re-yara
MCP server wrapping the YARA pattern-matching engine for binary triage, enabling users to compile and scan files against analyst-defined YARA rules.
README
re-yara
MCP server wrapping the YARA pattern-matching engine for binary triage.
re-yara is intentionally rule-agnostic: the server compiles
whatever rule directory the analyst points it at, then scans files
or directories against the compiled rules. No rules are bundled
with the plugin — YARA rules describe categories of binary
behaviour (e.g. encrypted-VM bytecode interpreter dispatcher,
MBA-obfuscated arithmetic routine, legacy disc-based protection
handshake) and writing them is an analyst decision, not a plugin
one.
Tools
| Tool | What it does |
|---|---|
check_yara |
Health check — return YARA version + whether yara-python is importable |
compile_rules |
Compile all *.yar / *.yara files under a directory into a YARA ruleset |
scan_binary |
Run a compiled ruleset against a single file |
scan_directory |
Walk a directory and run the compiled ruleset against every file |
Install
Part of the RE-AI plugin; ./install.sh installs the package. To
install standalone:
pip install -e ./servers/re-yara
Requires the yara C library (libyara) at runtime — yara-python
links against it. Most package managers ship yara as a system
package; on Debian/Ubuntu:
sudo apt-get install yara libyara-dev
Run
re-yara # stdio transport (default for MCP)
python -m re_yara # equivalent
Workflow
- Author or download a directory of
*.yarfiles. Each rule describes a category of behaviour the analyst wants to find. - Call
compile_rules(rules_dir=<path>)to validate + compile. - Call
scan_binary(path=<file>, rules_dir=<path>)for a single file, orscan_directory(path=<dir>, rules_dir=<path>)for a whole tree.
compile_rules is the heavy step (parses every rule file). The
scan tools re-compile as needed — they're cheap if the rules
haven't changed.
Why no bundled rules
YARA rules are an analyst artefact: they describe what you are
looking for, which is a question only the user can answer. The
plugin gives the engine; the user brings the policies. The
server is also compatible with the signature-base and
[MalwareBazaar] rule collections — point rules_dir at any of
them.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。