asterisk
Asterisk Model Context Protocol (MCP) server.
claude mcp add --transport stdio winfunc-asterisk-mcp-server pipx run asterisk-mcp-server --api-url https://api.mcp.asterisk.so --transport stdio --key YOUR_API_KEY \ --env API_KEY="YOUR_API_KEY" \ --env API_URL="https://api.mcp.asterisk.so"
How to use
The Asterisk MCP Server provides security scanning capabilities by connecting to the Asterisk Vulnerability Scanner API and exposing its tools through the MCP protocol. It offers three primary actions you can invoke from your IDE or chat-enabled assistant: scan_snippet to analyze a single code snippet for vulnerabilities, scan_codebase to assess multiple files with context-aware results, and verify to check whether recent changes introduce security issues. The server also supports a graphical settings UI (settings) and can operate over stdio or server-sent events (SSE) transports, giving you flexibility in how results are streamed to your editor or assistant. To get started, configure the MCP server with your API URL and API key, then use the provided MCP commands from your IDE or integration to run scans or verification on your code.
How to install
Prerequisites:
- Python 3.10+
- pipx or uvx (for Python package installation)
- httpx, mcp[cli], dearpygui (for settings UI)
Installation steps (using pipx):
- Ensure Python and pipx are installed
- macOS/Linux: python3 -m ensurepip --upgrade
- Windows: python -m ensurepip --upgrade
- Install pipx: python3 -m pip install --user pipx
- Add pipx to PATH if needed
- Install the MCP server package
- pipx install asterisk-mcp-server or to run directly without install: pipx run asterisk-mcp-server
- Verify installation
- pipx list (should show asterisk-mcp-server)
- Run the server with your configuration
- Use the example from the README to supply --api-url and --key
Optional (uvx):
- Install uvx via your preferred method
- Install the package that provides the MCP server following the project’s uvx instructions
- Run the server and pass the same API URL and key as in the pipx example
Additional notes
Tips and notes:
- Ensure the API URL and API key are valid and have the necessary permissions on the Asterisk API.
- If you encounter timeouts during large scans, adjust the --timeout value in your MCP config.
- The server supports two transports: stdio (default for local editor integrations) and SSE (for streaming results). Choose based on your editor/IDE capabilities.
- If you use the settings UI (via the settings command), you can adjust logging level, transport, and server name without restarting the process.
- Environment variables in the config can be used to store sensitive values; never commit real API keys in code or config files.
- For troubleshooting, verify network access to https://api.mcp.asterisk.so and confirm the API key has not expired.
Related MCP Servers
mcp -odoo
A Model Context Protocol (MCP) server that enables AI assistants to securely interact with Odoo ERP systems through standardized resources and tools for data retrieval and manipulation.
boilerplate
TypeScript Model Context Protocol (MCP) server boilerplate providing IP lookup tools/resources. Includes CLI support and extensible structure for connecting AI systems (LLMs) to external data sources like ip-api.com. Ideal template for creating new MCP integrations via Node.js.
mcp_autogen_sse_stdio
This repository demonstrates how to use AutoGen to integrate local and remote MCP (Model Context Protocol) servers. It showcases a local math tool (math_server.py) using Stdio and a remote Apify tool (RAG Web Browser Actor) via SSE for tasks like arithmetic and web browsing.
janee
Secrets management for AI agents via MCP • @janeesecure
vscode-context
MCP Server to Connect with VS Code IDE
django-admin
Expose Django admin models to MCP (Model Context Protocol) clients. Add a mixin to your ModelAdmin classes and let AI assistants like Claude perform CRUD operations, execute admin actions, and explore relationships—all respecting Django's permission system.
