What dependencies are required?
SecureAnnex MCP Server uses `uv` and the included `pyproject.toml` to handle dependencies automatically; no manual Python environment setup is needed.
@arsolutioner
基本信息
A Model Context Protocol (MCP) server for analyzing browser extension security
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"secureannex": {
"command": "uv",
"args": [
"--directory",
"/path/to/secure-annex-mcp",
"run",
"secure_annex_mcp"
],
"env": {
"SECUREANNEX_API_KEY": "your_api_key_here"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
SecureAnnex MCP Server is a Model Context Protocol server for analyzing browser extension security. It provides tools for querying, analyzing, and evaluating security aspects of browser extensions—including vulnerability detection, signature checking, code review, and more—via the SecureAnnex API. It is designed for use with Claude Desktop and other MCP-compatible clients.
Download or clone the repository and ensure pyproject.toml is present. Configure Claude Desktop by editing claude_desktop_config.json to point uv at the server directory and set the SECUREANNEX_API_KEY environment variable. Once configured, Claude can invoke tools such as search_extensions, get_extension_vulnerabilities, get_extension_signatures, and others directly through natural language.
SecureAnnex MCP Server uses `uv` and the included `pyproject.toml` to handle dependencies automatically; no manual Python environment setup is needed.
Obtain your API key from the SecureAnnex service and set it as the `SECUREANNEX_API_KEY` environment variable in the Claude Desktop configuration.
Yes, the README explicitly shows integration with VirusTotal MCP to check domain reputation, and Claude can combine tools from multiple servers in a single workflow.
No. The server is designed to work with Claude Desktop, which automatically handles all dependencies using `uv` and the `pyproject.toml` file.
The server runs via stdio, launched by Claude Desktop using the `uv run secure_annex_mcp` command. Authentication is handled through the API key in the environment variables.

Build custom POS apps with your AI agent. Final's MCP server lets developers scaffold checkout flows, adapt vetted screen blueprints for counter POS, self-checkout kiosks, restaurant ordering and payment terminals, previ
JiCo for Jira & Confluence: local MCP server for Jira Data Center - redacts personal data before the AI model, holds every write for approval

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app
评论