tw-jobs-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TW_JOBS_HOST | No | Bind address for the HTTP transports | 127.0.0.1 |
| TW_JOBS_PORT | No | Bind port for the HTTP transports | 8000 |
| TW_JOBS_BOARDS | No | Extra career boards, comma separated, e.g. `g:gitlab,l:kraken,-g:stripe` (`g:` Greenhouse, `l:` Lever, a leading `-` removes one). A board without Taiwan roles simply returns nothing. | built-in list |
| TW_JOBS_FORMAT | No | `json` returns every field as compact JSON instead of the text tables | text |
| TW_JOBS_CACHE_TTL | No | Seconds to keep responses; `0` turns the cache off | 300 |
| TW_JOBS_TRANSPORT | No | Transport for the server: `stdio`, `streamable-http` or `sse` (same as `--transport`) | stdio |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_jobsA | 搜尋職缺，回傳表格（id 給 get_job，company_id 給 get_company）。 keyword 中文（給 104）、keyword_en 英文（給其他來源），互為翻譯；只填一個時兩邊共用。 非 104 來源只支援 keyword、area（yourator 另有 sort=newest，boards 另有 remote_only），其餘條件會在註記說明未套用。 area/jobcat 填中文名稱（台北市、軟體工程師）。salary_min 的單位是 salary_unit，104 預設不含面議，include_negotiable=True 才納入。 my_years＝使用者的年資，列出要求不超過它的（含經驗不拘）。per_page≤30，用 page 翻頁。 |
| get_jobA | 職缺完整內容，full=True 看全文。104 限定：applicants＝近兩週應徵者人數與背景，similar＝相似職缺。 |
| get_companyC | 公司簡介。with_openings=True 附目前職缺；keyword 只列符合的職缺（104 連內文比對）。 |
| salary_overviewA | 薪資行情：取前 pages（1~5）頁有公開薪資的職缺，依單位統計筆數、最低、四分位、中位、最高。 參數同 search_jobs。樣本統計，非全站。 |
| sourcesA | 即時檢查 104、Yourator 與各外商職缺板目前哪些連得上，哪些被擋。 |
| lookup_codeA | 查地區（area）或職類（jobcat）代碼。name 留空則列 parent 的下一層（parent 也空＝最上層）。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each of the six tools has a clearly distinct purpose: job search, job detail, company profile, code lookup, salary aggregation, and source availability. Although salary_overview shares some parameters with search_jobs, its statistical/aggregate role is clearly differentiated. An agent can select tools without meaningful ambiguity.
The tools consistently use snake_case and mostly follow a verb_noun or noun_phrase pattern such as get_company, lookup_code, and search_jobs. Minor deviations are the bare noun 'sources' and noun_phrase 'salary_overview', but the set remains predictable.
Six tools is well scoped for a job-search aggregation server. Each tool covers a distinct part of the workflow: searching, inspecting jobs and companies, decoding filters, summarizing salaries, and checking source availability.
The surface covers the core read-only job-search lifecycle: discovery, detail retrieval, company context, filter code lookup, salary insight, and source health. It lacks application/save/favorite operations and explicit company-level search, but those are reasonable omissions for an aggregation MCP.