Agent Audit Logger Mcp

io.github.CSOAI-ORG由 GitHub 账号 CSOAI-ORG 发布v1.1.10更新于 Nov 4, 2026

Hash-chained HMAC-signed audit log MCP for A2A (agent-to-agent) calls. Every tool-call, agent-ha...

发布方自己的服务:audit.domains - Domain Valuation

已验证Streamable HTTP可网页运行开发者工具安全与监控

概览

AI 生成的概览

将智能体的工具调用、交接与决策记录为哈希链式 HMAC 签名的审计条目,并支持链校验与检索。

可以做什么
  • 写入工具调用、智能体交接与决策的防篡改审计记录
  • 校验哈希链,确认记录未被改动
  • 检索已保存的审计日志
  • 在付费方案下生成合规报告与每日签名证明
适用场景
当你需要为 AI 智能体的行为留下防篡改记录时使用,例如用于审计、事件响应或 AI 治理文档。
运行要求
可作为远程端点运行,也可作为本地 Python 包(pip 安装或 uvx)以 stdio 运行。清单未声明认证、环境变量或请求头。付费方案与签名证明需要订阅。
安装前请注意
README 大量推销付费方案与 Stripe 结账链接,价格说法应视为营销内容。记录使用 HMAC 签名,密钥管理很关键;清单未声明任何凭据,需自行确认签名密钥来源。日志内容可能包含敏感的智能体活动,使用远程端点时这些数据会发送给第三方。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Agent Audit Logger Mcp,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.CSOAI-ORG%2Fagent-audit-logger-mcp/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "agent-audit-logger": {
      "type": "http",
      "url": "https://api.meok.ai/v1/a2a/audit-logger"
    }
  }
}

README

[MCP Scorecard: 78/100]

Agent Audit Logger MCP

[MEOK AI Labs] [EU AI Act] [License] [PyPI]

Hash-chained HMAC-signed audit log MCP for A2A (agent-to-agent) calls

Hash-chained HMAC-signed audit log MCP for A2A (agent-to-agent) calls. Every tool-call, agent-handoff, decision gets a tamper-evident signed record. EU AI Act Art 12 automatic logs, DORA Art 17 ICT incident logs, ISO 42001 clause 9 monitoring — auditor-ready end-of-day attestations. By MEOK AI Labs.


🚀 Quick Start

bash
# Install via pippip install agent_audit_logger_mcp
# Or install via Smitherynpx -y @smithery/cli@latest install agent-audit-logger-mcp --client claude

✨ Features

  • HMAC-signed audit logs
  • Hash-chained integrity
  • A2A agent tracking
  • Compliance reporting
  • Tamper-proof records

📖 Documentation

🛡️ Compliance

This MCP server is built with EU AI Act compliance built-in:

  • ✅ Article 9 — Risk Management System
  • ✅ Article 13 — Transparency & Instructions for Use
  • ✅ Article 15 — Bias Detection & Testing
  • ✅ Article 26 — FRIA Support (where applicable)
  • ✅ Article 50 — AI Content Watermarking (where applicable)
  • Free — 1,000 log entries/day, ephemeral, chain verification
  • Pro £199/mo — unlimited + signed end-of-day attestations + chain integrity reports — subscribe
  • Enterprise £1,499/mo — multi-tenant + SIEM webhook push + retention policy — subscribe

Need help getting compliant? Book a free 15-min diagnostic →

🏢 Enterprise

Need custom development, SLA guarantees, or white-label deployment?

  • Pro: £79/mo — Full MCP suite + EU AI Act tracking
  • Enterprise: £499/mo — Custom dev + SLA + Dedicated support

View Pricing → | Contact Sales →

🤝 Part of the MEOK Ecosystem

This server is part of the MEOK AI Labs ecosystem — 26 PyPI packages · ~16,300 monthly installs.

DomainPurpose
councilof.aiEU AI Act compliance marketplace
safetyof.aiAI safety & monitoring
meok.aiSovereign AI platform
cobolbridge.aiLegacy modernization

📜 License

MIT © CSOAI-ORG


Built with 💜 by MEOK AI Labs · UK Companies House 16939677

- **Prompt Injection Firewall** → `uvx agent-prompt-injection-firewall-mcp` · [PyPI](https://pypi.org/project/agent-prompt-injection-firewall-mcp/) · [GitHub](https://github.com/CSOAI-ORG/agent-prompt-injection-firewall-mcp) - **Data Residency** → `uvx agent-data-residency-mcp` · [PyPI](https://pypi.org/project/agent-data-residency-mcp/) · [GitHub](https://github.com/CSOAI-ORG/agent-data-residency-mcp) - **Certified Handoff** → `uvx agent-handoff-certified-mcp` · [PyPI](https://pypi.org/project/agent-handoff-certified-mcp/) · [GitHub](https://github.com/CSOAI-ORG/agent-handoff-certified-mcp) - **Policy Enforcement** → `uvx agent-policy-enforcement-mcp` · [PyPI](https://pypi.org/project/agent-policy-enforcement-mcp/) · [GitHub](https://github.com/CSOAI-ORG/agent-policy-enforcement-mcp) - **Rate Limiter** → `uvx agent-rate-limiter-mcp` · [PyPI](https://pypi.org/project/agent-rate-limiter-mcp/) · [GitHub](https://github.com/CSOAI-ORG/agent-rate-limiter-mcp)

Full catalogue + Anthropic Registry verify links: meok.ai/anthropic-registry

Protocol coverage + Universal PAYG

This MCP is part of MEOK's 47-MCP fleet that bridges every active agent-interop protocol and 30+ regulatory frameworks. See the full coverage matrix at meok.ai/protocols.

Agent interop protocols supported (8 live):

  • ✅ MCP (Anthropic) — native
  • ✅ A2A (Google + Linux Foundation, absorbed IBM ACP Sept 2025)
  • ✅ IBM ACP — covered via A2A merge
  • ◐ Stripe ACP (Agentic Commerce Protocol) — Q3 bridge via agent-commerce-protocol-mcp
  • ◐ AP2 (Google Agent Payments) — partial via agent-commerce-payments-mcp
  • ◐ x402 (Coinbase HTTP 402) — partial via api.meok.ai gateway
  • → OASF / AGNTCY (Cisco Outshift + Linux Foundation) — Q3 bridge
  • 👁 ANP (Cisco Agent Network) — watch-list

Pricing options:

OptionPriceBest for
Self-host (this MCP)£0 — MITDevs
This MCP Starter£29/moOne-MCP teams
This MCP Pro£79/moProduction + 24h SLA
Universal PAYG£29/mo + £0.0002/callSpiky usage across many MCPs
Substrate bundle (this category)£99-£499/moA whole pack
MEOK Universe£1,499/moAll 47 MCPs, 500K calls

Each tier above the free self-host adds HMAC-signed attestations verifiable at verify.meok.ai. Linux Foundation governance on the A2A spine means EU regulated buyers can deploy without vendor-lock-in objections.

💸 Try MEOK in 30 seconds — instant buy ladder

TierPriceWhat you getStripe
Smoke test£1Signed sample MCP-Hardening report + Article 50 PDFhttps://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t
Quick Kit£9EU AI Act Article 50 implementation guide (C2PA + EU-Icon)https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t
Founder Call£2930-min 1-on-1 with the founderhttps://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t

Refundable. UK Stripe — VAT-clean. Builds on the 81-MCP MEOK fleet. Verify any signed report at https://meok.ai/verify.

See also

MEOK compliance MCP fleet: agent-incident-relay-mcp, meok-eu-ai-act-art-13-ifu-mcp

Configuration

Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:

json
{  "mcpServers": {    "agent-audit-logger-mcp": {      "command": "uvx",      "args": ["agent-audit-logger-mcp"]    }  }}

Or: pip install agent-audit-logger-mcp then run the agent-audit-logger-mcp command (stdio transport).

Examples

Once configured, ask your assistant, for example:

  • "Use log to …"
  • "Use verify_chain to …"
  • "Use search to …"

来源:README.md,提交 8694b81

工具

0
SourceWeft 尚未读取此服务器的工具。

版本历史

1
  1. v1.1.10最新Sep 16, 2026

评分

已满足适用检查项的 85%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Audit 集成