A
licenseNot graded
qualityNot graded
maintenanceA lightweight MCP server for managing DNS records, purging cache, and interacting with the Cloudflare API through natural language commands.
24
-
mcp-server-cloudflare
Officialby cloudflare
Servidor MCP de Cloudflare
El Protocolo de Contexto de Modelo (MCP) es un nuevo protocolo estandarizado para gestionar el contexto entre modelos de lenguaje grandes (LLMs) y sistemas externos. En este repositorio, puedes encontrar varios servidores MCP que te permiten conectarte al servicio de Cloudflare desde un cliente MCP (por ejemplo, Cursor, Claude) y usar lenguaje natural para realizar tareas a través de tu cuenta de Cloudflare.
Estos servidores MCP permiten que tu cliente MCP lea configuraciones de tu cuenta, procese información, haga sugerencias basadas en datos e incluso realice esos cambios sugeridos por ti. Todas estas acciones pueden ocurrir a través de los numerosos servicios de Cloudflare, incluyendo el desarrollo de aplicaciones, seguridad y rendimiento.
Admiten tanto el transporte streamable-http a través de /mcp como el transporte sse (obsoleto) a través de /sse.
Los siguientes servidores están incluidos en este repositorio:
Nombre del servidor | Descripción | URL del servidor |
Obtén información de referencia actualizada sobre Cloudflare |
| |
Crea aplicaciones de Workers con primitivas de almacenamiento, IA y computación |
| |
Obtén información y gestiona tus compilaciones de Cloudflare Workers |
| |
Depura y obtén información sobre los registros y análisis de tu aplicación |
| |
Obtén información sobre el tráfico global de Internet, tendencias, escaneos de URL y otras utilidades |
| |
Inicia un entorno de desarrollo en sandbox |
| |
Obtén páginas web, conviértelas a markdown y toma capturas de pantalla |
| |
Obtén resúmenes rápidos del estado de los trabajos de Logpush |
| |
Busca en tus registros, obtén detalles sobre las solicitudes y respuestas |
| |
Consulta registros de auditoría y genera informes para su revisión |
| |
Optimiza el rendimiento de DNS y depura problemas basados en la configuración actual |
| |
Obtén información rápida sobre aplicaciones críticas para tu organización |
| |
Identifica rápidamente cualquier configuración de seguridad incorrecta para aplicaciones SaaS y proteger a los usuarios y datos |
| |
Obtén datos de análisis utilizando la API GraphQL de Cloudflare |
|
¿Qué servidor MCP de Cloudflare deberías usar?
Cloudflare ofrece dos categorías de servidores MCP:
Servidor de modo de código (
mcp.cloudflare.com) encloudflare/mcp: es mejor cuando deseas un acceso amplio a través de las API de Cloudflare mediante la ejecución de código.Servidores específicos de dominio (
*.mcp.cloudflare.com) en este repositorio: es mejor cuando deseas herramientas seleccionadas y tipadas para un área de producto específica de Cloudflare.
¿Cuándo deberías usar cada uno?
Usa el servidor de modo de código cuando:
necesites una amplia cobertura de API en muchos productos de Cloudflare
prefieras un conjunto más pequeño de herramientas de propósito general
tu flujo de trabajo se vea mejor servido por la ejecución de código
Usa los servidores específicos de dominio en este repositorio cuando:
desees herramientas diseñadas específicamente para un área de producto
desees interacciones más guiadas y tipadas
trabajes principalmente dentro de un dominio de Cloudflare, como observabilidad, bindings, Radar o renderizado de navegador
Obtén más información sobre el servidor de modo de código aquí: cloudflare/mcp.
Related MCP server: Cloudflare MCP Server
Accede al servidor MCP remoto desde cualquier cliente MCP
Si tu cliente MCP tiene soporte de primera clase para servidores MCP remotos, el cliente proporcionará una forma de aceptar la URL del servidor directamente dentro de su interfaz (por ejemplo, Cloudflare AI Playground)
Si tu cliente aún no admite servidores MCP remotos, deberás configurar su archivo de configuración respectivo usando mcp-remote (https://www.npmjs.com/package/mcp-remote) para especificar a qué servidores puede acceder tu cliente.
{
"mcpServers": {
"cloudflare-observability": {
"command": "npx",
"args": ["mcp-remote", "https://observability.mcp.cloudflare.com/mcp"]
},
"cloudflare-bindings": {
"command": "npx",
"args": ["mcp-remote", "https://bindings.mcp.cloudflare.com/mcp"]
}
}
}Uso de los servidores MCP de Cloudflare desde la API de respuestas de OpenAI
Para usar uno de los servidores MCP de Cloudflare con la API de respuestas de OpenAI, deberás proporcionar a la API de respuestas un token de API que tenga los alcances (permisos) requeridos para ese servidor MCP en particular.
Por ejemplo, para usar el servidor MCP de renderizado de navegador con OpenAI, crea un token de API en el panel de control de Cloudflare aquí, con los siguientes permisos:
¿Necesitas acceso a más herramientas de Cloudflare?
Seguimos añadiendo más funcionalidad a este repositorio de servidores MCP remotos. Si deseas dejar comentarios, informar de un error o realizar una solicitud de función, abre un issue en este repositorio.
Solución de problemas
"La respuesta de Claude fue interrumpida ... "
Si ves este mensaje, es probable que Claude haya alcanzado su límite de longitud de contexto y se haya detenido a mitad de la respuesta. Esto sucede con mayor frecuencia en servidores que activan muchas llamadas a herramientas encadenadas, como el servidor de observabilidad.
Para reducir la posibilidad de encontrarte con este problema:
Intenta ser específico, mantén tus consultas concisas.
Si una sola solicitud llama a varias herramientas, intenta dividirla en varias llamadas a herramientas más pequeñas para mantener las respuestas cortas.
Funciones de pago
Algunas funciones pueden requerir un plan de pago de Cloudflare Workers. Asegúrate de que tu cuenta de Cloudflare tenga el nivel de suscripción necesario para las funciones que pretendes utilizar.
Contribución
¿Te interesa contribuir y ejecutar este servidor localmente? Consulta CONTRIBUTING.md para empezar.
Available Tools
2 toolsmigrate_pages_to_workers_guideARead-only
ALWAYS read this guide before migrating Pages projects to Workers.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
A4.2/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true; description adds no additional behavioral context beyond the instruction to read the guide, which is sufficient for a static document.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded, no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter guide without output schema, the description adequately conveys the tool's purpose and usage context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so schema coverage is 100%. Description does not need to add parameter details; baseline 4 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool is a guide to be read before migrating Pages to Workers, distinguishing it from the sibling search tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use the tool (before migration), though no alternatives or exclusions are discussed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_cloudflare_documentationARead-only
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 Run
- 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.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| results | Yes |
TDQS
A4.1/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations include readOnlyHint=true, so the read-only nature is known. The description adds that results are 'semantically similar chunks', which gives insight into the behavior. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two paragraphs; the first sentence is concise, but the product list in the second paragraph is lengthy. Could be more concise, but overall efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, read-only search), the description covers purpose, usage, and return format. Output schema exists, so return values are explained elsewhere. Adequately complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It lists topics to search, implying the query is a search string, but adds no details about format, length, or constraints. With only one parameter, it's minimally acceptable.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Search the Cloudflare documentation' and lists many product areas. The verb 'search' and resource 'Cloudflare documentation' are specific. The sibling tool 'migrate_pages_to_workers_guide' is clearly different, so no confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description says it 'should be used to answer any question about Cloudflare products or features', providing clear usage context. It does not explicitly exclude cases where more specific tools might be better, but given only one sibling, it's adequate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
v1.0.4- Changed
migrate_pages_to_workers_guide1 field changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
- Changed
search_cloudflare_documentation2 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
1 tool update
v1.0.3- Changed
search_cloudflare_documentation1 field changed- changed
Output schema / (root)Previous value: -nullNew value: +{ + "$schema": "http://json-schema.org/draft-07/schema#", + "additionalProperties": false, + "properties": { + "results": { + "items": { + "additionalProperties": false, + "properties": { + "id": { + "description": "Source file ID", + "type": "string" + }, + "similarity": { + "description": "Similarity score from AI Search", + "type": "number" + }, + "text": { + "description": "Matching documentation chunk text", + "type": "string" + }, + "title": { + "description": "Documentation page title", + "type": "string" + }, + "url": { + "description": "Developer documentation URL", + "type": "string" + } + }, + "required": [ + "similarity", + "id", + "url", + "title", + "text" + ], + "type": "object" + }, + "type": "array" + } + }, + "required": [ + "results" + ], + "type": "object" +}
2 tool updates
v1.0.2- Changed
migrate_pages_to_workers_guide1 field changed- removed
Input schema / additionalPropertiesRemoved value: -false
- Changed
search_cloudflare_documentation1 field changed- removed
Input schema / additionalPropertiesRemoved value: -false
2 tool updates
- First observed
migrate_pages_to_workers_guide - First observed
search_cloudflare_documentation
TDQS
A3.9/5.0
Scored across 2 tools
Disambiguation5/5
The two tools have clearly distinct purposes: one for general documentation search and one specifically for migrating Pages to Workers. There is no overlap.
Naming Consistency4/5
Both tool names follow a verb_noun pattern in snake_case, with 'search_cloudflare_documentation' and 'migrate_pages_to_workers_guide', though the second is much longer.
Tool Count2/5
With only 2 tools, the server feels very thin for the broad domain of Cloudflare products. It likely needs more tools to be useful.
Completeness2/5
Only documentation search and a specific migration guide are provided. Many core Cloudflare operations (e.g., managing resources, troubleshooting) are missing, leading to significant gaps.
Maintenance
ActivityActive
ResponsivenessWithin a week
Related MCP Connectors
Cloudflare Workers MCP server: claude-skill-validator
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Cloudflare Workers MCP server: ai-model-router
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceAn MCP server that allows using natural language to manage Cloudflare resources (Workers, KV, R2, D1) through Claude Desktop, VSCode, and other MCP clients.16 npm10Apache 2.0
Cloudflare MCP Serverofficial
AlicenseNot gradedqualityCmaintenanceA token-efficient MCP server that provides access to the entire Cloudflare API (2500+ endpoints) using a code execution pattern, enabling natural language management of Cloudflare services.9 npm883Apache 2.0- AlicenseCqualityDmaintenanceA high-performance MCP server providing AI assistants with read-only access to the Cloudflare ecosystem. Query your entire Cloudflare infrastructure using natural language through Claude, Cursor, or any MCP-compatible client.3905MIT