crowdsec-ops-mcp
Local MCP server for CrowdSec operations, enabling inspection of decisions/alerts, summaries, and generation of audited single-IP action proposals without executing changes.
README
crowdsec-ops-mcp
crowdsec-ops-mcp is a local MCP server for CrowdSec operations.
It exposes CrowdSec decisions, alerts, summaries, and safe single-IP action proposals to MCP clients. It is intentionally CrowdSec-only: it does not connect to VictoriaMetrics, VictoriaLogs, Grafana, Snort, reverse proxies, or Docker.
Supported runtime reads use CrowdSec LAPI. Actual cscli reads or cscli execution are not supported by the MCP today; write tools only generate cscli command text for an operator to review and run outside the MCP if appropriate.
Contents
What You Can Do
- Check whether the CrowdSec backend is reachable.
- Inspect active decisions and recent alerts for one IP.
- Summarize recent CrowdSec activity.
- Find top offending source IPs.
- Generate scenario-tuning proposals from repeated alert patterns.
- Prepare audited single-IP ban, allow, or unban commands for manual review.
Write tools do not execute CrowdSec changes. They validate a single IP, prepare a plausible cscli command for an operator to review, append the prepared intent to the JSON Lines audit log, and return executed=false.
Getting Started
See ONBOARDING.md for installation, deployment, MCP client configuration, first tool calls, safety notes, and troubleshooting.
See docs/decision-inventory-example.md for example decision_inventory tool calls.
Tools
crowdsec_health(include_sample_counts=false)inspect_ip(ip, window?)security_summary(window?)top_offenders(window?)recent_crowdsec_decisions(window?)decision_inventory(action?, origin?, scenario?, country?, asn?, ip?, limit?, expiring_soon_hours?, long_lived_days?)recent_crowdsec_alerts(window?)suggest_scenario(window?)unban_ip(ip, reason?, execute=false)allow_ip(ip, duration?, reason, execute=false)ban_ip(ip, duration?, reason, execute=false)
Configuration
| Variable | Purpose |
|---|---|
CROWDSEC_LAPI_URL |
CrowdSec LAPI base URL. Required for supported read operation. |
CROWDSEC_LAPI_KEY |
CrowdSec LAPI key for decision reads. |
CSCLI_PATH |
Command name/path used only when formatting prepared potential_cscli_command text. The MCP does not run cscli. |
DEFAULT_WINDOW |
Default lookback window, defaults to 24h. |
WRITE_AUDIT_LOG_PATH |
JSON Lines audit trail for prepared write intents, defaults to crowdsec-write-audit.jsonl. |
LOG_LEVEL |
Python log level, defaults to INFO. |
Project Documents
- ONBOARDING.md: user installation and first-use guide
- CHANGELOG.md: version history
- docs/decision-inventory-example.md: example
decision_inventorytool calls - docs/agent-usage.md: agent prompt patterns and investigation guidance
- docs/development.md: local development workflow
- docs/roadmap.md: project roadmap
- docs/release-notes/v0.2.1.md: release notes for
v0.2.1 - docs/RELEASE.md: release process
- docs/pull-request-rules.md: pull request rules
- docs/release-notes-template.md: release notes template
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。