MCP server official
Risk level
medium
45/100

Neon MCP Server ↗

Neon MCP Server is an officially published MCP server from Neon. Anomity scores its risk at 45 out of 100 (medium). It matches 1 dangerous capability combination.

database:read database:write network:outbound credentials:access

Analysis summary

Neon MCP Server is an officially published MCP server from Neon. Anomity scores its risk at 45 out of 100 (medium). It matches 1 dangerous capability combination.

Neon's official server lets an agent manage serverless Postgres projects — creating branches, running SQL, inspecting schemas, and reading documentation. Database branching makes it unusually well suited to agent work, because an assistant can be given a throwaway branch instead of production.

Capabilities are database read and write, outbound network access, and credential access. That set includes the database-exfiltration combination, so the branching feature is not just convenience, it is the control: give the agent a branch, let it break things, discard it. An assistant connected directly to a production branch has both read access to your data and a network path off the machine.

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.

See the full scoring formula →

Findings

  • Published by the vendor Trust offset
    Contribution to score: -40
  • 2 high-risk capabilities: database:write, credentials:access Critical
    Contribution to score: +20
  • Database exfiltration risk (high) High
    Evidence
    Database read combined with outbound network can exfiltrate production data.
    Contribution to score: +15

Capabilities

Every capability the entry declares, with the security implication of each.

  • database:read Database read
    Reads from connected databases. Useful for query and analytics agents; risky when combined with outbound network.
  • database:write Database write
    Writes to connected databases. High-impact; combined with outbound network is treated as exfiltration-class.
  • network:outbound Outbound network
    Can make outbound network requests. Required for hosted model providers and remote APIs; also the path for data exfiltration if combined with read access.
  • credentials:access Credentials access
    Reads 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 high
    Database read combined with outbound network can exfiltrate production data.
    database:read network:outbound