> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns. > > **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal): > ```bash > npx -y @scalekit-inc/cli setup -y > ``` > > Global: > ```bash > npm install -g @scalekit-inc/cli > scalekit setup -y > ``` > > Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`. > Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim. > [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/) --- # Connect AI agents to the Cloudflare MCP server The Cloudflare MCP connector routes your AI agent's tool calls to Cloudflare's own MCP server through Scalekit. Each user signs in to Cloudflare once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 3 tools. **Authentication:** OAuth 2.1/DCR **Categories:** Developer Tools, Automation **Tools:** 3: 2 read, 1 write, 0 destructive **Users sign in with:** OAuth **OAuth app:** Scalekit's or your own **Built by:** Vendor MCP **Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=CLOUDFAREMCP) ## Setup 1. ### Install the SDK **Node.js** ```bash npm install @scalekit-sdk/node dotenv ``` **Python** ```bash pip install scalekit-sdk-python python-dotenv ``` 2. ### Set your credentials Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**. ```sh title=".env" SCALEKIT_ENVIRONMENT_URL= SCALEKIT_CLIENT_ID= SCALEKIT_CLIENT_SECRET= ``` 3. ### Create the Cloudflare MCP connection In **AgentKit > Connections**, create a Cloudflare MCP connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/). Scalekit credentials are available for Cloudflare, so you don't need to register an OAuth app. 4. ### Authorize a user and make your first call **Node.js** (`quickstart.mts`) ```typescript import { ScalekitClient } from '@scalekit-sdk/node' import 'dotenv/config' import { createInterface } from 'node:readline/promises' const scalekit = new ScalekitClient( process.env.SCALEKIT_ENVIRONMENT_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET, ) const actions = scalekit.actions const connector = 'cloudfaremcp' const identifier = 'user_123' // Generate an authorization link for the user const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier }) console.log('Authorize Cloudflare MCP:', link) const rl = createInterface({ input: process.stdin, output: process.stdout }) await rl.question('Press Enter after authorizing...') rl.close() // Make your first call const result = await actions.executeTool({ connector, identifier, toolName: 'cloudfaremcp_docs', toolInput: { query: 'YOUR_QUERY' }, }) console.log(result) ``` ```bash npx tsx quickstart.mts ``` **Python** (`quickstart.py`) ```python import os from scalekit import ScalekitClient from dotenv import load_dotenv load_dotenv() scalekit_client = ScalekitClient( env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"), client_id=os.getenv("SCALEKIT_CLIENT_ID"), client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"), ) actions = scalekit_client.actions connection_name = "cloudfaremcp" identifier = "user_123" # Generate an authorization link for the user link_response = actions.get_authorization_link( connection_name=connection_name, identifier=identifier, ) print("Authorize Cloudflare MCP:", link_response.link) input("Press Enter after authorizing...") # Make your first call result = actions.execute_tool( tool_input={"query":"YOUR_QUERY"}, tool_name="cloudfaremcp_docs", connection_name=connection_name, identifier=identifier, ) print(result) ``` ```bash python quickstart.py ``` Each user signs in once. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses. ## Tools Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool). **Node.js** ```typescript const result = await actions.executeTool({ toolName: 'cloudfaremcp_docs', toolInput: { query: '', }, connector: 'cloudfaremcp', identifier: 'user_123', }) ``` **Python** ```python result = actions.execute_tool( tool_name="cloudfaremcp_docs", tool_input={ "query": "", }, connection_name="cloudfaremcp", identifier="user_123", ) ``` `result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call. ### `cloudfaremcp_docs` Cloudflare Docs Search · Read-only Search the Cloudflare documentation. Use this tool to answer any question about Cloudflare products or features, including Workers, Pages, R2, Images, Stream, D1, Durable Objects, KV, Workflows, Hyperdrive, Queues, AI Search, Workers AI, Vectorize, AI Gateway, Browser Rendering, Zero Trust, Access, Tunnel, Gateway, Browser Isolation, WARP, DDOS, Magic Transit, Magic WAN, CDN, Cache, DNS, Zaraz, Argo, Rulesets, Terraform, Account and Billing. Results are returned as semantically similar chunks to the query. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `query` (`string`, required): Cloudflare documentation search query. Example input: `{"query":""}` ### `cloudfaremcp_search` Cloudflare Search · Read-only Search the Cloudflare OpenAPI spec to discover API endpoints, request parameters, and response schemas. Run this before execute to find the right path and method for your operation. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `code` (`string`, required): JavaScript async arrow function that queries `spec.paths` to find matching Cloudflare API endpoints. Example input: `{"code":""}` ### `cloudfaremcp_execute` Cloudflare Execute · Write Execute JavaScript code against the Cloudflare API using the `cloudflare.request()` helper. Use the search tool first to discover the right endpoint path and schema. Read only: no. Destructive: no. Idempotent (safe to retry): no. Inputs: - `code` (`string`, required): JavaScript async arrow function that calls `cloudflare.request()` to interact with the Cloudflare API. - `account_id` (`string`, optional): Your Cloudflare account ID. Auto-selected if you only have one account. Example input: `{"code":""}` ## Related Other ways to connect Cloudflare: - [OAuth](/agentkit/connectors/cloudflare/): Scalekit connector, OAuth, 31 tools Other Developer Tools connectors ([all 94](/agentkit/connectors/?category=developer-tools)): - [GitHub](/agentkit/connectors/github/): Scalekit connector, OAuth, 217 tools - [Datadog](/agentkit/connectors/datadog/): Scalekit connector, API key, 105 tools - [Linear](/agentkit/connectors/linear/): Scalekit connector, OAuth, 62 tools --- ## More Scalekit documentation | Resource | What it contains | When to use it | |----------|-----------------|----------------| | [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content | | [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas | | [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |