PostgreSQL
PostgreSQL is an officially published MCP server from Anthropic. Anomity scores its risk at 45 out of 100 (medium). It matches 1 dangerous capability combination.
Analysis summary
PostgreSQL is an officially published MCP server from Anthropic. Anomity scores its risk at 45 out of 100 (medium). It matches 1 dangerous capability combination.
Why this entry scored 45 out of 100
This profile starts at the catalog's neutral base of 50. Because the entry is officially published, trust adjusts the score by -40. Declared high-risk capabilities add +20 (capped at +30). It matches 1 dangerous capability combination, which contributes additional severity weight. The clamped result is 45, placing it in the medium band.
Findings
-
Published by the vendor Trust offset
-
2 high-risk capabilities: database:write, credentials:access Critical
-
Database exfiltration risk (high) HighEvidenceDatabase read combined with outbound network can exfiltrate production data.
Capabilities
Every capability the entry declares, with the security implication of each.
-
database:readDatabase readReads from connected databases. Useful for query and analytics agents; risky when combined with outbound network. -
database:writeDatabase writeWrites to connected databases. High-impact; combined with outbound network is treated as exfiltration-class. -
network:outboundOutbound networkCan make outbound network requests. Required for hosted model providers and remote APIs; also the path for data exfiltration if combined with read access. -
credentials:accessCredentials accessReads provider API keys, OAuth tokens, or other secrets from the host keychain or environment.
Dangerous combinations matched
Capability pairings that compound into well-known attack patterns.
-
Database exfiltration risk highDatabase read combined with outbound network can exfiltrate production data.database:read network:outbound