Skip to content
Back to search

ruyuejian-jobs-mcp

Search China tech jobs from companies' official career pages, directly inside Claude, Cursor, or another MCP client. Every result preserves its official source URL when available, source publication…

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 21 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/aaron20032/ruyuejian-jobs-mcp with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/aaron20032/ruyuejian-jobs-mcp'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/aaron20032--ruyuejian-jobs-mcp/badge.svg)](/listings/aaron20032--ruyuejian-jobs-mcp)

HTML

<a href="/listings/aaron20032--ruyuejian-jobs-mcp"><img src="/api/listings/aaron20032--ruyuejian-jobs-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 141 lines
  1. # Ruyuejian Jobs MCP
  2. Search China tech jobs from companies' **official career pages**, directly inside Claude, Cursor, or another MCP client. Every result preserves its official source URL when available, source publication time, and first-seen time.
  3. **Data is collected from public official career pages and refreshed daily, not in real time.** Delisted jobs are removed by source-reachability checks and the existing delisting pipeline. No API key is required; the server is read-only.
  4. ## 30-second example
  5. User: `帮我找北京最近三天发布的 AI 产品经理岗位,给出官网链接。`
  6. The client should call:
  7. ```json
  8. {
  9. "query": "AI 产品经理",
  10. "city": "北京",
  11. "postedWithinDays": 3,
  12. "limit": 20,
  13. "offset": 0
  14. }
  15. ```
  16. The response contains active matching jobs with `source.officialUrl`, `source.publishedAt`, and `source.firstSeenAt`. If `dateFilter.coverage` is `partial`, the agent must say the scan was incomplete rather than claiming these are all matching jobs.
  17. ## Clients
  18. ### Claude Desktop / Cursor / generic `mcpServers`
  19. ```json
  20. {
  21. "mcpServers": {
  22. "ruyuejian-jobs": {
  23. "command": "npx",
  24. "args": ["-y", "ruyuejian-jobs-mcp"]
  25. }
  26. }
  27. }
  28. ```
  29. ### Claude Code
  30. ```bash
  31. claude mcp add ruyuejian-jobs -- npx -y ruyuejian-jobs-mcp
  32. ```
  33. Node.js 20 or newer is required. For a local checkout, build with `npm run build`, then use `node /absolute/path/to/mcp/dist/index.js` as the command instead.
  34. ## Tools
  35. | Tool | Purpose | Important inputs |
  36. | --- | --- | --- |
  37. | `search_jobs` | Search active postings with provenance | `query`, `city`, `company`, `recruitmentType`, `limit`, `offset`, `postedWithinDays` |
  38. | `get_job_detail` | Read one active posting by UUID | `id` |
  39. | `list_companies` | List companies and active-job counts | `query`, `city`, `recruitmentType`, `limit` |
  40. | `get_campus_timeline` | Read campus phases, dates, source links and confidence | none |
  41. Use short title keywords such as `AI 产品经理`, not a full natural-language sentence. City values are normal names such as `北京`, not URL slugs.
  42. ## Data contract v1
  43. The durable contract is the versioned JSON returned by the tools; MCP is only its transport. Every response has:
  44. - `contractVersion`: currently `1.0.0`.
  45. - `status`: `ok`, `no_results`, or `error`.
  46. - `data`: tool-specific structured data, or `null` on failure.
  47. - `meta`: retrieval time, `company_official_career_pages`, and `daily` refresh semantics.
  48. - `reason`: structured empty-result semantics when applicable.
  49. - `error`: stable code, message, and retryability on failure.
  50. - `agentInstructions`: constraints the consuming agent must preserve in its answer.
  51. ### Provenance and time
  52. - `source.officialUrl` is an HTTP(S) official-career-page link, or `null`. Agents must never invent a replacement URL.
  53. - `source.publishedAt` is the publication time supplied by the official source, or `null`.
  54. - `source.firstSeenAt` is when Ruyuejian first observed the job; it is not represented as the official publication time.
  55. - `urlDowngradedToListing=true` means the source leads to an official listing page rather than a reliable job-detail page.
  56. - Detail `salaryMin`/`salaryMax` follow the website's monthly-K convention: values at least 1000 are divided by 1000 for K/month; smaller values are already K/month. Agents must not silently convert them to annual salary.
  57. ### Empty results and anti-fabrication
  58. `no_results` is a successful, authoritative tool outcome—not an invitation to fill gaps from model memory. Stable reason codes include `NO_MATCHING_JOBS`, `NO_JOBS_IN_DATE_RANGE`, `JOB_NOT_FOUND_OR_DELISTED`, `NO_MATCHING_COMPANIES`, and `NO_CAMPUS_TIMELINE_DATA`.
  59. ### Date-window completeness
  60. The existing public API has no server-side relative-date filter. `postedWithinDays` therefore uses a rolling `N * 24h` window and scans at most 100 upstream records, newest first:
  61. - `complete`: the scan reached all candidates or records older than the window.
  62. - `partial`: more recent candidates may exist beyond the scanned set. `matchedInScannedSet` is not a global total.
  63. - Records with no usable date are excluded and counted as `excludedUnknownDate`.
  64. - Date-filtered searches do not support offset pagination; the input schema rejects that combination.
  65. ### Errors and local budgets
  66. Upstream timeout, HTTP 429/5xx, invalid responses, and local rate limiting return `status=error` with no fabricated fallback data. The package limits itself to 30 upstream requests per rolling minute, 50 jobs per normal page, 100 records per date scan, and a 10-second upstream timeout.
  67. `RUYUEJIAN_API_BASE_URL` can point to another HTTP(S) API base for development. It defaults to `https://ruyuejian.com/api`.
  68. ## Measurement and live eval
  69. Set `RUYUEJIAN_MCP_TELEMETRY=1` to emit one structured JSON event per tool call to stderr. Events contain tool name, status, reason/error code, result counts, date coverage and duration; they deliberately exclude raw queries, job IDs, descriptions and source URLs. This is local, opt-in telemetry—nothing is transmitted to Ruyuejian by the package.
  70. Run `npm run eval:live` after each schema or mapping change. It performs read-only production calls through a real MCP client and asserts search, detail, companies, recent-date coverage and campus-timeline contracts.
  71. ## Development
  72. ```bash
  73. npm install
  74. npm run build
  75. npm test
  76. ```
  77. The eval suite covers source citation, recent-date filtering, partial coverage, empty results, delisting, upstream failures, invalid parameters, and real MCP client/server calls over an in-memory transport.
  78. Maintainers: see [PUBLISHING.md](./PUBLISHING.md) for npm, Official Registry, directory submission, production rollout and community-post steps.
  79. ## 中文说明
  80. 如约见岗位数据全部来自公司官方招聘页,由 Scrapy + Playwright 采集,并非第三方岗位聚合。每条结果尽可能保留官网原始链接、官网发布时间与首次收录时间;数据按日刷新,**不得宣称实时**。空结果、部分日期覆盖和上游故障都有独立机器可读状态,Agent 不得编造岗位、日期或链接。
  81. **国内访问**:本仓库的权威源是 GitHub(`github.com/aaron20032/ruyuejian-jobs-mcp`)。若访问 GitHub 较慢,可用只读镜像 `gitee.com/mindisland_1_0/ruyuejian-jobs-mcp` 浏览与克隆代码;镜像由 GitHub 单向同步,**Issue、PR 与代码提交请一律提到 GitHub**,在镜像仓的提交会被同步覆盖。
  82. **快速接入**:需要 Node.js 20 或更高版本。把下面的配置加进客户端的 `mcpServers`,重启客户端后即可让 AI 调用如约见岗位工具:
  83. ```json
  84. {
  85. "mcpServers": {
  86. "ruyuejian-jobs": {
  87. "command": "npx",
  88. "args": ["-y", "ruyuejian-jobs-mcp"]
  89. }
  90. }
  91. }
  92. ```
  93. Claude Code 用户执行:
  94. ```bash
  95. claude mcp add ruyuejian-jobs -- npx -y ruyuejian-jobs-mcp
  96. ```
  97. 国内网络若访问 npm 官方源较慢,可先执行 `npm config set registry https://registry.npmmirror.com`(该包已在 npmmirror 同步)。

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.