Cloudflare

Cloudflare MCP Server

Model Context Protocol (MCP) is a new, standardized protocol for managing context between large language models (LLMs) and external systems. In this repository, we provide an installer as well as an MCP Server for Cloudflare's API.

This lets you use Claude Desktop, or any MCP Client, to use natural language to accomplish things on your Cloudflare account, e.g.:

• Please deploy me a new Worker with an example durable object.
• Can you tell me about the data in my D1 database named '...'?
• Can you copy all the entries from my KV namespace '...' into my R2 bucket '...'?

Demo

Setup

1. Run npx @cloudflare/mcp-server-cloudflare init

   Note: The MCP server will automatically run npx wrangler login if you're not already authenticated with Cloudflare. You'll be prompted to complete the authentication process in your browser if needed.

3. Restart Claude Desktop, you should see a small 🔨 icon that shows the following tools available for use:

Paid Features

Some features in this MCP server require a paid Cloudflare Workers plan:

• Observability and Analytics: The analytics_get tool and related analytics features require a paid Workers plan to access these metrics
• Other premium Cloudflare features like advanced D1 database capabilities and higher usage limits also require appropriate paid plans

Ensure your Cloudflare account has the necessary subscription level for the features you intend to use.

Features

KV Store Management

• get_kvs: List all KV namespaces in your account
• kv_get: Get a value from a KV namespace
• kv_put: Store a value in a KV namespace
• kv_list: List keys in a KV namespace
• kv_delete: Delete a key from a KV namespace

R2 Storage Management

• r2_list_buckets: List all R2 buckets in your account
• r2_create_bucket: Create a new R2 bucket
• r2_delete_bucket: Delete an R2 bucket
• r2_list_objects: List objects in an R2 bucket
• r2_get_object: Get an object from an R2 bucket
• r2_put_object: Put an object into an R2 bucket
• r2_delete_object: Delete an object from an R2 bucket

D1 Database Management

• d1_list_databases: List all D1 databases in your account
• d1_create_database: Create a new D1 database
• d1_delete_database: Delete a D1 database
• d1_query: Execute a SQL query against a D1 database

Workers Management

• worker_list: List all Workers in your account
• worker_get: Get a Worker's script content
• worker_put: Create or update a Worker script
• worker_delete: Delete a Worker script

Durable Objects

• durable_objects_list: List all Durable Objects namespaces
• durable_objects_create: Create a new Durable Objects namespace
• durable_objects_delete: Delete a Durable Objects namespace
• durable_objects_list_instances: List all instances for a specific Durable Objects namespace
• durable_objects_get_instance: Get details about a specific Durable Objects instance
• durable_objects_delete_instance: Delete a specific Durable Objects instance

Queues

• queues_list: List all Queues in your account
• queues_create: Create a new Queue
• queues_delete: Delete a Queue
• queues_get: Get details about a specific Queue
• queues_send_message: Send a message to a Queue
• queues_get_messages: Get messages from a Queue
• queues_update_consumer: Update a Queue consumer

Workers AI

• workers_ai_list_models: List available AI models
• workers_ai_get_model: Get details about a specific AI model
• workers_ai_run_inference: Run inference using Workers AI
• workers_ai_list_tasks: List AI tasks

Workflows

• workflows_list: List all Workflows in your account
• workflows_create: Create a new Workflow
• workflows_delete: Delete a Workflow
• workflows_get: Get details about a specific Workflow
• workflows_update: Update a Workflow
• workflows_execute: Execute a Workflow

Templates

• templates_list: List available Worker templates
• templates_get: Get details about a specific template
• templates_create_from_template: Create a new Worker from a template

Workers for Platforms

• w4p_list_dispatchers: List all Workers for Platforms dispatchers
• w4p_create_dispatcher: Create a new dispatcher
• w4p_delete_dispatcher: Delete a dispatcher
• w4p_get_dispatcher: Get details about a specific dispatcher
• w4p_update_dispatcher: Update a dispatcher configuration

Service Bindings

• bindings_list: List all service bindings for a Worker
• bindings_create: Create a new service binding
• bindings_update: Update a service binding
• bindings_delete: Delete a service binding

URL Routing

• routing_list_routes: List all routes for a Worker
• routing_create_route: Create a new route
• routing_update_route: Update a route
• routing_delete_route: Delete a route

Cron Triggers

• cron_list: List all cron triggers for a Worker
• cron_create: Create a new cron trigger
• cron_update: Update a cron trigger
• cron_delete: Delete a cron trigger

Zones & Domains

• zones_list: List all zones in your account
• zones_create: Create a new zone
• zones_delete: Delete a zone
• zones_get: Get details about a specific zone
• zones_check_activation: Check zone activation status

Secrets

• secrets_list: List all secrets for a Worker
• secrets_put: Create or update a secret
• secrets_delete: Delete a secret

Version Management

• versions_list: List all versions of a Worker
• versions_get: Get details about a specific version
• versions_rollback: Rollback to a previous version

Wrangler Config

• wrangler_get_config: Get the current Wrangler configuration
• wrangler_update_config: Update Wrangler configuration

Analytics

• analytics_get: Retrieve analytics data for your domain
  • Includes metrics like requests, bandwidth, threats, and page views
  • Supports date range filtering

Developing

In the current project folder, run:

pnpm install
pnpm build:watch

Then, in a second terminal:

node dist/index.js init

This will link Claude Desktop against your locally-installed version for you to test. If you're not already authenticated with Wrangler, the server will automatically prompt you to complete the authentication process in your browser.

Testing

The project uses Vitest as the testing framework with MSW (Mock Service Worker) for API mocking.

Running Tests

To run all tests:

1pnpm test

To run tests with coverage:

1pnpm test:coverage

To run a specific test file:

1pnpm test -- tests/tools/queues.test.ts

To run tests in watch mode (useful during development):

1pnpm test:watch

Test Structure

The test suite is organized as follows:

• tests/tools/: Contains tests for each Cloudflare API tool
• tests/mocks/: Contains mock data and request handlers
• tests/utils/: Contains test helper functions
• tests/setup.ts: Global test setup configuration

Each tool test file follows a consistent pattern of testing both successful operations and error handling scenarios.

Usage outside of Claude

To run the server locally, run node dist/index run <account-id>.

If you're using an alternative MCP Client, or testing things locally, emit the tools/list command to get an up-to-date list of all available tools. Then you can call these directly using the tools/call command.

Workers

1// List workers
2worker_list()
3
4// Get worker code
5worker_get({ name: "my-worker" })
6
7// Update worker
8worker_put({
9  name: "my-worker",
10  script: "export default { async fetch(request, env, ctx) { ... }}",
11  bindings: [
12    {
13      type: "kv_namespace",
14      name: "MY_KV",
15      namespace_id: "abcd1234"
16    },
17    {
18      type: "r2_bucket",
19      name: "MY_BUCKET",
20      bucket_name: "my-files"
21    }
22  ],
23  compatibility_date: "2024-01-01",
24  compatibility_flags: ["nodejs_compat"]
25})
26
27// Delete worker
28worker_delete({ name: "my-worker" })

KV Store

1// List KV namespaces
2get_kvs()
3
4// Get value
5kv_get({
6    namespaceId: "your_namespace_id",
7    key: "myKey"
8})
9
10// Store value
11kv_put({
12    namespaceId: "your_namespace_id",
13    key: "myKey",
14    value: "myValue",
15    expirationTtl: 3600 // optional, in seconds
16})
17
18// List keys
19kv_list({
20    namespaceId: "your_namespace_id",
21    prefix: "app_", // optional
22    limit: 10 // optional
23})
24
25// Delete key
26kv_delete({
27    namespaceId: "your_namespace_id",
28    key: "myKey"
29})

R2 Storage

1// List buckets
2r2_list_buckets()
3
4// Create bucket
5r2_create_bucket({ name: "my-bucket" })
6
7// Delete bucket
8r2_delete_bucket({ name: "my-bucket" })
9
10// List objects in bucket
11r2_list_objects({ 
12    bucket: "my-bucket",
13    prefix: "folder/", // optional
14    delimiter: "/", // optional
15    limit: 1000 // optional
16})
17
18// Get object
19r2_get_object({
20    bucket: "my-bucket",
21    key: "folder/file.txt"
22})
23
24// Put object
25r2_put_object({
26    bucket: "my-bucket",
27    key: "folder/file.txt",
28    content: "Hello, World!",
29    contentType: "text/plain" // optional
30})
31
32// Delete object
33r2_delete_object({
34    bucket: "my-bucket",
35    key: "folder/file.txt"
36})

D1 Database

1// List databases
2d1_list_databases()
3
4// Create database
5d1_create_database({ name: "my-database" })
6
7// Delete database
8d1_delete_database({ databaseId: "your_database_id" })
9
10// Execute a single query
11d1_query({
12    databaseId: "your_database_id",
13    query: "SELECT * FROM users WHERE age > ?",
14    params: ["25"] // optional
15})
16
17// Create a table
18d1_query({
19    databaseId: "your_database_id",
20    query: `
21        CREATE TABLE users (
22            id INTEGER PRIMARY KEY AUTOINCREMENT,
23            name TEXT NOT NULL,
24            email TEXT UNIQUE,
25            created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
26        )
27    `
28})

Analytics

1// Get today's analytics
2analytics_get({
3    zoneId: "your_zone_id",
4    since: "2024-11-26T00:00:00Z",
5    until: "2024-11-26T23:59:59Z"
6})

Durable Objects

1// List Durable Objects namespaces
2durable_objects_list()
3
4// Create a new Durable Objects namespace
5durable_objects_create({
6    name: "my-durable-object",
7    script_name: "my-worker",
8    class_name: "MyDurableObjectClass"
9})
10
11// Delete a Durable Objects namespace
12durable_objects_delete({
13    id: "your_namespace_id"
14})
15
16// List instances for a namespace
17durable_objects_list_instances({
18    namespaceId: "your_namespace_id",
19    limit: 100 // optional
20})
21
22// Get details about a specific instance
23durable_objects_get_instance({
24    namespaceId: "your_namespace_id",
25    instanceId: "your_instance_id"
26})
27
28// Delete a specific instance
29durable_objects_delete_instance({
30    namespaceId: "your_namespace_id",
31    instanceId: "your_instance_id"
32})

Queues

1// List all queues
2queues_list()
3
4// Create a new queue
5queues_create({
6    name: "my-queue",
7    settings: {
8        delivery_delay: 0,
9        dead_letter_queue: "dead-letter-queue" // optional
10    }
11})
12
13// Delete a queue
14queues_delete({
15    name: "my-queue"
16})
17
18// Get queue details
19queues_get({
20    name: "my-queue"
21})
22
23// Send a message to a queue
24queues_send_message({
25    queue: "my-queue",
26    messages: [
27        { body: JSON.stringify({ key: "value" }) }
28    ]
29})
30
31// Get messages from a queue
32queues_get_messages({
33    queue: "my-queue",
34    batchSize: 10, // optional
35    visibilityTimeout: 30 // optional, in seconds
36})
37
38// Update a queue consumer
39queues_update_consumer({
40    queue: "my-queue",
41    consumer: "my-consumer",
42    settings: {
43        dead_letter_queue: "dead-letter-queue",
44        batch_size: 10,
45        max_retries: 3
46    }
47})

Workers AI

1// List available AI models
2workers_ai_list_models()
3
4// Get details about a specific model
5workers_ai_get_model({
6    model: "@cf/meta/llama-2-7b-chat-int8"
7})
8
9// Run inference using Workers AI
10workers_ai_run_inference({
11    model: "@cf/meta/llama-2-7b-chat-int8",
12    input: {
13        messages: [
14            { role: "system", content: "You are a helpful assistant." },
15            { role: "user", content: "Hello, who are you?" }
16        ]
17    },
18    options: {
19        temperature: 0.7,
20        max_tokens: 100
21    }
22})
23
24// List AI tasks
25workers_ai_list_tasks()

Workflows

1// List all workflows
2workflows_list()
3
4// Create a new workflow
5workflows_create({
6    name: "my-workflow",
7    content: "// Workflow script content here"
8})
9
10// Delete a workflow
11workflows_delete({
12    name: "my-workflow"
13})
14
15// Get workflow details
16workflows_get({
17    name: "my-workflow"
18})
19
20// Update a workflow
21workflows_update({
22    name: "my-workflow",
23    content: "// Updated workflow script content"
24})
25
26// Execute a workflow
27workflows_execute({
28    name: "my-workflow",
29    input: { key: "value" }
30})

Templates

1// List available templates
2templates_list()
3
4// Get details about a specific template
5templates_get({
6    template: "worker-typescript"
7})
8
9// Create a worker from a template
10templates_create_from_template({
11    name: "my-new-worker",
12    template: "worker-typescript",
13    options: {
14        // Template-specific options
15    }
16})

Workers for Platforms

1// List dispatchers
2w4p_list_dispatchers()
3
4// Create a new dispatcher
5w4p_create_dispatcher({
6    name: "my-dispatcher",
7    script: "// Dispatcher script content"
8})
9
10// Delete a dispatcher
11w4p_delete_dispatcher({
12    name: "my-dispatcher"
13})
14
15// Get dispatcher details
16w4p_get_dispatcher({
17    name: "my-dispatcher"
18})
19
20// Update dispatcher
21w4p_update_dispatcher({
22    name: "my-dispatcher",
23    script: "// Updated dispatcher script content"
24})

Service Bindings

1// List all service bindings for a worker
2bindings_list({
3    workerName: "my-worker"
4})
5
6// Create a new service binding
7bindings_create({
8    workerName: "my-worker",
9    bindingName: "MY_SERVICE",
10    serviceEnvironment: "production",
11    serviceName: "target-worker"
12})
13
14// Update a service binding
15bindings_update({
16    workerName: "my-worker",
17    bindingName: "MY_SERVICE",
18    serviceEnvironment: "staging",
19    serviceName: "target-worker"
20})
21
22// Delete a service binding
23bindings_delete({
24    workerName: "my-worker",
25    bindingName: "MY_SERVICE"
26})

URL Routing

1// List all routes for a worker
2routing_list_routes({
3    workerName: "my-worker"
4})
5
6// Create a new route
7routing_create_route({
8    workerName: "my-worker",
9    pattern: "example.com/*",
10    zoneId: "your_zone_id"
11})
12
13// Update a route
14routing_update_route({
15    routeId: "your_route_id",
16    pattern: "api.example.com/*",
17    zoneId: "your_zone_id"
18})
19
20// Delete a route
21routing_delete_route({
22    routeId: "your_route_id"
23})

Cron Triggers

1// List all cron triggers for a worker
2cron_list({
3    workerName: "my-worker"
4})
5
6// Create a new cron trigger
7cron_create({
8    workerName: "my-worker",
9    schedule: "*/5 * * * *",
10    timezone: "UTC" // optional
11})
12
13// Update a cron trigger
14cron_update({
15    triggerId: "your_trigger_id",
16    schedule: "0 */2 * * *",
17    timezone: "America/New_York"
18})
19
20// Delete a cron trigger
21cron_delete({
22    triggerId: "your_trigger_id"
23})

Zones & Domains

1// List all zones
2zones_list()
3
4// Create a new zone
5zones_create({
6    name: "example.com",
7    account: {
8        id: "your_account_id"
9    }
10})
11
12// Get zone details
13zones_get({
14    zoneId: "your_zone_id"
15})
16
17// Delete a zone
18zones_delete({
19    zoneId: "your_zone_id"
20})
21
22// Check zone activation status
23zones_check_activation({
24    zoneId: "your_zone_id"
25})

Secrets

1// List all secrets for a worker
2secrets_list({
3    workerName: "my-worker"
4})
5
6// Create or update a secret
7secrets_put({
8    workerName: "my-worker",
9    secretName: "API_KEY",
10    secretValue: "your-secret-api-key"
11})
12
13// Delete a secret
14secrets_delete({
15    workerName: "my-worker",
16    secretName: "API_KEY"
17})

Version Management

1// List all versions of a worker
2versions_list({
3    workerName: "my-worker"
4})
5
6// Get details about a specific version
7versions_get({
8    workerName: "my-worker",
9    versionId: "your_version_id"
10})
11
12// Rollback to a previous version
13versions_rollback({
14    workerName: "my-worker",
15    versionId: "your_version_id"
16})

Wrangler Config

1// Get current wrangler configuration
2wrangler_get_config()
3
4// Update wrangler configuration
5wrangler_update_config({
6    config: {
7        name: "my-worker",
8        main: "src/index.ts",
9        compatibility_date: "2024-03-11",
10        workers_dev: true
11    }
12})

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.