Unbundle OpenAPI Specs MCP
Desvincular el servidor MCP de OpenAPI
Este proyecto proporciona un servidor de Protocolo de Contexto de Modelo (MCP) con herramientas para dividir los archivos de especificación de OpenAPI en varios archivos o extraer puntos finales específicos en un nuevo archivo. Permite a un cliente MCP (como un asistente de IA) manipular las especificaciones de OpenAPI mediante programación.
Prerrequisitos
Node.js (versión LTS recomendada, por ejemplo, v18 o v20)
npm (viene con Node.js)
Related MCP server: openapi-mcp-proxy
Uso
Instalación mediante herrería
Para instalar Unbundle OpenAPI MCP Server para Claude Desktop automáticamente a través de Smithery :
npx -y @smithery/cli install @auto-browse/unbundle_openapi_mcp --client claudeLa forma más sencilla de utilizar este servidor es a través de npx , lo que garantiza que siempre esté utilizando la última versión sin necesidad de una instalación global.
npx @auto-browse/unbundle-openapi-mcp@latestAlternativamente, puedes instalarlo globalmente (generalmente no se recomienda):
npm install -g @auto-browse/unbundle-openapi-mcp
# Then run using: unbundle-openapi-mcpEl servidor se iniciará y escuchará las solicitudes MCP en la entrada/salida estándar (stdio).
Configuración del cliente
Para usar este servidor con clientes MCP como VS Code, Cline, Cursor o Claude Desktop, agregue su configuración al archivo de configuración correspondiente. El método recomendado es npx .
VS Code / Cline / Cursor
Agregue lo siguiente a su User settings.json (accesible a través de Ctrl+Shift+P > Preferences: Open User Settings (JSON) ) o a un archivo .vscode/mcp.json en la raíz de su espacio de trabajo.
// In settings.json:
"mcp.servers": {
"unbundle_openapi": { // You can choose any key name
"command": "npx",
"args": [
"@auto-browse/unbundle-openapi-mcp@latest"
]
}
// ... other servers can be added here
},
// Or in .vscode/mcp.json (omit the top-level "mcp.servers"):
{
"unbundle_openapi": { // You can choose any key name
"command": "npx",
"args": [
"@auto-browse/unbundle-openapi-mcp@latest"
]
}
// ... other servers can be added here
}Escritorio de Claude
Agregue lo siguiente a su archivo claude_desktop_config.json .
{
"mcpServers": {
"unbundle_openapi": {
// You can choose any key name
"command": "npx",
"args": ["@auto-browse/unbundle-openapi-mcp@latest"]
}
// ... other servers can be added here
}
}Después de agregar la configuración, reinicie su aplicación cliente para que los cambios surtan efecto.
Herramientas MCP proporcionadas
split_openapi
Descripción: Ejecuta el comando redocly split para descomponer un archivo de definición de OpenAPI en varios archivos más pequeños según su estructura.
Argumentos:
apiPath(cadena, obligatoria): la ruta absoluta al archivo de definición de OpenAPI de entrada (por ejemplo,openapi.yaml).outputDir(cadena, obligatoria): La ruta absoluta al directorio donde se guardarán los archivos de salida divididos. Este directorio se creará si no existe.
Devoluciones:
En caso de éxito: un mensaje de texto que contiene la salida estándar del comando
redocly split(generalmente un mensaje de confirmación).En caso de error: un mensaje de error que contiene los detalles del error estándar o de la excepción de la ejecución del comando, marcado con
isError: true.
Ejemplo de uso (solicitud MCP conceptual):
{
"tool_name": "split_openapi",
"arguments": {
"apiPath": "/path/to/your/openapi.yaml",
"outputDir": "/path/to/output/directory"
}
}extract_openapi_endpoints
Descripción: Extrae puntos de conexión específicos de un archivo de definición OpenAPI grande y crea un nuevo archivo OpenAPI más pequeño que contiene únicamente esos puntos de conexión y sus componentes referenciados. Esto se logra dividiendo el archivo original, modificando la estructura para conservar únicamente las rutas especificadas y, a continuación, empaquetando el resultado.
Argumentos:
inputApiPath(cadena, obligatoria): la ruta absoluta al archivo de definición de OpenAPI de entrada grande.endpointsToKeep(matriz de cadenas, obligatorio): Una lista de las rutas exactas de los endpoints (cadenas) que se incluirán en la salida final (p. ej.,["/api", "/api/projects/{id}{.format}"]). Se ignorarán las rutas que no se encuentren en la especificación original.outputApiPath(cadena, obligatoria): La ruta absoluta donde se guardará el archivo OpenAPI final, más pequeño y empaquetado. El directorio se creará si no existe.
Devoluciones:
En caso de éxito: un mensaje de texto que indica la ruta del archivo creado y la salida estándar del comando
redocly bundle.En caso de error: un mensaje de error que contiene detalles sobre el paso que falló (dividir, modificar, agrupar), marcado con
isError: true.
Ejemplo de uso (solicitud MCP conceptual):
{
"tool_name": "extract_openapi_endpoints",
"arguments": {
"inputApiPath": "/path/to/large-openapi.yaml",
"endpointsToKeep": ["/users", "/users/{userId}/profile"],
"outputApiPath": "/path/to/extracted-openapi.yaml"
}
}Nota: Este servidor utiliza internamente npx @redocly/cli@latest para ejecutar los comandos subyacentes split y bundle . Es posible que se requiera una conexión a internet para que npx obtenga @redocly/cli si no está almacenado en caché. Los archivos temporales se crean durante el proceso extract_openapi_endpoints y se limpian automáticamente.
Desarrollo
Si desea contribuir o ejecutar el servidor desde la fuente:
Clonar: Clonar este repositorio.
Navegar:
cd unbundle_openapi_mcpInstalar dependencias:
npm installCompilación:
npm run build(compila TypeScript endist/)Ejecutar:
npm start(inicia el servidor usando el código compilado endist/)
Available Tools
2 toolsextract_openapi_endpointsD
| Name | Required | Description | Default |
|---|---|---|---|
| endpointsToKeep | Yes | List of exact endpoint paths to keep (e.g., ['/users', '/users/{id}']). | |
| inputApiPath | Yes | Absolute path to the large input OpenAPI definition file. | |
| outputApiPath | Yes | Absolute path where the final, smaller bundled OpenAPI file should be saved. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
split_openapiD
| Name | Required | Description | Default |
|---|---|---|---|
| apiPath | Yes | Absolute path to the input OpenAPI definition file. | |
| outputDir | Yes | Absolute path to the directory for split output files. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
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. Dates show when Glama detected each change.
2 tool updates
v1.0.0- First observed
extract_openapi_endpoints - First observed
split_openapi
TDQS
The two tools have clearly distinct purposes: 'extract_openapi_endpoints' likely retrieves endpoints from an OpenAPI spec, while 'split_openapi' probably divides a spec into parts. There is no overlap in functionality, though the lack of descriptions leaves some room for minor uncertainty about exact differences.
Both tools follow a consistent snake_case naming pattern with a verb_noun structure ('extract_endpoints', 'split_openapi'). The naming is predictable and aligned, making it easy to understand the action and target for each tool.
With only two tools, the server feels thin for its purpose of unbundling OpenAPI specs. This limited set may not cover essential operations like validation, merging, or transformation, leaving obvious gaps in functionality for a domain that typically requires more comprehensive handling.
The tool surface is severely incomplete for unbundling OpenAPI specs. Missing are tools for tasks such as validating specs, merging split parts, converting formats, or handling errors. Agents will likely encounter dead ends when trying to perform common workflows in this domain.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
APIs.guru MCP — keyless directory of 2,500+ public APIs and their OpenAPI specs.
MCP Hub: AI service discovery, per-user OAuth, and multi-service workflow orchestration
JSON Schema validation MCP.
MCP-Native LLM Orchestration Agent
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceMCP server providing token-efficient access to OpenAPI/Swagger specs via MCP Resources for client-side exploration.23476MIT
- AlicenseAqualityDmaintenanceAn MCP server that provides tools for exploring large OpenAPI schemas without loading entire schemas into LLM context. Perfect for discovering and analyzing endpoints, data models, and API structure efficiently.914MIT
- AlicenseNot gradedqualityCmaintenanceA stateless gateway that turns any OpenAPI spec into MCP tools on the fly.1MIT
- AlicenseAqualityCmaintenanceParses Swagger 2.0 and OpenAPI 3.x specifications, exposing API endpoints, schemas, and authentication through MCP tools with local caching to reduce token usage.11271MIT
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gurvinder-dhillon/unbundle_openapi_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server