Server data from the Official MCP Registry
Per-agent-pair IAM for A2A. Define policies ('orchestrator may call billing only when amount<100...
Per-agent-pair IAM for A2A. Define policies ('orchestrator may call billing only when amount<100...
This MCP server implements agent-to-agent policy enforcement with several security strengths (API key-based tier access, no hardcoded credentials, proper policy evaluation logic) but has notable concerns that prevent a higher score. The server makes unauthenticated network calls to external attestation APIs without verification, stores all policy decisions and logs in memory without persistence or encryption, lacks input validation on the DSL condition parser (potential injection risk), and the free tier check is bypassable due to client-side API key control. Additionally, the authentication fallback and optional external module dependencies create unclear security boundaries. Supply chain analysis found 3 known vulnerabilities in dependencies (0 critical, 3 high severity). Package verification found 1 issue (1 critical, 0 high severity).
5 files analyzed · 14 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Unverified package source
We couldn't verify that the installable package matches the reviewed source code. Proceed with caution.
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-csoai-org-agent-policy-enforcement-mcp": {
"args": [
"agent-policy-enforcement-mcp"
],
"command": "uvx"
}
}
}From the project's GitHub README.
Per-agent-pair IAM for A2A orchestration
The runtime-governance primitive that EU AI Act Article 14 (human oversight) + ISO 42001 Annex A.7 (authorisation) demand for agent-to-agent systems.
By MEOK AI Labs.
pip install agent-policy-enforcement-mcp
define_policyevaluate_calllist_policiesremove_policydecision_logsign_policy_attestation{
"mcpServers": {
"agentpolicyenforcement": { "command": "agent-policy-enforcement-mcp" }
}
}
The EU AI Act (Aug 2026), DORA (live), ISO 42001, and OWASP LLM01 Top-10 all demand runtime controls for agent systems — not just deployment-time audits. This MCP is that runtime control layer, emitting cryptographically signed evidence your auditor accepts.
agent-policy-enforcement-mcp — per-pair IAMagent-handoff-certified-mcp — signed delegation chainagent-prompt-injection-firewall-mcp — prompt injection WAFagent-rate-limiter-mcp — fleet-wide quotaagent-audit-logger-mcp — hash-chained signed loga2a-governance-bridge-mcp — map A2A to compliance frameworksmeok-attestation-verify — independent cert verifierMIT — MEOK AI Labs, 2026.
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
by Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption
by mcp-marketplace · Developer Tools
Scaffold, build, and publish TypeScript MCP servers to npm — conversationally
by mcp-marketplace · Finance
Free stock data and market news for any MCP-compatible AI assistant.