mcpField
A
agent-policy-enforcement-mcp

agent-policy-enforcement-mcp

Remote
github.com/CSOAI-ORGSecurity0Updated 18w ago
Repository

About agent-policy-enforcement-mcp

agent-policy-enforcement-mcp is an MCP server for defining and enforcing access policies between agent pairs. It evaluates A2A calls against policies and can provide signed policy-decision attestations.

Key features

  1. 01Per-agent-pair access control
  2. 02Policy evaluation for A2A calls
  3. 03Permission inheritance
  4. 04Audit logging
  5. 05Dynamic policy updates

Use cases

  1. 01Restricting calls between agents
  2. 02Applying conditions to A2A requests
  3. 03Reviewing policy decisions

MCP support

It provides MCP clients with policy-management capabilities, including `define_policy`, `evaluate_call`, and `list_policies`.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.meok.ai/v1/a2a/policy-enforcement
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
pypiagent-policy-enforcement-mcp1.0.11

Tools

Details

From the project README

MCP Scorecard: 78/100

Agent Policy Enforcement MCP

MEOK AI Labs EU AI Act License PyPI

Per-agent-pair IAM for A2A

Per-agent-pair IAM for A2A. Define policies ('orchestrator may call billing only when amount<1000'), gate every A2A call via evaluate_call. EU AI Act Art 14 + ISO 42001 Annex A.7 evidence with signed policy-decision attestations.


🚀 Quick Start

# Install via pip
pip install agent_policy_enforcement_mcp

# Or install via Smithery
npx -y @smithery/cli@latest install agent-policy-enforcement-mcp --client claude

✨ Features

  • Per-agent-pair IAM
  • Policy enforcement
  • Permission inheritance
  • Audit logging
  • Dynamic updates

📖 Documentation

🛡️ Compliance

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

  • Free — generous daily limit (100-1,000 depending on operation)

  • Pro £199/mo — unlimited + signed HMAC attestations with public verify URLs — subscribe

  • Enterprise £1,499/mo — multi-tenant + custom predicate DSL + SIEM webhook push — subscribe

  • ✅ 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)

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

Part of the MEOK **A2a** pack — designed to work together as a fleet. Install the whole pack with `npx meok-setup --pack a2a`, or pick the ones you need:
  • Prompt Injection Firewall → uvx agent-prompt-injection-firewall-mcp · PyPI · GitHub
  • Data Residency → uvx agent-data-residency-mcp · PyPI · GitHub
  • Certified Handoff → uvx agent-handoff-certified-mcp · PyPI · GitHub
  • Audit Logger → uvx agent-audit-logger-mcp · PyPI · GitHub
  • Rate Limiter → uvx agent-rate-limiter-mcp · PyPI · GitHub

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.

Configuration

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

{
  "mcpServers": {
    "agent-policy-enforcement-mcp": {
      "command": "uvx",
      "args": ["agent-policy-enforcement-mcp"]
    }
  }
}

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

Examples

Once configured, ask your assistant, for example:

  • "Use define_policy to …"
  • "Use evaluate_call to …"
  • "Use list_policies to …"

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.