Connect your AI agent to Cloudflare MCP
Manage Cloudflare resources through the Cloudflare API MCP server.
Set it up in Melso
- 1In Melso, open Settings → Agent Apps and hit Connect on Cloudflare MCP.
- 2Finish the DCR_OAUTH sign-in in the window that opens. Melso stores the connection, not your credentials.
- 3Open your agent, go to its Agent Apps tab, and allow Cloudflare MCP.
- 4Give the agent a task. It calls Cloudflare MCP itself when the work needs it.
What Cloudflare MCP gives your agent
The tools, permissions, and events Cloudflare MCP exposes — the same ones your agent can use once the app is authorized.
What you sign in with
Cloudflare MCP connects with DCR_OAUTH.
Permissions
Cloudflare MCP does not break access down into granular permissions.
Tools Cloudflare MCP exposes
Docs
Search the Cloudflare documentation. This tool should be used 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.
Execute
Execute JavaScript code against the Cloudflare API. First use the 'search' tool to find the right endpoints, then write code using the cloudflare.request() function. Available in your code: interface CloudflareRequestOptions { method: "GET" | "POST" | "PUT" | "PATCH" | "DELETE"; path: string; query?: Record<string, string | number | boolean | undefined>; body?: unknown; contentType?: string; // Custom Content-Type header (defaults to application/json if body is present) rawBody?: boolean; // If true, sends body as-is without JSON.stringify } interface CloudflareResponse<T = unknown> { success: boolean; status: number; result: T; errors: Array<{ code: number; message: string }>; messages: Array<{ code: number; message: string }>; result_info?: { page: number; per_page: number; total_pages: number; count: number; total_count: number; }; } declare const cloudflare: { request<T = unknown>(options: CloudflareRequestOptions): Promise<CloudflareResponse<T>>; }; declare const accountId: string; // accountId is pre-set to "e8a40544a7211334b83bf588bbf7dec1" (Qa@agent51testing.com's Account) — use it directly in API paths. Your code must be an async arrow function that returns the result. Example: Worker with bindings (requires multipart/form-data): async () => { const code = `addEventListener('fetch', e => e.respondWith(MY_KV.get('key').then(v => new Response(v || 'none'))));`; const metadata = { body_part: "script", bindings: [{ type: "kv_namespace", name: "MY_KV", namespace_id: "your-kv-id" }] }; const b = `--F${Date.now()}`; const body = [`--${b}`, 'Content-Disposition: form-data; name="metadata"', 'Content-Type: application/json', '', JSON.stringify(metadata), `--${b}`, 'Content-Disposition: form-data; name="script"', 'Content-Type: application/javascript', '', code, `--${b}--`].join("\r\n"); return cloudflare.request({ method: "PUT", path: `/accounts/${accountId}/workers/scripts/my-worker`, body, contentType: `multipart/form-data; boundary=${b}`, rawBody: true }); }
Search
Search the Cloudflare OpenAPI spec. All $refs are pre-resolved inline. Products: cloudforce-one, access, magic, workers, dlp, realtime, email-security, devices, email, ai-gateway, intel, gateway, stream, brand-protection, settings, ai-search, data-security, browser-rendering, dex, logpush, api_gateway, builds, addressing, images, load_balancers, security-center, rulesets, vectorize, firewall, logs... (160 total) Types: interface OperationInfo { summary?: string; description?: string; tags?: string[]; parameters?: Array<{ name: string; in: string; required?: boolean; schema?: unknown; description?: string }>; requestBody?: { required?: boolean; content?: Record<string, { schema?: unknown }> }; responses?: Record<string, { description?: string; content?: Record<string, { schema?: unknown }> }>; } interface PathItem { get?: OperationInfo; post?: OperationInfo; put?: OperationInfo; patch?: OperationInfo; delete?: OperationInfo; } declare const spec: { paths: Record<string, PathItem>; }; Examples: // Find endpoints by product async () => { const results = []; for (const [path, methods] of Object.entries(spec.paths)) { for (const [method, op] of Object.entries(methods)) { if (op.tags?.some(t => t.toLowerCase() === 'workers')) { results.push({ method: method.toUpperCase(), path, summary: op.summary }); } } } return results; } // Get endpoint with requestBody schema (refs are resolved) async () => { const op = spec.paths['/accounts/{account_id}/d1/database']?.post; return { summary: op?.summary, requestBody: op?.requestBody }; } // Get endpoint parameters async () => { const op = spec.paths['/accounts/{account_id}/workers/scripts']?.get; return op?.parameters; }
Compare nearby apps
Other Developer Tools connections your agents can use.
Connect to GitHub
GitHub is a code hosting platform for version control and collaboration, offering Git-based repository management, issue tracking, and continuous integration features
Connect to Supabase
Supabase is an open-source backend-as-a-service providing a Postgres database, authentication, storage, and real-time subscription APIs for building modern applications
Connect to Code Interpreter
CodeInterpreter extends Python-based coding environments with integrated data analysis, enabling developers to run scripts, visualize results, and prototype solutions inside supported platforms
Connect to Firecrawl
Firecrawl automates web crawling and data extraction, enabling organizations to gather content, index sites, and gain insights from online sources at scale
Connect to Tavily
Tavily offers search and data retrieval solutions, helping teams quickly locate and filter relevant information from documents, databases, or web sources
Connect to Bitbucket
Bitbucket is a Git-based code hosting and collaboration platform supporting private and public repositories, enabling teams to manage and review code through pull requests and integrations