VAARA 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
VAARA 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
VAARA 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/vaaraio/vaara
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"vaara": {
"command": "npx",
"args": ["-y", "vaara"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 VAARA 执行以下任务... Claude: [自动调用 VAARA MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"vaara": {
"command": "npx",
"args": ["-y", "vaara"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="docs/vaara-wordmark-dark.png"> <img src="docs/vaara-wordmark-light.png" alt="Vaara" width="900"> </picture> </p>
<p align="center"> <a href="https://pypi.org/project/vaara/"><img src="https://img.shields.io/pypi/v/vaara.svg" alt="PyPI"></a> <a href="https://github.com/vaaraio/vaara/blob/main/LICENSE"><img src="https://img.shields.io/pypi/l/vaara.svg" alt="License"></a> <a href="https://github.com/vaaraio/vaara/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/vaaraio/vaara/ci.yml?branch=main&label=tests" alt="CI"></a> <a href="https://scorecard.dev/viewer/?uri=github.com/vaaraio/vaara"><img src="https://api.scorecard.dev/projects/github.com/vaaraio/vaara/badge" alt="OpenSSF Scorecard"></a> <a href="https://www.bestpractices.dev/projects/12612"><img src="https://www.bestpractices.dev/projects/12612/badge" alt="OpenSSF Best Practices"></a> <a href="https://huggingface.co/spaces/vaaraio/vaara"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Space-blue" alt="Hugging Face Space"></a> </p>
Vaara is the open-source runtime evidence layer for AI agents under the EU AI Act. It sits in front of an agent's tool calls, gates each one against your policy, and writes a tamper-evident record an outside party can verify. When a regulator, an auditor, or a public-sector buyer needs proof of what your agent actually did and why, that record is the answer. Runs entirely in your own environment. No SaaS, no telemetry.
EU AI Act Article 12 record-keeping is the driver. The same trail answers any "show me exactly what the agent did" demand: procurement validation, incident reconstruction, SOC 2 evidence.
pip install vaara
Python 3.10+. Zero runtime deps. Optional XGBoost classifier: pip install vaara[ml]. Releases ship with SLSA Build Level 3 provenance, verifiable via slsa-verifier verify-artifact.
build-bundle is the issuer side of the same file. Where verify-bundle checks a bundle, build-bundle produces it, from the receipt and whatever identity, signature, inclusion, consistency, and revocation material you hold:
vaara build-bundle --from-dir ./pieces --out evidence-bundle.json
vaara verify-bundle evidence-bundle.json
It writes the exact document verify-bundle reads, then loads it back and reports the verdict, so producing and checking the evidence is one closed loop over one file.
from vaara.pipeline import InterceptionPipeline
pipeline = InterceptionPipeline()
result = pipeline.intercept(
agent_id="agent-007",
tool_name="fs.write_file",
parameters={"path": "/etc/service.yaml", "content": "..."},
agent_confidence=0.8,
)
if result.allowed:
pipeline.report_outcome(result.action_id, outcome_severity=0.0)
else:
print(result.reason)
report_outcome closes the loop: the signal weights reweight based on which ones predicted the outcome.
The same scorer and audit trail are available over HTTP for non-Python agents and control planes that prefer a network boundary.
pip install 'vaara[server]'
vaara serve --host 0.0.0.0 --port 8000
curl -sX POST http://localhost:8000/v1/score \
-H 'content-type: application/json' \
-d '{"tool_name":"tx.transfer","agent_id":"agent-007","base_risk_score":0.5}'
Wire contract in docs/openapi.yaml. Operator endpoints include POST /v1/policy/reload (atomic hot policy swap) and named detectors POST /v1/detect/injection and POST /v1/detect/pii, with matching CLI subcommands that exit non-zero on detection for CI gating.
The first-party TypeScript client ships on npm as @vaara/client: typed wrappers over every v1 endpoint, Node 18+, ESM. JS/TS agents call Vaara without a Python sidecar.
import { VaaraClient } from "@vaara/client";
const vaara = new VaaraClient({ baseUrl: "http://localhost:8000" });
const r = await vaara.score({ tool_name: "tx.transfer", agent_id: "agent-007", base_risk_score: 0.6 });
if (r.decision === "deny") throw new Error("blocked");
VAARA是一个开源的MCP工具,提供了EU AI Act Article 12运行时证据的参考实现
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
经综合评估,VAARA 在MCP工具赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | vaara |
| 原始描述 | 开源MCP工具:Open-source reference implementation for EU AI Act Article 12 runtime evidence. 。⭐6 · Python |
| Topics | mcpai-actai-governance |
| GitHub | https://github.com/vaaraio/vaara |
| License | Apache-2.0 |
| 语言 | Python |
收录时间:2026-06-09 · 更新时间:2026-06-09 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端