Lets an AI client search and call any Cloudflare API endpoint, run GraphQL analytics queries, and read Cloudflare developer docs.
Also known as cloudflare/mcp
- Stars
- 1,096
- Tools
- 4
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 15, 2026
- License
- Apache-2.0
What is Cloudflare MCP?
Cloudflare lets an AI client search and call any Cloudflare API endpoint, run GraphQL analytics queries, and read Cloudflare developer docs. It exposes 4 tools, such as docs, search, execute.
Summary generated from the project's README
About Cloudflare MCP server
Managing Cloudflare infrastructure through an AI client is possible with this MCP server, which provides access to over 2,500 API endpoints. It is designed for developers who need to interact with products like Workers, KV, R2, D1, and DNS without consuming massive amounts of context window. By utilizing a code execution pattern, the server keeps token usage extremely low, requiring only about 1,100 tokens compared to the millions needed for a raw OpenAPI specification.
Users can connect via OAuth for easy authorization or use a Cloudflare API token for automation and CI/CD workflows. The server provides specific tools including search for finding endpoints, execute for making API calls or running GraphQL analytics queries, docs for reading developer documentation, and whoami to identify the authenticated user or account. It can also serve Cloudflare skills related to Wrangler and Durable Objects through the MCP skills extension.
What you can do with it
- 1Running complex analytics queriesDevelopers can use the execute tool to run GraphQL queries against the Cloudflare Analytics API to retrieve traffic data.
- 2Searching technical documentationYou can ask an AI client to find specific implementation details within the official Cloudflare developer guides.
- 3Efficient API discoveryInstead of loading a massive specification, the agent uses JavaScript to find specific paths within the API spec.
Written from the project's README. Every use case is checked against a quote from it.
Cloudflare MCP tools 4
Detected from the READMEdocssearchexecutewhoami
| docs | — | |
| search | — | |
| execute | — | |
| whoami | — |
Automated checks
Ran Nov 12, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packageNot checked
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubCloudflare MCP Server
A token-efficient MCP server for the entire Cloudflare API. 2500 endpoints in 1k tokens, powered by Code Mode.
Token Comparison
| Approach | Tools | Token cost | Context used (200K) |
|---|---|---|---|
| Raw OpenAPI spec in prompt | — | ~2,000,000 | 977% |
| Native MCP (full schemas) | 2,594 | 1,170,523 | 585% |
| Native MCP (minimal — required params only) | 2,594 | 244,047 | 122% |
| Code mode | 3 | ~1,100 | 0.5% |
Get Started
MCP URL: https://mcp.cloudflare.com/mcp
Option 1: OAuth (Recommended)
Just connect to the MCP server URL - you'll be redirected to Cloudflare to authorize and select permissions.
Example JSON Configuration
{
"mcpServers": {
"cloudflare-api": {
"type": "http",
"url": "https://mcp.cloudflare.com/mcp"
}
}
}
Option 2: API Token
For CI/CD, automation, or if you prefer managing tokens yourself.
Create a Cloudflare API token with the permissions you need. Both user tokens and account tokens are supported. For account tokens, include the Account Resources : Read permission so the server can auto-detect your account ID.
Note: API tokens with Client IP Address Filtering enabled are not currently supported.
Add to Agent
| Setting | Value |
|---|---|
| MCP URL | https://mcp.cloudflare.com/mcp |
| Bearer Token | Your Cloudflare API Token |
Disable Code Mode
If your MCP client already uses code mode, or you're composing this server with another server that uses code mode, you can disable it with the ?codemode=false query parameter. This registers a tool for each Cloudflare API method instead of the code mode API tools, about 3,000, generated by forge. Each takes its arguments grouped by where they go: { path, query, headers, body }. The docs and whoami tools remain available in both modes.
https://mcp.cloudflare.com/mcp?codemode=false
Example JSON Configuration
{
"mcpServers": {
"cloudflare-api": {
"type": "http",
"url": "https://mcp.cloudflare.com/mcp?codemode=false"
}
}
}
When code mode is disabled:
- Each API endpoint is registered as its own tool (e.g.,
get_workers_scripts,post_d1_database) - Tool input schemas are derived from the endpoint's path parameters, query parameters, and request body
- Tools make direct API calls — no code execution involved
- Path parameters like
account_idare auto-resolved when possible (single account)
Note: Disabling code mode significantly increases the token cost (~244k tokens vs ~1k tokens). Only disable it when necessary for composition with other code mode systems.
Tool Result Truncation
In code mode, the server caps each search and execute result at ~6,000 tokens, to avoid context overload. Oversized JSON stays valid JSON: long lists keep their first items whole, long strings are clipped, and every cut is marked with --- TRUNCATED ---. An agent that writes a result straight to a file or pipe, rather than reading it into the conversation, can pass truncate: false to that call to get the whole result.
Note: Without the cap, a broad query can return megabytes. Only turn it off when the result doesn't go to the model.
With code mode disabled, the direct tools return whole results. The clients that disable it usually run code mode themselves: they call the direct tools from their own code and parse each result, so a capped result would lose data.
Missing Permissions
When Cloudflare refuses a call because the OAuth connection lacks a scope, the server asks the client to re-authorize with that scope added to the ones it already has. Claude and other clients that follow the MCP authorization spec get a 403 insufficient_scope challenge. Codex and ChatGPT get it in the tool result, which is where they look for it. Either way, the tool error says which scope is missing. Some endpoints, such as GET /zones, don't refuse: they answer with an empty list when the scope is missing. An empty list from a read the connection holds no accepted scope for is refused the same way, so it isn't mistaken for an empty account.
The Problem
The Cloudflare OpenAPI spec is 2 million tokens. Even with native MCP tools using minimal schemas, it's still ~244k tokens. Traditional MCP servers that expose every endpoint as a tool leak this entire context to the main agent.
This server solves the problem by using code execution in a Code Mode pattern - the spec lives on the server, and only the result of the code execution is returned to the agent.
Tools
Agent writes code to search the spec and execute API calls. It can also search Cloudflare's developer documentation directly.
| Tool | Description |
|---|---|
docs |
Search Cloudflare developer documentation |
search |
Write JavaScript to query spec.paths and find endpoints |
execute |
Write JavaScript to call cloudflare.request() with the discovered endpoints |
whoami |
Return the Cloudflare user or account this connection is authenticated as |
Agent MCP Server
│ │
├──search({code: "..."})───────►│ Execute code against spec.json
│◄──[matching endpoints]────────│
│ │
├──execute({code: "..."})──────►│ Execute code against Cloudflare API
│◄──[API response]──────────────│
whoami takes no arguments and returns { id, email } for a user credential or { id, name } for an account token. The id is user:<user id> or account:<account id>, so it stays the same across token refresh, reconnection and permission changes. Clients can use it to tell connected accounts apart; it is marked as an OpenAI profile tool.
Skills
The server also serves the Cloudflare skills (Wrangler, Durable Objects, Agents SDK, Workers best practices and more) through the MCP Skills extension. Clients that support it discover them with skills/list and read each file at skill://<name>/<path>. The catalog is synced from GitHub every six hours.
Supported Products
Workers, KV, R2, D1, Pages, DNS, Firewall, Load Balancers, Stream, Images, AI Gateway, Vectorize, Access, Gateway, and more. The server ships the OpenAPI document from a pinned Forge release (openapi.forge.json), updated by pull request.
Usage
Once configured, just ask your agent to do things with Cloudflare:
- "List all my Workers"
- "Create a KV namespace called 'my-cache'"
- "Add an A record for api.example.com pointing to 192.0.2.1"
The agent will search for the right endpoints and execute the API calls. Here's what happens behind the scenes:
// 1. Search for endpoints
search({
code: `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;
}`,
});
// 2. Execute API call (user token - account_id required)
execute({
code: `async () => {
const response = await cloudflare.request({
method: "GET",
path: \`/accounts/\${accountId}/workers/scripts\`
});
return response.result;
}`,
account_id: "your-account-id",
});
// 2. Execute API call (account token - account_id auto-detected)
execute({
code: `async () => {
const response = await cloudflare.request({
method: "GET",
path: \`/accounts/\${accountId}/workers/scripts\`
});
return response.result;
}`,
});
GraphQL Analytics API
The server automatically detects and handles Cloudflare's GraphQL Analytics API endpoints. GraphQL queries work seamlessly through the same execute tool:
execute({
code: `async () => {
const response = await cloudflare.request({
method: "POST",
path: "/client/v4/graphql",
body: {
query: \`query {
viewer {
zones(filter: { zoneTag: "your-zone-id" }) {
httpRequests1dGroups(limit: 7, orderBy: [date_ASC]) {
dimensions {
date
}
sum {
requests
bytes
cachedBytes
}
}
}
}
}\`,
variables: {}
}
});
return response.result;
}`,
account_id: "your-account-id",
});
Build a Code Mode MCP Server
Code execution uses Cloudflare's Dynamic Worker Loader API to run generated code in isolated Workers, following the Code Mode pattern.
Read the Code Mode SDK docs for more info.
Resources
Cloudflare MCP questions
What tools does Cloudflare MCP provide?
It exposes 4 tools, including docs, search, execute, whoami.
Can I use a Cloudflare API token instead of OAuth?
Yes. Create a Cloudflare API token with the permissions you need; both user tokens and account tokens are supported. Account tokens need the Account Resources : Read permission so the account ID is auto-detected.
Which Cloudflare products does the MCP server support?
It covers Workers, KV, R2, D1, Pages, DNS, Firewall, Load Balancers, Stream, Images, AI Gateway, Vectorize, Access, Gateway and more.
How does code mode keep token usage low?
Instead of exposing thousands of tool schemas, the server keeps the OpenAPI spec on its side and exposes three tools; the agent writes JavaScript to search the spec and execute API calls.
Can I turn off code mode?
Yes, append ?codemode=false to the MCP URL to register one tool per Cloudflare API method, though this greatly increases token cost.