Cloudflare (official) MCP Server
@cloudflare/mcp-server-cloudflare
npm
v0.2.0
Official
Published by Cloudflare — an official vendor package. A brand name in a package name proves nothing; this one is verified by npm scope ownership or publish provenance.
Cloudflare’s official MCP server: manage Workers, KV, R2 and D1 from an assistant.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 6 = 94. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 8
high Sensitive-source and external-sink co-existMTC-FLOW-004
Tools that read sensitive data ([d1_query, kv_list]) and tools that can send data out ([do_create_namespace, queue_send_message]) are exposed together. An agent can move private data to the sink.
Evidence: sources [d1_query, kv_list] → sinks [do_create_namespace, queue_send_message]
Fix: Keep secret-reading and egress capabilities on separate, separately-approved servers.
Location: flow d1_query → do_create_namespace
high Tool "do_create_namespace" exposes command/code executionMTC-CAP-001
Tool "do_create_namespace" appears to run shell commands or evaluate code (parameter "script"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool do_create_namespace
high Shell/command execution in server code (dist/index.js)MTC-SRC-002
In the server's implementation (`dist/index.js:4`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: s import { exec } from "child_process"; import { promisify } from "util"; // src/utils/wrangler.ts import fs, { mkdirSy
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 dist/index.js
medium Hardcoded egress to an external endpoint (dist/index.js)MTC-SRC-003
In the server's implementation (`dist/index.js:138`): 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: ed" }; return await fetch("https://dash.cloudflare.com/oauth2/token", { method: "POST", body: body.toString(
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 dist/index.js
medium Tool "r2_put_object" can modify the filesystemMTC-CAP-002
Tool "r2_put_object" can write, overwrite or delete files (keyword "put_object" in tool name). Verify it is scoped to a safe directory.
Fix: Constrain file operations to an explicit, non-sensitive root; reject path traversal.
Location: tool r2_put_object
medium Unconstrained command parameter "script" on "do_create_namespace"MTC-CAP-006
Tool "do_create_namespace" takes a command-shaped parameter "script" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool do_create_namespace · inputSchema.properties.script
low Mutating tool "r2_put_object" declares no destructiveHintMTC-CAP-005
Tool "r2_put_object" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool r2_put_object
low Mutating tool "do_create_namespace" declares no destructiveHintMTC-CAP-005
Tool "do_create_namespace" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool do_create_namespace
Tools 92
Each tool and what it can reach — statically extracted from the published source.
d1_queryreads sensitive datado_create_namespaceruns code / shellkv_listreads sensitive dataqueue_send_messagenetwork egressr2_put_objectwrites filesai_embeddingsno sensitive capabilityai_get_modelno sensitive capabilityai_image_generationno sensitive capabilityai_inferenceno sensitive capabilityai_list_modelsno sensitive capability
Show 82 more tools ↓
ai_text_generationno sensitive capabilityanalytics_getno sensitive capabilitycron_createno sensitive capabilitycron_deleteno sensitive capabilitycron_listno sensitive capabilitycron_updateno sensitive capabilityd1_create_databaseno sensitive capabilityd1_delete_databaseno sensitive capabilityd1_list_databasesno sensitive capabilitydo_alarm_deleteno sensitive capabilitydo_alarm_listno sensitive capabilitydo_alarm_setno sensitive capabilitydo_delete_namespaceno sensitive capabilitydo_delete_objectno sensitive capabilitydo_get_objectno sensitive capabilitydo_list_namespacesno sensitive capabilitydo_list_objectsno sensitive capabilitydomain_listno sensitive capabilityenv_var_bulk_setno sensitive capabilityenv_var_deleteno sensitive capabilityenv_var_listno sensitive capabilityenv_var_setno sensitive capabilityget_kvsno sensitive capabilitykv_deleteno sensitive capabilitykv_getno sensitive capabilitykv_putno sensitive capabilityqueue_createno sensitive capabilityqueue_deleteno sensitive capabilityqueue_delete_messageno sensitive capabilityqueue_getno sensitive capabilityqueue_get_messageno sensitive capabilityqueue_listno sensitive capabilityqueue_send_batchno sensitive capabilityqueue_update_visibilityno sensitive capabilityr2_create_bucketno sensitive capabilityr2_delete_bucketno sensitive capabilityr2_delete_objectno sensitive capabilityr2_get_objectno sensitive capabilityr2_list_bucketsno sensitive capabilityr2_list_objectsno sensitive capabilityroute_createno sensitive capabilityroute_deleteno sensitive capabilityroute_listno sensitive capabilityroute_updateno sensitive capabilitysecret_deleteno sensitive capabilitysecret_listno sensitive capabilitysecret_putno sensitive capabilityservice_binding_createno sensitive capabilityservice_binding_deleteno sensitive capabilityservice_binding_listno sensitive capabilityservice_binding_updateno sensitive capabilitytemplate_create_workerno sensitive capabilitytemplate_getno sensitive capabilitytemplate_listno sensitive capabilityTest Template 1no sensitive capabilityTest Template 2no sensitive capabilitytest-templateno sensitive capabilityversion_getno sensitive capabilityversion_listno sensitive capabilityversion_rollbackno sensitive capabilitywfp_add_custom_domainno sensitive capabilitywfp_create_dispatch_namespaceno sensitive capabilitywfp_delete_dispatch_namespaceno sensitive capabilitywfp_list_custom_domainsno sensitive capabilitywfp_list_dispatch_namespacesno sensitive capabilitywfp_remove_custom_domainno sensitive capabilityworker_deleteno sensitive capabilityworker_deployno sensitive capabilityworker_getno sensitive capabilityworker_listno sensitive capabilityworker_putno sensitive capabilityworkers_analytics_searchno sensitive capabilityworkflow_createno sensitive capabilityworkflow_deleteno sensitive capabilityworkflow_executeno sensitive capabilityworkflow_getno sensitive capabilityworkflow_listno sensitive capabilityworkflow_updateno sensitive capabilitywrangler_config_getno sensitive capabilitywrangler_config_updateno sensitive capabilityzones_getno sensitive capabilityzones_listno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (92 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
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 |
|---|---|---|---|---|
v0.2.0 latest |
A 94/100 | 8 | 1.13.0 | 2026-08-25 |
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 @cloudflare/mcp-server-cloudflare --onlineOther implementations of Cloudflare (official) 9
Independent packages implementing the same tool, scanned with the same engine. Compare all 10 side by side →
Lets AI agents manage Cloudflare DNS records for your domains.
MCP server for managing Cloudflare DNS records across multiple domains from one API token
MCP server for cloudflare integration
Cloudflare connector covering DNS, Pages, Workers, and R2.
Slim Cloudflare server for DNS, zones, tunnels, WAF, and Zero Trust management via the Cloudflare v4 API.
MCP server for interacting with Cloudflare API
More in Cloud & DevOps
Operator control CLI for AdGuard Home with an MCP adapter
interacting with Aliyun (Alibaba Cloud) services through This MCP server provides tools.
MCP server for the Aspro.Cloud REST API
MCP server for Atlassian Confluence and Jira Cloud APIs
AuroraCloud-first MCP server that exposes AuroraDocs workspace data to Claude Desktop and other AI agents
The official AWS Knowledge Base retrieval server using Bedrock Agent Runtime.