Job Boards MCP Server: 35 job sites, 50+ countries, one search_jobs tool

Search jobs

search_jobs

Search live job postings from 34 public job boards in one call: France Travail, Free-Work, HelloWork (France), Arbeitsagentur (Germany), Reed (UK), Infoempleo (Spain), EURES (all EU and EEA countries), Computrabajo, Bumeran, Gupy (Latin America), Job Bank (Canada), Dice, Built In (US), MyCareersFuture (Singapore), and RemoteOK, Remotive, We Work Remotely for remote jobs. Give a country code (FR, DE, ES, GB, IT, NL, MX, AR, BR, US, CA, SG...) or "REMOTE", plus keywords. Returns title, company, location, remote mode, salary when published, date posted, skills and the posting URL, deduplicated across boards. Costs $0.002 per job returned, nothing more for a search with no result (plus a $0.005 start fee per session; a session lasts up to 100 seconds). Call list_job_sources to see which boards cover a country.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "country": "<country>"
    },
    "name": "search_jobs"
  }
}

Input Schema

Name	Required	Description
`remote`	No	Work mode filter; "any" by default.
`country`	Yes	ISO 3166-1 alpha-2 country code (AR, AT, BE, BG, BO, BR, CA, CH, CL, CO, CR, CY, CZ, DE, DK, DO, EC, EE, ES, FI, FR, GB, GR, GT, HN, HR, HU, IE, IS, IT, LI, LT, LU, LV, MT, MX, NI, NL, NO, PA, PE, PL, PR, PT, PY, RO, SE, SG, SI, SK, SV, US, UY, VE) or "REMOTE" for remote jobs worldwide.
`sources`	No	Limit the search to these boards (names from list_job_sources). By default every default board of the country runs.
`keywords`	No	Job title, skill or company, for example "data engineer" or "nurse". Leave empty for the latest postings.
`location`	No	City or region inside the country, for example "Lyon" or "Berlin". Matched by each board its own way.
`maxResults`	No	How many jobs to return, 20 by default, at most 50. Each returned job is charged.
`includeDescriptions`	No	Add each posting's description, cut to 1,500 characters. Slower on some boards.
`publishedWithinDays`	No	Only jobs published in the last N days.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 10, 2026

changedInput schema / properties / sources / items / enum

Previous value: -[
-  "free-work",
-  "francetravail",
-  "hellowork",
-  "meteojob",
-  "emploi-territorial",
-  "choisirleservicepublic",
-  "qapa",
-  "arbeitsagentur",
-  "stellenanzeigen",
-  "jobware",
-  "reed",
-  "infoempleo",
-  "trabajos",
-  "ticjob",
-  "empleate",
-  "arbetsformedlingen",
-  "jobsch",
-  "pracuj",
-  "eures",
-  "navent",
-  "computrabajo",
-  "getonbrd",
-  "gupy",
-  "jobbank",
-  "themuse",
-  "builtin",
-  "dice",
-  "mycareersfuture",
-  "remoteok",
-  "remotive",
-  "weworkremotely",
-  "workingnomads",
-  "jobicy",
-  "hackernews",
-  "wellfound"
-]New value: +[
+  "free-work",
+  "francetravail",
+  "hellowork",
+  "meteojob",
+  "emploi-territorial",
+  "choisirleservicepublic",
+  "qapa",
+  "arbeitsagentur",
+  "stellenanzeigen",
+  "jobware",
+  "reed",
+  "infoempleo",
+  "trabajos",
+  "ticjob",
+  "empleate",
+  "arbetsformedlingen",
+  "jobsch",
+  "pracuj",
+  "eures",
+  "navent",
+  "computrabajo",
+  "getonbrd",
+  "gupy",
+  "jobbank",
+  "builtin",
+  "dice",
+  "mycareersfuture",
+  "remoteok",
+  "remotive",
+  "weworkremotely",
+  "workingnomads",
+  "jobicy",
+  "hackernews",
+  "wellfound"
+]

First observedNov 9, 2026

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations present, the description carries the burden and does so well: it discloses the pricing model ($0.002 per returned job, nothing for an empty result), the $0.005 per-session fee with a 100-second session window, deduplication across boards, and that includeDescriptions is slower on some boards. It omits authentication, rate limiting, and failure modes, which keeps it below a 5.

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?

Purpose and cost are front-loaded and the sentences are dense rather than rambling. The first sentence's long enumeration of ~20 board names is the weakest part – it consumes space to convey what could be summarized as coverage breadth, though it does communicate scope.

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 an eight-parameter search tool with no annotations and no output schema, the description covers the essentials: required country input, return fields (title, company, location, remote mode, salary, date, skills, URL), deduplication, and billing. Only error behavior and the effect of sources defaults on cost are left unstated.

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 100%, so all eight parameters are already documented in the schema, including country enum values, remote mode, and maxResults bounds. The description only restates country/keywords semantics and adds the cost coupling of maxResults ('Each returned job is charged'), which is marginal added meaning over the schema.

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?

States a specific verb and resource ('Search live job postings') and immediately scopes it: 34 public boards aggregated in one call, with the named sources and regions. This is clearly distinguishable from the sibling list_job_sources, which only enumerates boards.

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?

Gives concrete invocation guidance ('Give a country code (FR, DE...) or "REMOTE", plus keywords') and routes the agent to list_job_sources to discover which boards cover a country. It stops short of explicit when-not-to-use conditions or guidance on choosing between keyword-driven and browse-the-latest searches.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Job Boards MCP Server: 35 job sites, 50+ countries, one search_jobs tool tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.