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/mitre-attack-mcp/cursorrulesgit clone --depth 1 https://github.com/CSOAI-ORG/mitre-attack-mcpWhat 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 | $0.00184 | $0.00184 |
| Opus 5 | $0.00092 | $0.00092 |
| Sonnet 5 | $0.00037 | $0.00037 |
| Haiku 4.5 | $0.00018 | $0.00018 |
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 yesterday.
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
MITRE ATT&CK Mapper MCP - Auto-trigger Rules
When the user asks about MITRE ATT&CK, tactics, techniques, threat intel, STIX, IOC, use mitre-attack-mcp tools:
- query_technique: Query ATT&CK technique by ID (Txxxx) or name
- list_tactics: All 14 enterprise tactics (TA0001-TA0040+)
- map_incident: Map incident IOCs/behaviors to ATT&CK techniques
- group_threat_actor: Threat actor groups (G-codes) using a technique
- mitigation_lookup: Mitigations (M-codes) for a technique
Install: pip install mitre-attack-mcp
By MEOK AI Labs — industry governance MCP. Pairs with meok-attestation-api for signed compliance certs.
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.
- yesterday First seen · 14 lines · 184 tokens per session scan A ce1f78d5ff39
cursorrules is a cursor rule published in the GitHub repository CSOAI-ORG/mitre-attack-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 184 tokens to every session, about $0.0009 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 CPCS, CISRS, NPORS, BS 7121, lift plan, LOLER, crane operator, use crane-hire-cpcs-mcp tools.
cursorrules
When the user is in scope for BOTH DORA and NIS2 (banks, insurers, payment institutions, CTPPs) and asks about dual compliance, overlapping obligations, or unified evidence collection, use dora-nis2-crosswalk-mcp tools.
cursorrules
When the user asks about UK haulage, Operator Licence, tachograph, drivers' hours, DVSA, road user levy, use haulage-uk-compliance-mcp tools.
cursorrules
When the user asks about MiFID II, algo trading, HFT, RTS 6, best execution, market abuse, use mifid-ii-ai-mcp tools.
cursorrules
When the user asks about MITRE ATLAS, adversarial AI, ML security, OWASP LLM, use mitre-atlas-mcp tools.
cursorrules
When the user asks about NRSWA, street works, Section 50/58/74, utility works, accreditation, use nrswa-ai-mcp tools.