Skip to main content
Glama
CSOAI-ORG

Agent Audit Logger MCP

README.md
[![MCP Scorecard: 78/100](https://img.shields.io/badge/proofof.ai-78%2F100-5b21b6)](https://proofof.ai/scorecard/agent-audit-logger-mcp.html)

# Agent Audit Logger MCP

[![MEOK AI Labs](https://img.shields.io/badge/MEOK-AI%20Labs-667eea)](https://meok.ai)
[![EU AI Act](https://img.shields.io/badge/EU%20AI%20Act-Compliant-22c55e)](https://councilof.ai)
[![License](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
[![PyPI](https://img.shields.io/badge/PyPI-Install-3775a9)](https://pypi.org/project/agent_audit_logger_mcp/)

> 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 โ€” auditor-ready end-of-day attestations. By MEOK AI Labs.

---

## ๐Ÿš€ Quick Start

```bash
# Install via pip
pip install agent_audit_logger_mcp

# Or install via Smithery
npx -y @smithery/cli@latest install agent-audit-logger-mcp --client claude
```

## โœจ Features

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

## ๐Ÿ“– Documentation

- [Full Documentation](https://docs.meok.ai/agent-audit-logger-mcp)
- [API Reference](https://meok-attestation-api.vercel.app)
- [EU AI Act Compliance Guide](https://councilof.ai)

## ๐Ÿ›ก๏ธ Compliance

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

- โœ… Article 9 โ€” Risk Management System
- โœ… Article 13 โ€” Transparency & Instructions for Use
- โœ… Article 15 โ€” Bias Detection & Testing
- โœ… Article 26 โ€” FRIA Support (where applicable)
- โœ… Article 50 โ€” AI Content Watermarking (where applicable)
- **Free** โ€” 1,000 log entries/day, ephemeral, chain verification
- **Pro ยฃ199/mo** โ€” unlimited + signed end-of-day attestations + chain integrity reports โ€” [subscribe](https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t)
- **Enterprise ยฃ1,499/mo** โ€” multi-tenant + SIEM webhook push + retention policy โ€” [subscribe](https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t)

Need help getting compliant? **[Book a free 15-min diagnostic โ†’](mailto:nicholas@meok.ai?subject=Compliance%20diagnostic)**

## ๐Ÿข Enterprise

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

- **Pro:** ยฃ79/mo โ€” Full MCP suite + EU AI Act tracking
- **Enterprise:** ยฃ499/mo โ€” Custom dev + SLA + Dedicated support

[View Pricing โ†’](https://councilof.ai/payg) | [Contact Sales โ†’](mailto:sales@meok.ai)

## ๐Ÿค Part of the MEOK Ecosystem

This server is part of the **[MEOK AI Labs](https://meok.ai)** ecosystem โ€” 26 PyPI packages ยท ~16,300 monthly installs.

| Domain | Purpose |
|--------|---------|
| [councilof.ai](https://councilof.ai) | EU AI Act compliance marketplace |
| [safetyof.ai](https://safetyof.ai) | AI safety & monitoring |
| [meok.ai](https://meok.ai) | Sovereign AI platform |
| [cobolbridge.ai](https://cobolbridge.ai) | Legacy modernization |

## ๐Ÿ“œ License

MIT ยฉ [CSOAI-ORG](https://github.com/CSOAI-ORG)

---

<p align="center">
  <sub>Built with ๐Ÿ’œ by <a href="https://meok.ai">MEOK AI Labs</a> ยท UK Companies House 16939677</sub>
</p>
- **Prompt Injection Firewall** โ†’ `uvx agent-prompt-injection-firewall-mcp` ยท [PyPI](https://pypi.org/project/agent-prompt-injection-firewall-mcp/) ยท [GitHub](https://github.com/CSOAI-ORG/agent-prompt-injection-firewall-mcp)
- **Data Residency** โ†’ `uvx agent-data-residency-mcp` ยท [PyPI](https://pypi.org/project/agent-data-residency-mcp/) ยท [GitHub](https://github.com/CSOAI-ORG/agent-data-residency-mcp)
- **Certified Handoff** โ†’ `uvx agent-handoff-certified-mcp` ยท [PyPI](https://pypi.org/project/agent-handoff-certified-mcp/) ยท [GitHub](https://github.com/CSOAI-ORG/agent-handoff-certified-mcp)
- **Policy Enforcement** โ†’ `uvx agent-policy-enforcement-mcp` ยท [PyPI](https://pypi.org/project/agent-policy-enforcement-mcp/) ยท [GitHub](https://github.com/CSOAI-ORG/agent-policy-enforcement-mcp)
- **Rate Limiter** โ†’ `uvx agent-rate-limiter-mcp` ยท [PyPI](https://pypi.org/project/agent-rate-limiter-mcp/) ยท [GitHub](https://github.com/CSOAI-ORG/agent-rate-limiter-mcp)

Full catalogue + Anthropic Registry verify links: [meok.ai/anthropic-registry](https://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](https://meok.ai/protocols).

**Agent interop protocols supported (8 live):**

- โœ… **MCP** (Anthropic) โ€” native
- โœ… **A2A** (Google + Linux Foundation, absorbed IBM ACP Sept 2025)
- โœ… **IBM ACP** โ€” covered via A2A merge
- โ— **Stripe ACP** (Agentic Commerce Protocol) โ€” Q3 bridge via [agent-commerce-protocol-mcp](https://github.com/CSOAI-ORG/agent-commerce-protocol-mcp)
- โ— **AP2** (Google Agent Payments) โ€” partial via [agent-commerce-payments-mcp](https://github.com/CSOAI-ORG/agent-commerce-payments-mcp)
- โ— **x402** (Coinbase HTTP 402) โ€” partial via api.meok.ai gateway
- โ†’ **OASF / AGNTCY** (Cisco Outshift + Linux Foundation) โ€” Q3 bridge
- ๐Ÿ‘ **ANP** (Cisco Agent Network) โ€” watch-list

**Pricing options:**

| Option | Price | Best for |
|---|---|---|
| Self-host (this MCP) | ยฃ0 โ€” MIT | Devs |
| This MCP Starter | ยฃ29/mo | One-MCP teams |
| This MCP Pro | ยฃ79/mo | Production + 24h SLA |
| [Universal PAYG](https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t) | ยฃ29/mo + ยฃ0.0002/call | Spiky usage across many MCPs |
| Substrate bundle (this category) | ยฃ99-ยฃ499/mo | A whole pack |
| [MEOK Universe](https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t) | ยฃ1,499/mo | All 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.

<!-- mcp-name: io.github.CSOAI-ORG/agent-audit-logger-mcp -->

<!-- BUY-LADDER:START -->

## ๐Ÿ’ธ Try MEOK in 30 seconds โ€” instant buy ladder

| Tier | Price | What you get | Stripe |
|---|---|---|---|
| Smoke test | **ยฃ1** | Signed sample MCP-Hardening report + Article 50 PDF | <https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t> |
| Quick Kit | **ยฃ9** | EU AI Act Article 50 implementation guide (C2PA + EU-Icon) | <https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t> |
| Founder Call | **ยฃ29** | 30-min 1-on-1 with the founder | <https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t> |

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

<!-- BUY-LADDER:END -->

## See also

MEOK compliance MCP fleet:
[`agent-incident-relay-mcp`](https://github.com/CSOAI-ORG/agent-incident-relay-mcp), [`meok-eu-ai-act-art-13-ifu-mcp`](https://github.com/CSOAI-ORG/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 โ€ฆ"
- "Use `verify_chain` to โ€ฆ"
- "Use `search` to โ€ฆ"

TDQS

B3.4/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a unique and well-defined purpose: logging, searching, daily stats, attestation, and chain verification. No two tools overlap in functionality.

Naming Consistency3/5

Naming is a mix: 'daily_stats' uses noun_verb, 'log' and 'search' are single verbs, while 'sign_day_attestation' and 'verify_chain' follow a verb_noun pattern. This inconsistency is noticeable but not chaotic.

Tool Count5/5

With 5 tools, the server covers the essential operations for an audit logging system: append, search, statistics, attestation, and verification. The count is well-scoped without being excessive.

Completeness5/5

The tool set provides a complete lifecycle for audit logging: log entry creation, querying, daily statistics, integrity attestation, and chain verification. No obvious gaps given the append-only nature of audit logs.

Maintenance

ActivityStale
ResponsivenessNo issues