aiops-mcp
A self-contained, security-first, EU-sovereign unified AI-operations MCP server that fuses a live bitemporal fleet model, a drift engine, and a tiered audited actuator into one control plane.
README
aiops-mcp
praxis, the unified AI-operations MCP.
Status: v0 implemented and gated.
make ci-successis green (ruff + mypy strict
- pytest + the schema-drift guard + the dispatch eval gate), and each of the nine invariants has a passing test. The repository is now in iterative security hardening (audit waves ADR-0011 through ADR-0013; open items in
docs/backlog.md). The original build brief isdocs/first-session.md.
What it is
praxis is a self-contained, security-first, single-operator-operable,
EU-sovereign unified AI-operations MCP server. It fuses three things into one
control plane:
- A live bitemporal model of the fleet. Hosts, services, packages, storage, networks, identities, and alerts as typed vertices and edges, with every fact carrying four timestamps and never being deleted (corrections supersede). The source of truth.
- A drift engine. Observed host state vs desired state (IaC plan, config baseline, or an operator-blessed known-good snapshot), with structured drift findings and human-gated convergence.
- A tiered, audited actuator. A single execution path that classifies every action T0-T3, gates state-changing actions behind human confirmation, and wraps the right tool per host type (ssh/ansible/opentofu/runbooks/talosctl/redfish/ cloud) instead of reinventing it.
It implements everything itself. It has zero runtime dependency on, and no imports from, any other repository.
Why
It is the engineered successor to a hand-run fleet gateway: graduated autonomy made load-bearing in code (not just a design note), drift detection formalized out of manual markdown baselines into a queryable bitemporal store, scattered state unified, and flat skills given a real registry and router. Security-first, for real production deployments.
Quickstart
praxis is self-contained: the default path is the SQLite store over stdio with no
external services.
uv sync --extra dev # add --extra postgres for the production store backend
make check # ruff + mypy strict + pytest
make ci-success # the above plus the schema-drift guard and eval gate
python -m praxis # serve over stdio (JSON-RPC 2.0); refuses unsafe HTTP binds
Configuration is PRAXIS_-prefixed and bound once at import (src/praxis/config.py).
For the design rationale, the nine non-negotiable invariants, and the build sequence,
read docs/first-session.md.
Layout
See docs/first-session.md for the full tree. The spine: src/praxis/execution/
(the single audited executor), src/praxis/store/ (the pluggable bitemporal
store), src/praxis/drift/ (the drift engine), src/praxis/actuation/ (tool
adapters), src/praxis/tools/ (the MCP surface), and docs/{adr,stpa}/ plus
docs/backlog.md (governance-as-code).
Governance
- Decisions:
docs/adr/(Architecture Decision Records). - Safety and security requirements:
docs/stpa/(System-Theoretic Process Analysis, including STPA-Sec). - Work tracking:
docs/backlog.md(stableBL-NNNids). - Compliance mapping:
docs/governance/(EU AI Act, NIS2/NISG, CRA, GDPR, ISO 27001).
License
Apache-2.0 (see LICENSE) and NOTICE.
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。