kasra-mcp
Enables local code review and security scanning by reading files and sending them to the Kasra API for analysis, integrating with AI tools like Claude Desktop and Cursor via the Model Context Protocol.
README
kasra-mcp
Kasra MCP Server — local code review via the Model Context Protocol.
Reads files on your machine and sends them to the Kasra API for security scanning. Designed to work with AI tools like Claude Desktop, Cursor, Claude Code, and any MCP-compatible client.
Install
pip install kasra-mcp
Requires Python 3.11+.
Quick Start
# Verify installation
python3 -m kasra_mcp.server --help
The server connects to a Kasra API instance (default: http://localhost:8090).
Configuration
Environment variables:
| Variable | Default | Description |
|---|---|---|
KASRA_API_URL |
http://localhost:8090 |
Kasra API base URL |
KASRA_API_KEY |
"" |
API key for authentication |
Tools
kasra_scan_file
Scan a file or directory for security vulnerabilities.
| Parameter | Type | Description |
|---|---|---|
path |
string |
Path to a file or directory to scan |
Supports both single files and directories. Ignores common non-source files (images, binaries, .git, node_modules, etc.).
kasra_get_rules
List all loaded security rules.
| Parameter | Type | Description |
|---|---|---|
severity |
string? |
Filter by severity (P0, P1, P2) |
enabled_only |
boolean? |
Only return enabled rules |
health
Check the Kasra API connection and engine status.
Integration with AI Tools
Claude Desktop
{
"mcpServers": {
"kasra": {
"command": "python3",
"args": ["-m", "kasra_mcp.server"],
"env": {
"KASRA_API_URL": "http://localhost:8090",
"KASRA_API_KEY": "your-api-key-here"
}
}
}
}
Paste this into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).
Cursor
{
"mcpServers": {
"kasra": {
"command": "python3",
"args": ["-m", "kasra_mcp.server"],
"env": {
"KASRA_API_URL": "http://localhost:8090",
"KASRA_API_KEY": "your-api-key-here"
}
}
}
}
Claude Code
{
"mcpServers": {
"kasra": {
"command": "python3",
"args": ["-m", "kasra_mcp.server"],
"env": {
"KASRA_API_URL": "http://localhost:8090",
"KASRA_API_KEY": "your-api-key-here"
}
}
}
}
How it works
Claude Desktop / Cursor / Claude Code
│
│ stdio (JSON-RPC over stdin/stdout)
▼
┌─────────────────┐ POST /v1/scan/file ┌────────────────┐
│ kasra-mcp │ ─────────────────────────────→ │ Kasra API │
│ │ POST /v1/rules/export │ (Docker) │
│ reads local │ ←───────────────────────────── │ 193 rules │
│ file content │ findings + results │ CR scanning │
└─────────────────┘ └────────────────┘
- Claude Desktop starts
kasra-mcpas a subprocess (stdio transport) - When the user asks to scan a file, Claude calls
kasra_scan_filewith a path kasra-mcpreads the file content from local disk- Sends the content to the Kasra API via
POST /v1/scan/file - Kasra API runs 83 code review rules, returns findings
kasra-mcpreturns the results to Claude
The MCP server never stores your code — it reads, sends, and discards.
Development
git clone <repo>
cd kasra-mcp
pip install -e .
python3 -m kasra_mcp.server
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.