MCP server official
Risk level
medium
45/100

Cloudflare MCP Server ↗

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

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

Analysis summary

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

Cloudflare ships a family of remote MCP servers covering Workers, KV, R2, D1, DNS, Workers Logs, and account APIs. An agent can read observability data, query a D1 database, inspect DNS records, or deploy a Worker, depending on which server and scopes are connected.

This is infrastructure control, so the risk is proportional to the API token behind it rather than to the protocol. The declared capabilities are outbound network access, credential access, and database reads and writes for the D1 surface. A token that can edit DNS or deploy Workers can redirect or intercept production traffic — treat connecting this server as granting an agent a seat on your infrastructure, and prefer read-scoped tokens for anything an assistant uses interactively.

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: credentials:access, database:write 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.

  • 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.
  • 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.

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