Cloudflare (antidrift) (antidrift) MCP Server
@antidrift/mcp-cloudflare
npm
v0.22.0
Source verified
Published by probeo-io — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Cloudflare connector covering DNS, Pages, Workers, and R2.
Started at 100 and nothing was deducted: the deterministic scan raised no scored threat in the published surface it inspected. Capability observations and advisory notes are recorded but never lower the score.
Findings 2
medium Hardcoded egress to an external endpoint (bin/cli.mjs)MTC-SRC-003
In the server's implementation (`bin/cli.mjs:55`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: fetch('https://api.cloudflare.com/client/v4/user/tokens/verify'
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/cli.mjs
medium Hardcoded egress to an external endpoint (connectors/cloudflare.mjs)MTC-SRC-003
In the server's implementation (`connectors/cloudflare.mjs:8`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: fetch(`https://api.cloudflare.com/client/v4${path}`
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server connectors/cloudflare.mjs
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.22.0 latest |
A 100/100 | 2 | 1.5.0 | 2026-07-22 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @antidrift/mcp-cloudflare --onlineOther implementations of Cloudflare (antidrift) 9
Independent packages implementing the same tool, scanned with the same engine. Compare all 10 side by side →
Security scan results for the Cloudflare (cloudflare) MCP server.
Lets AI agents manage Cloudflare DNS records for your domains.
Slim Cloudflare server for DNS, zones, tunnels, WAF, and Zero Trust management via the Cloudflare v4 API.
Security scan results for the Cloudflare (hlos-ai) MCP server.
Security scan results for the Cloudflare (mcp-wormhole) MCP server.
Security scan results for the Cloudflare (archawat) MCP server.
More in Cloud & DevOps
Security scan results for the Actual MCP server.
Security scan results for the Adguard MCP server.
Security scan results for the Admob MCP server.
Security scan results for the Aem MCP server.
Security scan results for the Agent Domains MCP server.
Security scan results for the Agent Infra MCP server.