How we score MCP risk and effort.
Rule-based, deterministic, OWASP-aligned. No ML in the hot path. Same inputs always produce the same architecture, the same auth recommendations, and the same effort range.
Rule-based, deterministic, OWASP-aligned. No ML in the hot path. Same inputs always produce the same architecture, the same auth recommendations, and the same effort range.
Architecture rules
Effort formula
base_days = 5
per_server_days = {
standard: 1.5 // official server
community: 3.0 // community server, light adaptation
custom: 8.0 // build in-house
gateway: 15.0 // one-time add-on when gateway recommended
}
autonomy_multiplier = {
read_only: 1.0, suggest: 1.1, pre_approval: 1.4,
post_review: 1.6, autonomous: 2.0
}
regulatory_multiplier = min(1.0 + count_regulatory * 0.3, 2.0)
total_days = (base_days + sum(per_server_days) + gateway_days)
* autonomy_multiplier
* regulatory_multiplier
weeks_low = total_days / 5
weeks_high = weeks_low * 1.5Risk hotspots
| Pipeline node | OWASP refs | Mitigations |
|---|---|---|
| User → LLM | LLM01 | input filtering · prompt hardening |
| LLM → MCP | LLM06, LLM08 | tool allowlist · per-tool confirmation |
| MCP → Downstream | LLM08, LLM09 | per-session scope · rate limit gateway |
| Downstream → LLM | LLM01, LLM03 | output scanning · injection filter |
| LLM → User | LLM02 | pii redaction · audit log |
Integrity
Official servers are listed when they exist, regardless of vendor marketing spend.
We never cite a vendor demo as evidence of production readiness.
Every severity label traces to a specific OWASP ID or published advisory.