SecOps-MCP-Server

SecOps-MCP-Server

Enterprise MCP server for Google SecOps (Chronicle) SIEM/SOAR, enabling alert triage, UDM telemetry search, YARA-L detection rule management, log ingestion, and parser administration via Streamable HTTP.

Category
访问服务器

README

Google SecOps (Chronicle) MCP Server (Streamable HTTP)

Enterprise Model Context Protocol (MCP) server providing Google SecOps (Chronicle) SIEM/SOAR telemetry, alert triage, Universal Data Model (UDM) search, and YARA-L detection rule management using Streamable HTTP (streamable-http) transport—the current MCP specification standard.


🌟 Overview: Streamable HTTP Transport

Streamable HTTP is the standard remote transport for Model Context Protocol (MCP) servers:

  • Unified Endpoint (/mcp): Single endpoint for client-to-server messaging, tool discovery, and bi-directional communication.
  • Production Scalability: Seamlessly deployed to stateless and containerized platforms like Google Cloud Run.
  • Container Health Probes: Built-in /healthz liveness and readiness probes.
  • Enterprise Security: Native Google Cloud IAM authentication (roles/run.invoker) with OAuth2/OIDC token support.

🛠️ Implemented SecOps Tools (All 29 Official Tools)

1. Security Investigation & Alert Tools

  • search_security_events: Searches SecOps events via natural language or UDM queries.
  • get_security_alerts: Retrieves alerts filtered by severity (CRITICAL, HIGH, etc.) and status.
  • get_security_alert_by_id: Fetches detailed alert metadata and MITRE ATT&CK mapping.
  • do_update_security_alert: Updates triage status and appends analyst notes.
  • lookup_entity: 360-degree risk telemetry profile for IP, Domain, Hostname, User, or Hash.
  • get_ioc_matches: Retrieves Indicators of Compromise matches over a lookback window.
  • get_threat_intel: Query SecOps SecLM threat intelligence insights.

2. Detection Rules Management

  • list_security_rules: Lists custom and curated YARA-L detection rules.
  • search_security_rules: Searches detection rules using regex patterns or keywords.
  • get_rule_detections: Retrieves detections triggered by a specific rule.
  • list_rule_errors: Lists execution or compilation errors for rules.
  • create_rule: Creates new YARA-L 2.0 detection rules.
  • test_rule: Backtests detection rules against historical telemetry.
  • validate_rule: Validates syntax and structure of YARA-L definitions.

3. Log Ingestion Tools

  • ingest_raw_log: Ingests raw log payloads (JSON, XML, CEF, syslog).
  • ingest_udm_events: Ingests structured Universal Data Model events.
  • get_available_log_types: Enumerate supported log types (Cloud Audit, EDR, Okta, Zscaler, etc.).

4. Parser Management Tools

  • create_parser: Creates custom log parsers (CBN syntax).
  • get_parser: Retrieves parser configuration and filtering code.
  • activate_parser: Activates parser for live ingestion processing.
  • deactivate_parser: Deactivates an active parser.
  • run_parser_against_sample_logs: Tests parser rules against sample log strings.

5. Data Tables & Reference Lists

  • create_data_table / add_rows_to_data_table / list_data_table_rows / delete_data_table_rows
  • create_reference_list / get_reference_list / update_reference_list

🚀 Quick Start: Run Locally

1. Install Dependencies

pip install -r requirements.txt

2. Start the Server

export PORT=8080
export HOST=0.0.0.0
python server.py

The Streamable HTTP server is now accessible at:

  • Streamable HTTP Endpoint: http://localhost:8080/mcp
  • Health Probe: http://localhost:8080/healthz

☁️ One-Click Deployment to Google Cloud Run

Deploy directly using the automated deployment script:

chmod +x deploy.sh
./deploy.sh

Deployment Steps Executed:

  1. [Step 1/5] Custom Variables: Loads .env file and merges custom variables.
  2. [Step 2/5] Enable APIs: Enables Cloud Run, Cloud Build, and Chronicle APIs.
  3. [Step 3/5] Cloud Run Deploy: Deploys container with Streamable HTTP transport.
  4. [Step 4/5] IAM Policy Bindings: Grants roles/run.invoker to agent runner SA and active user.
  5. [Step 5/5] Verification: Checks /healthz probe and prints endpoint URLs.

🧪 Testing and Inspection

Option A: Run Test Suite

python3 test_client.py

Option B: Using the MCP Inspector UI

Launch the official Model Context Protocol Inspector:

npx -y @modelcontextprotocol/inspector

Connect via HTTP transport to http://localhost:8080/mcp.

Option C: Connect via Google ADK / GenAI Agent

Set the environment variable in your agent configuration:

export SECOPS_MCP_URL="https://<your-cloud-run-service-url>/mcp"

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选