-doc-server", "run", "server.py"]
},
"task-tracker": {
"command": "uv",
"args": ["--directory", "/path/to/mcp-doc-server", "run", "task_server.py"]
}
}
}Replace /path/to/mcp-doc-server with the actual path. Restart Cursor, then ask in agent chat:
"Find the Q1 report and summarize it"
"What tasks are in progress?"
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"document-db": {
"command": "uv",
"args": ["--directory", "/path/to/mcp-doc-server", "run", "server.py"]
},
"task-tracker": {
"command": "uv",
"args": ["--directory", "/path/to/mcp-doc-server", "run", "task_server.py"]
}
}
}Restart Claude Desktop. The tools appear automatically.
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.