ModelsAtlas
Explore
Atlas / MCP servers / getasterisk / Asterisk

AsteriskSAFE

mcp/getasterisk/asterisk
MCP server by getasterisk · ai · claude · claude 3 7 sonnet · Audited 2026-10-09
⚑ Report / re-scanSource ↗

Asterisk Model Context Protocol (MCP) server.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
4 4r · 0w · 0d
Transport
—
License
Apache-2.0
Stars
33
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

A Model Context Protocol (MCP) server that provides security scanning capabilities for code snippets, codebases, and verification of code changes.

Overview

Asterisk MCP Server is a middleware component that connects to the Asterisk security API to provide real-time security analysis of code. It implements the Model Context Protocol (MCP) to expose security scanning tools to AI assistants like Claude, Cursor, Cline, Windsurf, etc. enabling them to analyze code for security vulnerabilities.

Architecture

flowchart LR
IDE["IDE / Code Editor"]  |MCP Protocol| MCP["Asterisk MCP Server"]
MCP  |HTTP/HTTPS| API["Asterisk Vulnerability Scanner API"]

classDef primary fill:#6696FF,stroke:#333,stroke-width:1px,color:white;
classDef secondary fill:#45556B,stroke:#333,stroke-width:1px,color:white;
classDef tertiary fill:#FFCC00,stroke:#333,stroke-width:1px,color:black;

class IDE primary;
class MCP secondary;
class API tertiary;

Features

  • Code Snippet Scanning: Analyze individual code snippets for security vulnerabilities
  • Codebase Scanning: Scan multiple files for security issues with accurate context coverage
  • Change Verification: Verify if code changes in your chat history introduce security vulnerabilities
  • Beautiful Settings UI: Configure the server through a graphical interface
  • Flexible Transport: Support for stdio and SSE transport protocols
  • Comprehensive Logging: Detailed logging with configurable verbosity

Requirements

  • Python 3.10+
  • pipx / uvx
  • httpx
  • mcp[cli]
  • dearpygui (for settings UI)

Usage

{
"mcpServers": {
"asterisk-mcp": {
"command": "pipx",
"args": [
"run",
"asterisk-mcp-server",
"--api-url",
"https://api.mcp.asterisk.so",
"--transport",
"stdio",
"--key",
"YOUR_API_KEY"
],
"timeout": 3600
}
}
}

Configurati

Read from source at commit 1e1319f85e91OBSERVED · 2026-10-09
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add asterisk-mcp-server -- uvx asterisk-mcp-server
claude-desktop
{
  "mcpServers": {
    "asterisk-mcp-server": {
      "command": "uvx",
      "args": [
        "asterisk-mcp-server"
      ]
    }
  }
}
03

Exposed tools (4)

4 read · 0 write · 0 destructive.

ToolRiskDescription
scan_codebaseread
scan_snippetread
settingsread
verifyread
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeWARN
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (5 observation(s))
Shell
declared (1 observation(s))
Dependencies
pinned
Secrets in source
none-found

Findings (1)

MEDIUMInformation disclosure · disclose.log_secret · CWE-209, CWE-532
asterisk_mcp_server/server.py:703
logger.info(f"API key: {'[SET]' if config['api_key'] else '[NOT SET]'}")

Gates applied: no_behavioural_pass.

Audited 2026-10-09 · audit v0.4.1 · source sha 1e1319f85e91full audit observations/trust-audit/mcp-server/getasterisk__asterisk.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-091e1319f85e91SAFEB89first audit
06

Questions

What is the Asterisk MCP server?

Asterisk Model Context Protocol (MCP) server.

What tools does Asterisk expose?

4 in total: 4 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Asterisk safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Asterisk need?

No credential environment variables were found in its source, so it appears to need none.

How current is this page?

The grade is for one exact copy of the source (1e1319f85e91), read on 2026-10-09. The repository is watched and re-audited when it changes.

Advertisement