Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add rules/csoai-org/agent-policy-enforcement-mcp/cursorrulesgit clone --depth 1 https://github.com/CSOAI-ORG/agent-policy-enforcement-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/csoai-org/agent-policy-enforcement-mcp/cursorrules)<a href="https://agentmods.dev/rules/csoai-org/agent-policy-enforcement-mcp/cursorrules"><img src="https://agentmods.dev/badge/rules/csoai-org/agent-policy-enforcement-mcp/cursorrules.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00163 | $0.00163 |
| Opus 5 | $0.00081 | $0.00081 |
| Sonnet 5 | $0.00033 | $0.00033 |
| Haiku 4.5 | $0.00016 | $0.00016 |
Grade A, and why
cursorrules scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Agent Policy Enforcement MCP - Auto-trigger Rules
When the user asks about agent IAM, per-agent-pair policies, agent authorization rules, multi-tenant agent governance, or "agent A may only talk to agent B if X", use agent-policy-enforcement-mcp tools:
- define_policy: Create source→target policy with constraints (regions, spend caps, tools)
- evaluate_policy: Check if an agent action is permitted under current policies
- list_policies: Browse all defined policies
- get_policy_violations: List recent denials with reason codes
Install: pip install agent-policy-enforcement-mcp
The boring tedious "IAM for agents" layer that no one else ships well. Required for any enterprise rolling out agents across ≥2 tenants.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 13 lines · 163 tokens per session scan A c010f6f5fedf
cursorrules is a cursor rule published in the GitHub repository CSOAI-ORG/agent-policy-enforcement-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 163 tokens to every session, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
cursorrules
When the user asks about meok watermark attest, use meok-watermark-attest-mcp tools: getdeadlinestatus, classifyobligations, generatedisclosuretext, auditcontentpipeline, signwatermarkattestation.
cursorrules
When the user asks about agent-to-agent audit trails, immutable A2A logging, DORA/NIS2/EU AI Act audit requirements, or attestation-signed bundle export, use agent-audit-logger-mcp tools.
cursorrules
When the user asks about AI Bill of Materials, AI-BOM, supply chain transparency, model dependencies, training data provenance, or model card generation, use ai-bom-mcp tools.
cursorrules
When the user asks about AI incident reporting, serious incident classification, EU AI Act Article 73, OECD AI Incident Monitor (AIM), or multi-regime incident routing, use ai-incident-reporting-mcp tools.
cursorrules
When the user asks about a2a governance bridge, use a2a-governance-bridge-mcp tools: verifyagentcompliance, authorizea2atransaction, gettrustregistry, geta2aaudittrail, crossagentriskscore.
cursorrules
When the user asks about iso 27001, use iso-27001-ai-mcp tools: auditisms, riskassessment, gapanalysis, crosswalktoai, generatesoa.