Un servidor MCP para la búsqueda de empleo bajo una restricción de visado.
Si necesitas patrocinio, la mayoría de las herramientas de búsqueda de empleo responden a la pregunta equivocada. Te dicen que un puesto existe. No te dicen si el empleador puede contratarte legalmente, ni si el título «nivel medio» oculta una función de senior, ni si la empresa que publica la oferta es una agencia de reclutamiento que no tiene licencia alguna.
Este servidor responde a esas preguntas. Expone cuatro herramientas a través del Model Context Protocol para que un asistente de IA pueda comprobarlas por sí mismo en lugar de adivinar.
Herramienta | Responde |
| ¿Tiene este empleador de un Reino Unido una licencia de Trabajador Cualificado (Skilled Worker) y cuánto puedo fiarme de la coincidencia? |
| ¿Hay barreras infranqueables? ¿El título dice la verdad sobre la senioridad? |
| ¿Qué hay publicado ahora mismo, excluyendo a las agencias? |
| ¿Ya me he postulado aquí? |
Related MCP server: JobFindsMe
La forma más obvia de comprobar una licencia de patrocinio es buscar el nombre de la empresa en el registro. Así empezó esto, y falla lo bastante a menudo como para ser peligroso.
Los nombres de las empresas colisionan. Para emparejar Pimberly con su nombre registrado Pimberly Software Development Limited hay que quitar palabras como "Software" y "Limited". Esa misma normalización convierte Minerva Defence en minerva, que coincide con trece empresas sin relación: un negocio de mobiliario, una agencia de crédito y un proveedor de vivienda asistida.
Por eso check_sponsor devuelve un grado de confianza en lugar de un booleano:
high — la parte distintiva del nombre coincidió exactamente, una sola vez.
verify — algo coincidió, pero podría ser casualidad. Confirma la entidad legal registrada del empleador y luego busca ese nombre.
none — no coincidió nada. Esto no es una prueba de que no puedan patrocinar. Muchos empleadores con licencia comercializan con un nombre distinto al registrado.
Casos reales que dieron forma a esto:
Buscado | Coincidencia | Lo que era cierto |
Minerva Defence | 13 filas "Minerva" no relacionadas |
|
Prevail | Prevail Technology Limited (Poole) | El empleador es |
MAGIC | MAGIC SOFTWARE SERVICES LTD | Respuesta correcta, prueba incorrecta. El empleador es |
TransPerfect | PERFECT DIGITAL LTD | Coincidió con la palabra "perfect" |
eFinancialCareers | eFinancialCareers Ltd | Correcto e inútil: tiene licencia, pero es un portal de trabajo. Las facilidades a su nombre son de terceros sin nombre |
screen_posting read the body, not the titleUna oferta titulada "Software Engineer" abría con «Como ingeniero de software sénior, tendrás que…» y pedía a alguien unirse al «equipo fundador». Otra oferta titulada "Software Engineer (Java Mid)" mencionaba una posición sénior tres párrafos más abajo. Filtrar por el título se pierde ambas.
screen_posting también detecta barreras infranqueables que ninguna adaptación de la candidatura puede superar:
You must be a UK citizen and have lived in the UK for the past 10 years.
You must already hold high-level UK security clearance.y la que más importa cuando necesitas patrocinio, de una empresa que tiene una licencia con calificación A:
We are unable to offer visa sponsorship for this role. Candidates who need visa
sponsorship now or will need it in the future will not be considered.Una licencia no significa que una empresa puede patrocinarutshell. No significa que lo hará.
search_roles returns a funnelLos portales de empleo del Reino Unido están dominados por agencias de reclutamiento, y una agencia no tiene la licencia de patrocinio del puesto que publica. Excluirlas es esencial y es brutal: una búsqueda típica pasa de siete resultados a uno.
Un único resultado sin explicación parece un error. Por eso, la herramienta devuelve lo que cada etapa eliminó:
{
"totalFromSource": 7,
"funnel": { "fromSource": 7, "afterAgencyFilter": 2, "afterSalaryAndAge": 1 },
"notes": ["5 of 7 results were recruitment agencies or job boards. ..."]
}Los salarios no publicados se conservan, nunca se eliminan. El silencio sobre el salario no es una prueba de que el salario sea bajo.
npm install && npm run buildDescarga el registro actual (unos 11 MB, actualizado con regularidad):
https://www.gov.uk/government/publications/register-of-licensed-sponsors-workers
Guárdalo como data/register.csv o apunta SPONSOR_REGISTER_PATH hacia él.
{
"mcpServers": {
"job-search": {
"command": "node",
"args": ["/absolute/path/to/job-search-mcp/dist/index.js"],
"env": {
"SPONSOR_REGISTER_PATH": "/absolute/path/to/data/register.csv",
"REED_API_KEY_FILE": "/absolute/path/to/.reed-api-key"
}
}
}
}Variable | Otocolor | Propósito |
| no | CSV del registro. El valor por defecto es |
| para | Ruta de un archivo que contiene la clave. Preferible: el secreto vive en un solo sitio y la configuración del cliente solo contiene la ruta |
| alreal | La clave directamente. Más sencillo, pero copia el secreto en tu configuración de M |
| no | Historial de solicitudes en NDJSON |
Ninguna credencial se lee nunca de un archivo del repositorio, y el registro está en .gitignore.
O con la CLI de Claude Code:
claude mcp add job-search --scope user \
--env SPONSOR_REGISTER_PATH=/path/to/data/register.csv \
--env REED_API_KEY_FILE=/path/to/.reed-api-key \
-- node /path/to/job-search-mcp/dist/index.jsnpm testHay 54 pruebas. Cada fixture es una oferta real o de entrada real del registro que venció a una versión anterior de este código. Las pruebas de Reed mockean fetch, de modo que la suite se ejecuta sin conexión y no cuesta a cuota de API.
Dos errores que la suite detectó mientras se escribía:
£40,000-85,000 se interpretaba como una cantidad única de £40,000, porque la segunda cifra omitía el símbolo de divisa ..... Frente a un umbral de salario, esa es la diferencia entre «lo supera» y «no lo supera».
Un filtro de agencias escrito como \brecruit\b nunca coincidió con Recruitment ni con Consultancy. Unas cincuenta agencias pasaron directamente.
core() destruye la información deliberadamente. Quitar descriptores es lo que hace que la relación entre la marca y el nombre legal funcione, y es exactamente lo que causa falsos positivos. El grado de confianza dosentable ese equilibrio en lugar de ocultarlo.
La ausencia no es un no. none incluye una advertencia en ese sentido. El error más costoso en este ámbito es concluir que un empleador sin listar no puede patrocinar.
Solo de lectura. El servidor lee el libro de solicitudes; nunca escribe en él. Registrar un resultado es una decisión que una persona debe tomar.
MIT
Read the local application ledger. Use it before applying to avoid duplicate submissions to the same employer, and to see what has already been tried. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| company | No | Filter to one employer; omit for the full history |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and aptly declares 'Read-only', telling the agent this is a safe, non-mutating operation. It also notes the data is a 'local' ledger. It doesn't specify edge cases (e.g., empty history) or return format, but for a simple read this is solid disclosure.
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?
Two tight sentences, front-loaded with the core purpose, then usage guidance and a behavioral flag. Every sentence earns its place with zero filler.
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?
Complete for a low-complexity tool (one optional param, no output schema). It covers purpose, use case, and read-only behavior. The only gap is that the return contents aren't described, but for this simple ledger-read it's mostly sufficient.
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 description coverage is 100%, so the single optional parameter is already fully documented ('Filter to one employer; omit for the full history'). The description adds no parameter-level detail beyond this, which lands at the baseline 3.
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?
States a specific verb and resource ('Read the local application ledger') that clearly distinguishes it from siblings like search_roles (searching postings) and check_sponsor (visa status). The purpose is immediately actionable and unambiguous.
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?
Explicitly says when to use it ('Use it before applying to avoid duplicate submissions to the same employer, and to see what has already been tried'). It gives clear context, though it doesn't name sibling tools as explicit when-not-to-use alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up whether a company holds a UK Skilled Worker sponsor licence. Returns a confidence grade, because company names collide: a match on a generic word like 'global' or 'minerva' is not evidence. A result of 'none' does NOT mean the employer cannot sponsor; it means they are not listed under that name, and the registered legal entity should be checked instead.
| Name | Required | Description | Default |
|---|---|---|---|
| company | Yes | Employer name as it appears on the job posting | |
| skilledWorkerOnly | No | Restrict to the Skilled Worker route (default true) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that results include a confidence grade, that generic-word matches are unreliable, and that a 'none' result does not rule out sponsorship and should prompt checking the registered legal entity. This is substantial behavioral context beyond a basic lookup, though it does not cover aspects like rate limits or authentication.
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 three sentences and immediately states the action, then adds caveats about confidence and interpretation. Every sentence adds value, and the most important information (the lookup) comes first. No 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 tool with no output schema and no annotations, the description covers the essential aspects: what it checks, what result to expect (confidence grade), and how to interpret negative results. It does not specify the exact response format, but the description gives enough for an agent to decide whether to call the tool and how to interpret its output. Some detail on the confidence grade scale might be missing, but overall it is quite complete.
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 description coverage is 100%, so both parameters (company and skilledWorkerOnly) are already documented in the schema. The description adds no additional parameter-level detail; it only implies that company names may collide but does not clarify formatting or validation beyond what the schema states.
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 states a specific action: 'Look up whether a company holds a UK Skilled Worker sponsor licence.' It names the resource (company) and the licence type, and the wording clearly distinguishes it from the unrelated siblings like screen_posting or application_history.
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 does not explicitly specify when to use this tool versus alternatives, nor does it state exclusions. The purpose implies the use case (checking sponsorship), but there is no direct guidance on when not to use it or what to use instead. However, the description does provide interpretive guidance for results, which indirectly helps the agent decide next steps.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Screen a posting for hard eligibility bars (citizenship, residency, existing security clearance, explicit refusal to sponsor), for seniority the body implies but the title hides, and for salary and stack. Run this before investing effort in an application.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Job title | |
| description | Yes | Full posting text: description plus requirements |
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 does disclose what the tool evaluates (the explicit criteria list), which is genuinely useful context. But it never states whether the call is read-only, what it returns, or any side effects — for an analysis tool with zero annotation coverage these gaps are felt.
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 a tight two sentences with no filler and front-loads the core purpose and criteria. The usage directive is placed at the end, which is acceptable given the value of the criteria list, though it could arguably lead with the 'run before applying' guidance for maximum salience.
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 two-parameter analysis tool with no output schema, the inputs are fully covered and the screening categories are spelled out. However, the description does not indicate what the result conveys — whether it returns a verdict, a risk score, or flagged bars — leaving an agent unsure what to expect from the call.
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 description coverage is 100%, so the schema already documents both title and description fully; this earns the baseline 3. The description adds marginal semantic value by signaling why the parameters matter (the analysis centers on the posting text), but does not add syntax or format detail beyond what the schema provides.
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?
States a specific verb ('Screen') and resource ('a posting') with enumerated screening dimensions: hard eligibility bars (citizenship, residency, clearance, refusal to sponsor), hidden seniority, salary, and stack. This precise scope clearly differentiates it from siblings like check_sponsor, which covers only the sponsorship angle.
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?
'Run this before investing effort in an application' gives explicit timing and tells the agent to call it early in the workflow. However, it does not name alternatives or state exclusions — e.g., it never routes sponsorship-only cases to check_sponsor — so the guidance stops short of full alternative differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search live UK job listings via Reed, excluding recruitment agencies and job boards, which cannot sponsor roles they merely advertise. Returns a funnel showing what each filter removed, so a small result set can be explained rather than mistaken for an error. Requires REED_API_KEY.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum listings to return (default 25) | |
| keywords | Yes | Search terms, e.g. "react developer" | |
| location | No | UK town or city; omit for nationwide | |
| maxAgeDays | No | Maximum posting age in days (default 30) | |
| minSalaryGBP | No | Drop roles whose published band tops out below this. Unpublished salaries are kept. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It does: it states the auth requirement (REED_API_KEY), explains the funnel output (showing what each filter removed so a small result set is understandable), and notes the exclusion logic. These go beyond the schema and help the agent anticipate how the tool behaves. It lacks details on error handling or rate limits, but core behaviors are covered.
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 sentence states the core purpose and exclusions; the second explains the funnel and the auth requirement. No wasted words. The information is front-loaded: an agent gets the gist immediately, then the important behavioral details. This is exemplary conciseness.
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 there is no output schema, the description explains the return format (a funnel) and the API key requirement. The parameters are fully documented elsewhere. The only minor gap is the precise structure of the funnel output, but that is not essential for calling the tool correctly. The description covers the key operational aspects an agent needs.
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 five parameters are fully described in the input schema (coverage 100%), so the baseline is 3. The description does not add parameter-specific guidance beyond what the schema provides; it mentions the funnel generally but doesn't tie specific parameters to outcomes. Since the schema already handles semantics, there is no deficit requiring compensation.
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-resource pair ('Search live UK job listings via Reed') and adds a key scoping detail: exclusions of recruitment agencies and job boards, with the reason they cannot sponsor. This distinguishes it from sibling tools (check_sponsor, screen_posting, application_history) whose purposes are plainly different. An agent can tell exactly what this tool does and for whom.
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 gives context: it searches live UK roles on Reed and excludes entities that can't sponsor, implying it is used to find roles that can sponsor visas. It also explains the funnel output, which helps an agent interpret results. However, it doesn't explicitly state when to prefer this over siblings or when not to use it, though the tool names make alternatives obvious. The use case is well implied, if not formally stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0application_historycheck_sponsorscreen_postingsearch_rolesScored across 4 tools
Each tool addresses a clearly distinct aspect: sponsor verification, posting screening, application history, and job searching. No overlap in purpose and each has a specific trigger condition.
Three tools follow a verb_noun pattern (check_sponsor, screen_posting, search_roles), but application_history deviates as noun_noun. The naming is still descriptive and predictable, with only minor inconsistency.
Four tools is well-scoped for a focused job-search assistant, covering the core workflow without bloat. Each tool contributes a distinct function and none seem redundant.
The surface covers search, screening, sponsor checks, and local history, which addresses the primary workflow. A minor gap is the lack of a tool to update or add to the application ledger, but this may be handled externally.
Job search, application materials, and application tracking for AI assistants.
Job platform for AI agents. Track tech jobs from companies that match your stack.
Analyze job listings against your resume, track applications, and generate cover letters.
AI job search MCP — fact-checked jobs, application tracker, alerts. ChatGPT, Claude, Cursor.
