
Cerulean MCP server
Which MCP servers are Cerulean's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-20
- Registry namecom.ceruleanjobs/searchverified in the MCP registry
The registry name sits under ceruleanjobs.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools3
- Server calls itselfcerulean-jobs
- Server version3.0.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 117 ms.
- Whether its tools do the product's job has not been judged yet.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score100 of 100answers 100 · definitions 100 · context 100 · connects 100
- Answered100% of days16 of 16 daily checks
- Median first answer146 ms
- Space in an agent's context≈ 2,026 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results3 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · search open luxury job listings by brand and location
- not sure · compare current roles across luxury houses and cities
- not sure · find boutique, client advisor and management positions
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
fetchUse this when someone asks about one specific Cerulean listing — its responsibilities, qualifications, skills, experience, education, pay when the employer states it, benefits or required languages — and its id or Cerulean URL is known…
find_similar_jobsUse this when someone wants more roles like one specific Cerulean listing: the closest open roles by what the job is and where it is. Takes that listing's id, not keywords. If the listing is unknown or has no similarity data, it returns…
searchUse this when someone wants to find, browse, count or compare open roles at luxury houses and brands, the newest openings included. The listings are read from the houses' own career sites every four hours, and closed roles drop out. query…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"search": {
"type": "http",
"url": "https://ceruleanjobs.com/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http ceruleanjobs https://ceruleanjobs.com/api/mcpclaude.ai, ChatGPT and other clients: add https://ceruleanjobs.com/api/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.