Complexipy Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Complexipy 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 Model Context Protocol (MCP) server that wraps complexipy to provide cognitive complexity analysis for Python codebases. This server uses the complexipy Python API for accurate and robust analysis.
.py files in a directory and filter by complexity threshold.pandas for efficient data filtering and sorting.You can run the server directly using uvx (no installation required):
uvx complexipy-mcpAdd the following configuration to your MCP client settings (e.g., claude_desktop_config.json):
{
"mcpServers": {
"complexipy": {
"command": "uvx",
"args": [
"complexipy-mcp"
]
}
}
} uv sync uv run complexipy-mcp#### Local Configuration for Claude Desktop
If you are developing locally, point the configuration to your local setup:
{
"mcpServers": {
"complexipy": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/complexipy-mcp",
"run",
"complexipy-mcp"
]
}
}
}scan_directoryScans a directory for files exceeding a cognitive complexity threshold.
directory_path (string): Absolute path to the directory to scan.threshold (integer): Complexity limit (default: 15). [
{
"file_path": "/abs/path/to/file.py",
"complexity": 25,
"functions": [
{
"name": "function_name",
"complexity": 10,
"line_start": 5,
"line_end": 15
}
],
"status": "exceeds_threshold"
}
]scan_fileScans a single file for cognitive complexity.
file_path (string): Absolute path to the file.threshold (integer): Complexity limit (default: 15).~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.