Next Role MCP Proxy
Proxy MCP de NextRole
Un servidor proxy del Protocolo de Contexto de Modelo (MCP) que proporciona acceso a los servicios profesionales de adaptación de CV y cartas de presentación de NextRole. Este proxy permite a los clientes compatibles con MCP interactuar con los servicios alojados de NextRole.
Características
Adaptación profesional de CV: Personaliza tu CV para solicitudes de empleo específicas
Generación de cartas de presentación: Crea cartas de presentación adaptadas que coincidan con los requisitos del puesto
Múltiples niveles de servicio: Servicios profesionales de nivel inicial, intermedio y superior
Gestión de créditos: Realiza un seguimiento y gestiona tus créditos de servicio
Soporte internacional: Disponible para usuarios de todo el mundo
Related MCP server: LinkedIn MCP Server
Instalación
Desde el código fuente
Clona el repositorio y ejecuta el script de instalación. Instalará las dependencias, compilará el proyecto e imprimirá el JSON de configuración del cliente MCP para ti.
git clone https://github.com/bats64mgutsi/nextrole-mcp-proxy.git
cd nextrole-mcp-proxyLinux / macOS:
bash install.shWindows (PowerShell):
.\install.ps1Al final del script, verás el JSON de configuración del cliente MCP con la ruta correcta a tu instalación local. Cópialo en el archivo de configuración de tu cliente MCP.
Con npx (sin instalación local)
Añádelo a la configuración de tu cliente MCP:
{
"mcpServers": {
"nextrole": {
"command": "npx",
"args": ["nextrole-mcp-proxy"]
}
}
}Uso
Herramientas disponibles
1. get_pricing
Obtén los niveles de carrera disponibles y sus IDs de producto. Debes llamar a esto antes de realizar un pedido para obtener el productId correcto.
Uso:
What are your different CV tailoring packages?Respuesta:
[
{
"CountryCode": "ZA",
"ServiceTier": "Entry Level",
"ProductId": 1
},
{
"CountryCode": "ZA",
"ServiceTier": "Mid Level",
"ProductId": 2
},
{
"CountryCode": "ZA",
"ServiceTier": "Senior Level",
"ProductId": 3
}
]2. get_credits
Comprueba cuántos créditos le quedan a un cliente. Cada pedido cuesta 1 crédito.
Parámetros:
phoneNumber(obligatorio): Número de teléfono del cliente incluyendo el código de país (ej. +27831234567)
Uso:
How many credits do I have left? My phone number is +27831234567Respuesta:
{
"credits": 5
}3. place_order
Realiza un pedido para un CV y una carta de presentación adaptados. El pedido suele tardar unos 15 minutos en completarse. El cliente recibirá notificaciones por SMS cuando se confirme el pedido y cuando los documentos estén listos. Cuesta 1 crédito por pedido.
Parámetros:
customerPhone(obligatorio): Número de teléfono del cliente incluyendo el código de país, debe comenzar con '+' (ej. +27831234567)customerFirstName(obligatorio): Nombre del clientecustomerLastName(obligatorio): Apellido del clientecvMarkdown(obligatorio): El CV actual del cliente en formato markdownproductId(obligatorio): El ID de producto que coincide con el nivel profesional del cliente (llama primero a get_pricing)jobDescription(obligatorio): La descripción completa del puesto al que aplica el cliente
Uso:
I need to tailor my CV for a Junior Software Developer position. My phone number is +27831234567, my name is John Smith, and here's my current CV in markdown:
# John Smith
## Experience
- Junior Developer at TechCorp (2023-present)
The job description is: We are seeking a Junior Software Developer to join our team with React and Node.js experience.Respuesta:
{
"orderKey": "550e8400-e29b-41d4-a716-446655440000",
"status": "success",
"message": "Order placed successfully. SMS notifications sent."
}Casos de uso de ejemplo
Profesional de nivel inicial
Perfecto para recién graduados y profesionales al inicio de su carrera:
I'm Sarah Johnson (+44207123456) and need my CV tailored for this graduate software engineer role: Graduate Software Engineer requiring Python programming and problem-solving skills.
My current CV:
# Sarah Johnson
## Education
- Computer Science Degree, University of London (2024)
## Projects
- Built a web application using Python and FlaskCambio de carrera
Para profesionales que realizan la transición entre industrias:
I'm transitioning from finance to tech and need my CV (+27831112233, Jane Doe) tailored for this software developer role: Full Stack Developer position requiring JavaScript, React, and database skills.
Current CV:
# Jane Doe
## Background
- Financial Analyst at Bank Corp
- Recently completed coding bootcampEjecutivo senior
Para puestos de nivel C y alta dirección:
I'm Michael Chen from the US (+1555123456) and need my executive CV customized for this CTO role: Chief Technology Officer requiring strategic leadership and team management skills.
My current CV:
# Michael Chen
## Executive Summary
Senior Technology Leader with 15+ years experience
## Experience
- VP Engineering at Tech Startup (2020-2024)Niveles de servicio
Nivel inicial (ID de producto: 1): Para recién graduados y profesionales al inicio de su carrera
Nivel intermedio (ID de producto: 2): Para profesionales experimentados con 3-10 años de experiencia
Nivel senior (ID de producto: 3): Para profesionales senior, gerentes y ejecutivos
Privacidad y términos
Al utilizar este servicio, aceptas los siguientes documentos de NextRole:
Desarrollo
Compilación
npm run buildEjecución en desarrollo
npm run devPruebas locales
npm startArquitectura
Este es un proxy ligero que reenvía las solicitudes MCP al servicio alojado de NextRole en https://api.nextrole.co.za/firstroleprod-mcp/mcp. El proxy:
Traduce las solicitudes del protocolo MCP
Las reenvía al servicio alojado
Devuelve respuestas formateadas a los clientes MCP
Maneja errores y problemas de conexión
Requisitos
Node.js 18.0.0 o superior
Conexión a Internet para acceder al servicio alojado de NextRole
Licencia
Licencia MIT - consulta el archivo LICENSE para más detalles.
Soporte
Para problemas técnicos con este proxy, por favor abre un issue en GitHub. Para preguntas relacionadas con el servicio, contacta al soporte de NextRole a través de sus canales oficiales.
Available Tools
3 toolsget_creditsA
Check how many credits a customer has remaining. Each order to tailor a CV and cover letter costs 1 credit.
| Name | Required | Description | Default |
|---|---|---|---|
| phoneNumber | Yes | Customer phone number including country code (e.g. +27831234567) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It adds valuable domain context explaining what credits are used for (1 per CV/cover letter order), but lacks operational details like error handling, what happens if phone number not found, or caching behavior.
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?
Perfectly concise with two sentences. First states purpose immediately; second provides essential domain context about credit costs. Zero redundancy.
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?
For a simple single-parameter read operation without output schema, the description is nearly complete. It explains the credit system which is essential domain context. Minor gap: doesn't hint at return value structure or error states.
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?
Schema has 100% coverage with phoneNumber fully documented. Description mentions 'customer' which loosely maps to the parameter, but adds no additional semantics, format constraints, or examples beyond what the schema already provides. Baseline 3 is appropriate.
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?
Excellent clarity: specifies the verb 'Check', resource 'credits', and scope 'remaining'. The second sentence distinguishes the domain context (CV/cover letter tailoring) which differentiates this from generic balance checking tools.
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?
Provides implied usage context by explaining that orders cost 1 credit, suggesting this should be checked before placing orders. However, lacks explicit when-to-use guidance or direct comparison to siblings (get_pricing, place_order).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_pricingA
Get the available career-level tiers and their product IDs. Different products are designed for different career phases, so the customer should pick the tier that best matches where they are in their career. You must call this before placing an order to get the correct productId.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It successfully explains the business logic (career phases) and workflow ordering (must precede place_order), but lacks technical behavioral traits such as whether the operation is idempotent, cached, or rate-limited, and provides only high-level description of return values without structural details.
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?
The description consists of three efficiently structured sentences: the first defines the core action, the second provides business context for selection, and the third states the workflow prerequisite. Every sentence earns its place with no redundant or filler content.
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?
Despite lacking an output schema, the description partially compensates by explaining that the tool returns 'career-level tiers and their product IDs'. Combined with the explicit workflow integration (prerequisite for place_order), this provides sufficient context for a zero-parameter lookup tool, though specific return structure details would strengthen it further.
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?
The input schema contains zero parameters. Per evaluation rules, zero-parameter tools receive a baseline score of 4. The description appropriately does not mention parameters since none exist.
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?
The description explicitly states the tool retrieves 'career-level tiers and their product IDs' using the specific verb 'Get'. It distinguishes itself from sibling tools by explaining its role as a prerequisite for place_order (getting productId), clearly differentiating it from get_credits.
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?
The description provides explicit workflow guidance: 'You must call this before placing an order to get the correct productId.' It also includes selection criteria ('customer should pick the tier that best matches where they are in their career'), giving clear context on when and how to use the results.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
place_orderA
Place an order for a tailored CV and cover letter. The order typically takes about 15 minutes to complete. The customer will receive an SMS confirming their order and another SMS when their documents are ready to download. Costs 1 credit per order.
| Name | Required | Description | Default |
|---|---|---|---|
| customerPhone | Yes | Customer phone number including country code, must start with '+' (e.g. +27831234567). SMS notifications will be sent to this number. | |
| customerFirstName | Yes | Customer's first name | |
| customerLastName | Yes | Customer's last name | |
| cvMarkdown | Yes | The customer's current CV in markdown format. This is used as the basis for tailoring their documents. | |
| productId | Yes | The product ID that matches the customer's career level. Call get_pricing first to see available career-level tiers and their product IDs. | |
| jobDescription | Yes | The full job description the customer is applying for. The CV and cover letter will be tailored to match this role. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden, effectively disclosing key behavioral traits: processing time (~15 minutes), notification mechanism (two SMS messages), and cost (1 credit). It omits idempotency or error handling details.
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?
Four tightly constructed sentences with zero waste: purpose, timing, notifications, and cost. Information is front-loaded and every sentence earns its place.
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?
Given the 6-parameter complexity and lack of annotations/output schema, the description is reasonably complete, covering the user journey (order → SMS confirmation → SMS completion). It could strengthen by noting the prerequisite check for credits.
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?
The input schema has 100% description coverage, establishing a baseline of 3. The description text does not add parameter-specific semantics (e.g., explaining markdown format or productId sourcing), relying entirely on the schema.
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?
The description opens with a specific verb ('Place') and clear resource ('order for a tailored CV and cover letter'), immediately distinguishing it from the read-only sibling tools get_credits and get_pricing.
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?
The description mentions 'Costs 1 credit per order,' implying a prerequisite to check credits, but lacks explicit guidance on when to use versus alternatives or a required workflow (e.g., calling get_pricing first to obtain the productId).
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.
3 tool updates
v0.1.0- First observed
get_credits - First observed
get_pricing - First observed
place_order
TDQS
Each tool serves a distinct purpose with clear boundaries: get_credits checks account balance, get_pricing retrieves product catalog, and place_order executes transactions. No functional overlap exists between the three operations.
All tools follow a consistent verb_noun snake_case convention. The naming clearly distinguishes between retrieval operations (get_) and the transactional operation (place_).
Three tools is minimal but reasonable for a focused ordering workflow. While the surface is thin, it covers the essential path from balance check to order completion without unnecessary bloat.
The toolset supports order creation but lacks order management capabilities such as status checking, order history retrieval, or cancellation. Once place_order is called, the agent has no visibility into order progress, creating a dead end for follow-up queries.
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
Generate tailored, ATS-optimized resume PDFs and cover letters from a job description, over MCP.
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA specialized Model Context Protocol (MCP) server that enables AI-powered interview roleplay scenarios for practice with realistic conversational feedback.447Apache 2.0
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables seamless interaction with LinkedIn for job applications, profile retrieval, feed browsing, and resume analysis through natural language commands.31-
- AlicenseAqualityDmaintenanceA Model Context Protocol server for accessing NovaCV resume services API, enabling users to generate PDF resumes, analyze resume content, convert resume text to JSON format, and get available resume templates.4213MIT
- AlicenseNot gradedqualityDmaintenanceExposes a personalized AI agent that reads your resume and provides intelligent responses about your professional background through a standardized MCP server interface with RAG capabilities.MIT
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/bats64mgutsi/nextrole-mcp-proxy'
If you have feedback or need assistance with the MCP directory API, please join our Discord server