Cloudflare

Live

OAUTH 2.0

DNS & EDGE

Developer Tools

Zones, DNS records, Workers, and Zero Trust apps are the edge surface your agent has to reason about, reached with per-user OAuth against the Cloudflare account.

  • Acts as the user: zone and DNS reads stay tied to the Cloudflare account that authorized the agent, so account scoping holds.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: User permissions enforced. 90-day audit trail.
Cloudflare
agent · Acme Q3
Run
Which DNS records on acme.com point at the old load balancer?
S
cloudflare_dns_record_list
78ms
DevOps agent
4 records still resolve to 203.0.113.20: api (A, proxied), edge (A, proxied), legacy (CNAME), and staging (A, DNS only).
Sources: 1 zone, 4 DNS records
cloudflare
4 records
18:29
Message Claude...

Tools your DevOps agent reaches for on Cloudflare, scoped per user.

CALL ANY TOOL
Edge and DNS visibility in one toolkit: accounts, zones, DNS records, Worker scripts, and Zero Trust access apps. Each call uses the user's own OAuth token.
cloudflare_access_application_list
List access application
List all zero trust access applications configured in a cloudflare account, with optional filtering by name or domain.
Parameters
Name
Type
Required
Description
account_id
string
Required
The ID of the Cloudflare account
domain
string
Optional
Filter applications by domain
name
string
Optional
Filter applications by name
page
integer
Optional
Page number of results to return
per_page
integer
Optional
Number of results per page
cloudflare_user_get
Get user
cloudflare_account_list
List account
cloudflare_dns_record_list
List dns record
cloudflare_worker_script_list
List worker script
cloudflare_zone_list
List zone
Build your Agent
Drop the toolkit in, point it at the user, and your agent can audit zones and DNS from the first run.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["cloudflare"], toolNames: ["cloudflare_zone_list", "cloudflare_dns_record_list", "cloudflare_worker_script_list"] },
pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
name: t.tool.definition.name,
description: t.tool.definition.description,
schema: z.object({}).passthrough(),
func: async (args) => {
const { data } = await sk.tools.executeTool({
toolName: t.tool.definition.name,
identifier: "user_123",
params: args,
});
return JSON.stringify(data);
},
}));

const agent = createReactAgent({ llm, tools: lcTools });
import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["cloudflare"], toolNames: ["cloudflare_zone_list", "cloudflare_dns_record_list", "cloudflare_worker_script_list"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
type: "function",
function: {
name: t.tool.definition.name,
description: t.tool.definition.description,
parameters: t.tool.definition.input_schema,
},
}));

const resp = await openai.responses.create({
model: "gpt-4o", input: prompt, tools: llmTools,
});
import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["cloudflare"], toolNames: ["cloudflare_zone_list", "cloudflare_dns_record_list", "cloudflare_worker_script_list"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
name: t.tool.definition.name,
description: t.tool.definition.description,
input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
model: "claude-sonnet-4-6", max_tokens: 1024,
tools: llmTools,
messages: [{ role: "user", content: prompt }],
});
import { Agent } from "@google/adk/agents";
import {
MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
connectionParams: new StreamableHTTPConnectionParams({
url: "https://mcp.scalekit.com/cloudflare",
headers: { Authorization: `Bearer ${userScopedToken}` },
}),
});

const agent = new Agent({
name: "agent", model: "gemini-2.0-flash",
tools: await toolset.getTools(),
});
Try these prompts
Paste any prompt into your agent to start auditing Cloudflare DNS and edge config from your workflows.
DNS audits
Copy the prompt
Copied
List every A record on [zone] that is DNS only instead of proxied.
Copy the prompt
Copied
Find records across all zones still pointing at [old_ip].
Copy the prompt
Copied
Show TTLs for the MX records on [zone].
Edge inventory
Copy the prompt
Copied
List all Worker scripts in the account with their last modified date.
Copy the prompt
Copied
Which zones in this account are not on the active status?
Copy the prompt
Copied
Summarize the Zero Trust access applications and who they are scoped to.
Account review
Copy the prompt
Copied
Which Cloudflare accounts can I see and what plans are they on?
Copy the prompt
Copied
Show my current Cloudflare user profile and account memberships.
Copy the prompt
Copied
Group all zones by account and flag any without DNS records.
SEE HOW AUTH WORKS
Your users connect once. Their Cloudflare credentials stay vaulted, every call is scope-checked, and every action is logged.
1
Authorize
Your user connects
Cloudflare
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Cloudflare
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Cloudflare
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Cloudflare
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other connectors.
ENGINEERING
DevOps assistant agent
Poll GitHub for failing checks and stale pull requests, open Linear issues for the ones that need work, and digest to Slack.
ENGINEERING
Auto-release notes agent
Group merged GitHub PRs into structured release notes, publish the page to Notion, and announce the release in Slack.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.
01.
Shared tokens break per-user analytics
A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.
// shared token
audit → bot_service_account
user_filter → broken

// scalekit
audit → user_abc
scope → enforced ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Cloudflare today. Others tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Cloudflare as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.
Where is the Cloudflare OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.
Can I limit what the agent is allowed to do in Cloudflare?
Yes. Pass a tool name filter to listScopedTools so the DevOps agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Cloudflare.
What happens when a user revokes Cloudflare access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Does the agent see every Cloudflare zone or only the user's?
Only what the authorizing user can see. Scalekit resolves that user's OAuth token at request time, so Cloudflare's own account and role membership decides the result set. An agent run by a member with one account never returns zones from another.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""cloudflare"": {
""url"": ""https://mcp.scalekit.com/cloudflare"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.cloudflare]
url = ""https://mcp.scalekit.com/cloudflare""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""cloudflare"": {
""url"": ""https://mcp.scalekit.com/cloudflare"",
""type"": ""http""
}
}
}