
Ranked MCP server
Which servers in the official MCP registry are Ranked's own, 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 namejp.ranked/jobsverified in the MCP registry
The registry name sits under ranked.jp. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools4
- Server calls itselfjp.ranked/jobs
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 350 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 2 of the 7 days it takes to judge reliability.
Once connected
- Parameters are untyped or undescribed in 1 of 4 tools: check arguments before calling.
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 scoreafter a weeka score needs 7 daily checks: 2 so far
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer387 ms
- Space in an agent's context≈ 858 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsA · 96 of 100
- Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 1 of 4
What an agent can do with it
- not sure · Score Tokyo job listings against your resume
- not sure · Filter for visa-sponsoring backend roles in Tokyo
- not sure · Browse Tokyo listings by category and employer
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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 →
search_jobsSearch live job openings in Tokyo, Japan, listed on Ranked (ranked.jp). Built for foreign professionals: filter by whether English is enough, whether Japanese is required, visa sponsorship, remote work and minimum annual salary in yen…
get_jobFull details of one Ranked job by id: the complete description, salary, Japanese/English requirements, visa sponsorship, Ranked page URL for details and applying, and source freshness.
search_companiesSearch companies hiring in Tokyo on Ranked, by keywords over name, industry and description.
get_companyOne company's profile on Ranked and its open Tokyo jobs.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"jobs": {
"type": "http",
"url": "https://jobs.ranked.jp/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http ranked https://jobs.ranked.jp/mcpclaude.ai, ChatGPT and other clients: add https://jobs.ranked.jp/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.
Cookies
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.