AIAny
Icon for item

Cloudflare MCP Server

Official remote MCP servers that let AI agents read and change Cloudflare config in natural language — managing Workers and bindings, querying observability and DNS analytics, searching docs. Each capability is a separate scoped server.

Introduction

Most MCP integrations bolt one tool onto one API. Cloudflare took the opposite route: instead of a single monolithic server, it ships a dozen narrowly-scoped remote servers, each fronting one slice of its platform — Workers bindings, observability, DNS analytics, browser rendering, audit logs, AI Gateway, and more. You connect only the ones a given agent actually needs, which keeps the tool surface (and the blast radius) small.

What Sets It Apart
  • Remote and OAuth-based, not local: servers run on Cloudflare's edge and authenticate against your real account, so an agent operates on live config rather than a sandbox copy — and you grant access per server, not all-or-nothing.
  • Read and write, not just read: beyond querying logs or DNS analytics, agents can manage Workers and their storage/AI/compute bindings, turning "explain my setup" into "change my setup."
  • Coverage spans the whole platform: documentation search, Logpush health, CASB SaaS security, Digital Experience Monitoring, and a raw GraphQL analytics server mean one vendor's agent tooling reaches most of what Cloudflare offers.
Who It's For

Great fit if you run real workloads on Cloudflare and want an agent that can investigate incidents, audit security posture, or adjust Workers without you clicking through the dashboard. Look elsewhere if you're not a Cloudflare customer — these servers are useless without an account — or if you need a self-hosted, air-gapped MCP setup, since they're designed to run remotely against Cloudflare's own infrastructure.

Information

  • Websitegithub.com
  • OrganizationsCloudflare, Inc.
  • AuthorsCloudflare
  • Published date2024/11/27

Categories

More Items

GitHub
AI Client2025

Turns Chromium into a local-first AI browser with an embedded assistant that can summarise pages, extract structured data, automate web tasks, and run scheduled agents. Built as an open-source Chromium fork with 53+ built-in browser tools, 40+ app integrations, and support for BYO AI keys or fully local models (Ollama / LM Studio).

GitHub

Runs a self-hosted meeting bot and transcription API that joins Google Meet, Teams and Zoom and streams speaker-attributed transcripts in real time. Compiles meetings into a git-backed Markdown workspace and runs sandboxed agents on your infrastructure; Apache-2.0 and air-gap capable.

GitHub

Lets AI agents produce expressive, polished charts from compact, human-editable semantic specs; the compiler infers layout, scales, and labels and emits Vega-Lite, ECharts, or Chart.js outputs, with an MCP server for agent-driven chart creation and rendering.