MCP Job Toolkit
Kit de herramientas de trabajo MCP
Un servidor MCP (Model Context Protocol) que busca empleos en plataformas australianas desde Claude o cualquier cliente compatible con MCP.
Plataformas
Plataforma | Notas |
Seek | Analiza la caché SSR de Apollo desde |
API de empleos para invitados, incluye el número de solicitantes cuando está disponible |
Related MCP server: Jobs MCP Server
Instalación
Requisitos previos: Node.js 18+
git clone https://github.com/afrozk/mcp-job-toolkit.git
cd mcp-job-toolkit
npm install
npm run buildConfiguración de Claude Desktop
Añadir a ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) o %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"mcp-job-toolkit": {
"command": "node",
"args": ["/absolute/path/to/mcp-job-toolkit/dist/index.js"]
}
}
}Reinicia Claude Desktop. La herramienta search_jobs aparecerá automáticamente.
Uso
Una vez conectado, pregúntale a Claude de forma natural:
"Busca puestos de ingeniero backend por contrato en Melbourne publicados en los últimos 7 días" "Busca empleos de analista de datos a tiempo completo en Sídney con un salario superior a 100.000 $/año en Seek" "Muéstrame puestos de ingeniero de software en Brisbane con menos de 20 solicitantes"
Herramienta: search_jobs
Parámetros
Parámetro | Tipo | Predeterminado | Descripción |
| string | obligatorio | Título del puesto, rol o habilidad (ej. |
| string | obligatorio | Ciudad o suburbio australiano (ej. |
| number |
| Radio de búsqueda en km |
| array | all |
|
| string | — |
|
| number | — | Salario mínimo en la unidad que coincida con |
| number | — | Salario máximo |
| string | — |
|
| number | — | Excluir empleos con más solicitantes que este número (donde esté expuesto) |
| array | all |
|
| number |
| Número de página |
| number |
| Resultados por página por plataforma (máx. 25) |
Ejemplo de llamada a la herramienta
{
"keyword": "senior backend engineer",
"location": "Melbourne VIC",
"radius": 30,
"employment_type": ["contract", "fulltime"],
"salary_type": "yearly",
"salary_min": 120000,
"date_posted": "7d",
"max_applications": 25,
"platforms": ["seek", "linkedin"],
"per_page": 10
}Forma de la respuesta
{
"results": [
{
"platform": "seek",
"jobs": [
{
"id": "seek-91878509",
"title": "Senior Backend Engineer",
"company": "Acme Corp",
"location": "Melbourne VIC",
"salary": "$140,000 – $160,000 per year",
"description": "We are looking for...",
"url": "https://au.seek.com/job/91878509",
"posted_at": "2026-05-04T01:54:46.000Z",
"applications_count": null,
"platform": "seek"
}
],
"total": 41,
"page": 1
},
{
"platform": "linkedin",
"jobs": [],
"page": 1
}
],
"summary": [
{ "platform": "seek", "count": 10, "total": 41 },
{ "platform": "linkedin", "count": 8 }
],
"fetched_at": "2026-05-05T00:00:00.000Z"
}Desarrollo
# Run without building (uses tsx)
npm run dev
# Rebuild after changes
npm run build
# Run built server
npm startLicencia
MIT
Available Tools
1 toolsearch_jobsA
Search for jobs across Australian job platforms: Seek and LinkedIn. Supports keyword search, location with radius, employment type, salary, date posted, and application count filters.
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | Job title, skill, or keyword to search for (e.g. "software engineer", "data analyst") | |
| location | Yes | Australian city or suburb (e.g. "Melbourne", "Sydney CBD", "Brisbane QLD", "Perth") | |
| radius | No | Search radius in km from the location (default: 50) | |
| employment_type | No | Filter by employment type. Multiple values allowed. | |
| salary_type | No | Salary payment frequency for filtering | |
| salary_min | No | Minimum salary (in the currency unit matching salary_type, e.g. 80000 for yearly AUD) | |
| salary_max | No | Maximum salary | |
| date_posted | No | Only show jobs posted within this time window | |
| max_applications | No | Only show jobs with fewer than this many applicants (e.g. 10, 20, 25). Not all platforms expose application count. | |
| platforms | No | Which platforms to search (default: all) | |
| page | No | Page number for pagination (default: 1) | |
| per_page | No | Results per page per platform (default: 10, max: 25) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It mentions the platforms and filters but fails to state that the operation is read-only, whether authentication is needed, or how pagination works. Important limitations (e.g., filter compatibility) are only hinted at for one filter.
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 is two sentences: the first defines purpose and scope, the second lists filters. It is front-loaded with key information and contains no superfluous text.
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 high parameter count (12) and no output schema, the description covers the core function adequately but lacks details on return format, pagination behavior, or error conditions. It is minimally complete for an agent to understand basic usage.
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?
All 12 parameters have schema descriptions (100% coverage), so the description adds minimal value beyond what the schema provides. The baseline score of 3 is appropriate; the description lists filter categories but does not elaborate on individual parameters.
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 clearly states the tool's purpose: searching for jobs on Australian platforms (Seek and LinkedIn). It lists supported filters, making it specific and informative. With no sibling tools, differentiation is unnecessary.
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 implies when to use the tool (for job searches in Australia) but does not explicitly state when not to use it or provide alternatives. Since there are no siblings, the implicit guidance is sufficient.
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.
1 tool update
v1.0.0- First observed
search_jobs
TDQS
Scored across 1 tool
Only one tool exists, so there is no potential for confusion with other tools. The tool's purpose is clearly defined.
With a single tool, the naming follows a consistent verb_noun pattern ('search_jobs'), which is clear and predictable.
One tool is on the low end for a 'toolkit,' feeling thin but acceptable for a focused search-only server. It borders the threshold of being too few.
The server only provides search functionality, lacking other expected operations like retrieving job details, saving jobs, or managing applications. The surface is incomplete for a comprehensive job toolkit.
Maintenance
Related MCP Connectors
Public MCP server for discovering open jobs. Search, filter, and get application links.
A hosted LinkedIn MCP server for your own account. Paste one address into Claude, ChatGPT, Cursor or n8n to read your inbox, send messages and invitations, and search people. Free to start. Not made by LinkedIn.
Search live startup jobs from Claude, Cursor, or ChatGPT via MCP. Free, no account needed.
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceMCP server that exposes job search data from multiple boards, enabling clients to query and manage job listings via natural language.7MIT
- AlicenseNot gradedqualityDmaintenanceA custom MCP server that exposes a jobs database to any MCP-compatible LLM client, allowing users to ask in plain English to search, filter, and match job openings.MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server that exposes job-search and application-management capabilities to compatible AI clients, enabling discovery of vacancies, drafting of tailored application materials, and coordinated human-approved submissions.MIT
- FlicenseNot gradedqualityCmaintenanceAn MCP server that enables Claude to search live job postings, rank them against a user's skills profile, and track application statuses locally.-