Refine Job Search

co.getrefine由 getrefine.co 发布官方发布者v0.6.0更新于 Oct 24, 2026

Job search management: applications, interviews, offers, recruiter email, and company openings.

已验证Streamable HTTP可网页运行效率与工作流网页搜索与抓取沟通与协作

概览

AI 生成的概览

让助手管理求职流程:跟踪申请、面试和录用通知,关注公司,搜索职位,并读取匹配的招聘邮件。

可以做什么
Refine Job Search 为助手提供管理求职看板的工具:列出、添加、更新、归档或删除职位,标记为已申请,并记录面试、带薪酬信息的录用通知以及谈判事件。它可以搜索已索引的职位和公司,关注公司以获取新的匹配职位,读取关注动态和邮件摘要计划,并通过招聘页面网址提交缺失的公司。它还能读取与申请、面试和招聘方联系相匹配的邮件会话收件箱。
适用场景
当你希望助手端到端地整理求职过程时使用:跟踪申请和面试阶段、记录并比较录用通知、关注公司的新职位,或查看与某个申请相关的招聘邮件。
运行要求
通过 streamable HTTP 连接的远程 MCP 端点 mcp.getrefine.co;未声明任何软件包、环境变量或请求头。部分功能(如关注邮件摘要计划)需要 Plus 或 Student 套餐。
安装前请注意
许多工具会修改或删除数据:删除职位、面试和录用通知不可撤销,接受或拒绝录用通知是重大状态变更;工具说明要求先征得用户确认。取消关注公司和将全部职位标为已读也会改变存储状态。提交公司会将其加入共享索引。录用通知相关操作不会向雇主发送邮件。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Refine Job Search,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/co.getrefine%2Frefine/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "refine-job-search": {
      "type": "http",
      "url": "https://mcp.getrefine.co/mcp"
    }
  }
}

工具

62

jobs.list

List jobs

List jobs in your journey

输入参数pagelimit

jobs.get

Job details

Get details of a specific job

输入参数job_id必填

jobs.add

Add job

Add a new job to your journey

输入参数urltitle必填sourcecompany必填locationdescriptionqualificationscompensation_text

jobs.update

Update job

Update a job in your journey

输入参数urlnotestitlejob_id必填sourcecompanylocationdescriptionqualificationscompensation_text

jobs.delete

Delete job

Permanently delete a job and its application from the board. Confirm with the user first; it cannot be undone. To hide a job without recording a rejection or closure, use jobs.archive instead.

输入参数job_id必填confirmed必填

jobs.refresh

Re-scrape job

Queue a job posting to be re-scraped. The returned job may remain pending; use jobs.get later to inspect the refreshed state.

输入参数job_id必填

jobs.mark_applied

Mark applied

Mark a job as applied

输入参数job_id必填

jobs.archive

Archive job

Hide a job from the active board without recording a rejection or closing the application

输入参数job_id必填

jobs.unarchive

Unarchive job

Restore an archived job to the active board

输入参数job_id必填

jobs.interviews.add

Log interview

Log an interview for a job

输入参数name必填notesjob_id必填locationscheduled_at

jobs.interviews.update

Update interview

Update an existing interview

输入参数namenotesjob_id必填ratingoutcomefeedbacklocationnext_actioncancelled_atcompleted_atinterview_id必填interviewers另有 2 个

jobs.interviews.delete

Delete interview

Permanently delete an interview from a job. Confirm with the user first; it cannot be undone.

输入参数job_id必填confirmed必填interview_id必填

jobs.offer.create

Record offer

Record a job offer with compensation details

输入参数notesjob_id必填currencyrsu_textbonus_centsdeadline_atequity_textnext_actiontarget_rsu_textinitial_rsu_textbase_salary_centstarget_bonus_cents另有 5 个

jobs.offer.update

Update offer

Update the offer recorded for a job

输入参数notesjob_id必填currencyrsu_textbonus_centsdeadline_atequity_textnext_actiontarget_rsu_textinitial_rsu_textbase_salary_centstarget_bonus_cents另有 5 个

jobs.offer.delete

Delete offer

Permanently delete the offer recorded for a job (the job stays). Use only to fix a mistake, and confirm with the user first; it cannot be undone.

输入参数job_id必填confirmed必填

jobs.offer.accept

Accept offer

Accept the offer for a job. This is a major state change that closes out the search for this role; confirm with the user before calling. It does not email the employer.

输入参数job_id必填confirmed必填

jobs.offer.decline

Decline offer

Decline the offer for a job, a major state change; confirm with the user first. It does not email the employer.

输入参数job_id必填confirmed必填

jobs.offer.add_negotiation

Log negotiation event

Log a negotiation event on an offer (counter-offer, update, etc.)

输入参数notesjob_id必填event_dateevent_type必填bonus_centsequity_textsalary_cents

jobs.offer.delete_negotiation

Delete negotiation event

Remove a negotiation event from an offer

输入参数job_id必填event_id必填confirmed必填

following.list

Followed companies

List all followed companies, their filters, state, and unread counts. Returns the full list without pagination. Following delivers future matching openings; use Search to browse jobs already in the index.

无需输入参数。

following.follow

Follow company

Follow an indexed company for future matching openings and company recommendations. Get company_id from Search, a ready submission, or a recommendation candidate_company.id. Specify at least one match; [{}] follows all new openings. This does not submit an unknown careers page or collect historical matches.

输入参数filters必填company_id必填

following.update

Update follow filters

Replace all match filters for a followed company. Other follow settings are unchanged. Pass [{}] for all new openings. Pending means the new filters are being applied; old unread counts may change.

输入参数filters必填follow_id必填

following.unfollow

Unfollow company

Unfollow a company and remove its Following feed and recommendation source. Confirm with the user first. Board jobs remain. To pause temporarily instead, use following.pause.

输入参数confirmed必填follow_id必填

following.pause

Pause follow

Pause future matching openings for this follow without deleting it. This does not stop shared company indexing or pause other follows.

输入参数follow_id必填

following.resume

Resume follow

Resume a paused company follow.

输入参数follow_id必填

following.openings.list

Following openings

Read matching openings from followed companies. tab defaults to unread. Use the row id for marking read and nested opening.id for opening details or adding to the board. meta.unread_count/read_count cover the selected follow or all companies before view filters; meta.filtered_count covers the current filtered tab.

输入参数qtabpagelimitlocationfollow_iddepartment

following.openings.mark_read

Mark opening read

Mark one Following row as read. Use the row id from following.openings.list, not nested opening.id.

输入参数follow_opening_id必填

following.openings.mark_all_read

Mark all openings read

Mark all unread openings as read for one follow, or every followed company if follow_id is omitted. Includes every page and openings hidden by view filters. Confirm the scope with the user first. The API returns no affected count; do not invent one.

输入参数confirmed必填follow_id

following.digest.get

Following email schedule

Read the user-wide Following email digest schedule. data is null if no schedule is configured. Company match filters are managed separately with following.update.

无需输入参数。

following.digest.update

Update Following email schedule

Set the user-wide Following email digest schedule after the user requests it. Requires Plus or Student. For a new schedule supply frequency, hour (0–23), timezone (IANA), and weekday (Sunday=0) when weekly. Existing schedules can be patched.

输入参数hourweekdaytimezonefrequency

companies.submissions.create

Submit company

Submit a missing company using its public HTTPS careers URL, supplied or confirmed by the user. Refine detects supported sources and processes openings asynchronously. This adds to the shared index, not to Following. Use companies.submissions.get for progress; follow separately once company.id is available.

输入参数careers_url必填company_name必填

companies.submissions.get

Company submission status

Read company submission progress. queued/detecting/processing means wait; ready means search again using the company name. unsupported means the careers source is not supported; failed means processing failed. Do not claim the company was added or invent jobs while it is still working.

输入参数submission_id必填

openings.get

Opening details

Read an indexed opening, including its full description and qualifications. Use opening.id from Search or Following, not a follow-opening row ID.

输入参数opening_id必填

openings.add_to_board

Add opening to board

Add an indexed opening to the board after the user chooses it. Uses opening.id, not the Following row ID. Returns the existing board job if already added. This does not apply to the employer or send email; it also marks any matching Following item as read.

输入参数opening_id必填

search.create

Create search

Search indexed jobs or companies. Supply input OR query, not both. Natural-language searches return a search ID and processing state: use search.get later, without rapid polling. Keep the ID to paginate or update this same search. Empty query {} is All openings, currently sorted by newest without persona personalization.

输入参数pagesortviewinputquery

search.get

Search results

Read a search and its results, switch jobs/companies view, or fetch results.next_page. Pending/interpreting/processing means it is still working: do not create another search or poll rapidly. If missing_company_name is set, ask for its careers URL and use companies.submissions.create. Company rows contain samples, not all matching jobs.

输入参数pagesortviewsearch_id必填

search.update

Update search

Update the existing search instead of creating another. Supply input OR the complete replacement query; omitted filters are cleared. Wait until the current search is ready or failed before updating it.

输入参数pagesortviewinputquerysearch_id必填

search.company_openings

Company search openings

Read all matching jobs for a company in a ready search, not just its three preview jobs. Continue with data.next_page until null. Use company.id from the search results.

输入参数pagesortsearch_id必填company_id必填

inbox.list

List inbox

List email conversations Refine matched to your job search (applications, interviews, recruiter outreach)

输入参数tabpagelimitshelfstatusunreadaccount

inbox.get

Inbox item

Get one inbox item with its related job and application

输入参数item_id必填

inbox.get_thread

Email thread

Fetch the full email thread for an inbox item

输入参数item_id必填

inbox.draft_reply

Draft reply

Generate an AI reply draft for an inbox item. Returns HTML for review; it does not send anything.

输入参数kind必填item_id必填

inbox.send_reply

Send reply

Send an email reply through the user's Gmail. This emails a real person from the user's address. Only call after the user has seen the exact message body and explicitly approved sending it.

输入参数body必填item_id必填confirmed必填draft_kind

inbox.apply_suggestion

Apply inbox suggestion

Apply an inbox item's suggested action, such as adding an application to the board or recording a rejection. Confirm the specific action with the user first.

输入参数item_id必填confirmed必填

inbox.undo

Undo inbox action

Undo an auto-applied inbox action. This can delete a board record that the automatic action created, so confirm with the user first.

输入参数item_id必填confirmed必填

inbox.mark_read

Mark read

Clear an inbox item's unread-reply flag

输入参数item_id必填

inbox.unsubscribe

Unsubscribe sender

Unsubscribe the user from this sender's mailing list via one-click list-unsubscribe. This changes the user's real email subscriptions; confirm with them before calling. Use it for unwanted bulk senders, not for a person you can simply decline.

输入参数item_id必填confirmed必填

inbox.dismiss

Dismiss inbox items

Dismiss inbox items you are not acting on (also marks the mail read in Gmail)

输入参数ids必填confirmed必填

inbox.acknowledge

Acknowledge inbox items

Keep auto-applied inbox items as-is and finalize the automatic action. Confirm the specific items with the user first.

输入参数ids必填confirmed必填

inbox.decline

Decline conversations

Queue decline replies to recruiter outreach. Depending on the user's preference this SENDS email from their address. Only call after the user explicitly approved declining these specific conversations.

输入参数ids必填rememberconfirmed必填preference

inbox.refresh

Refresh inbox

Check Gmail for new mail now; returns per-account sync status

无需输入参数。

inbox.sync_status

Inbox sync status

Per-account Gmail synchronization status, including current progress and last sync time

无需输入参数。

persona.get

Get persona

Get the user's persona: inferred job-search preferences and traits with an understanding score. Use it to tailor advice and searches.

无需输入参数。

recommendations.list

List recommendations

Discover companies recommended from the companies you follow. Optionally filter by source_company_id (company.id from following.list, not a follow ID). Returns one flat list plus per-source counts. To follow a recommendation, use following.follow with candidate_company.id and your chosen filters.

输入参数pagelimitsource_company_id

recommendations.get

Recommendation details

Get one recommended company with sources and persona fit

输入参数recommendation_id必填

recommendations.dismiss

Dismiss recommendation

Dismiss a recommended company

输入参数reasonrecommendation_id必填

recommendations.block

Block recommendation

Dismiss a recommended company and block it from future recommendations

输入参数recommendation_id必填

recommendations.restore

Restore recommendation

Restore a dismissed or blocked recommendation

输入参数recommendation_id必填

recommendations.feedback

Recommendation feedback

Record recommendation feedback to improve future suggestions. The historical feedback tag "watched" records that a company was followed; it does not create a follow. Use following.follow first. Dismiss/block/restore actions are separate tools.

输入参数feedback_types必填recommendation_id必填interaction_source

account.agenda

Upcoming agenda

Get upcoming interviews and action items

无需输入参数。

integrations.list

Connected accounts

List connected Google accounts and their grant status. To connect a new account, use integrations.connect_google.

无需输入参数。

integrations.connect_google

Connect Gmail

Get a link for the user to connect Gmail to Refine or approve a missing Gmail permission. Refine selects the permission needed for the connected account. The connection happens in the browser with no Refine sign-in required. Share the link only with the owner of this Refine account.

无需输入参数。

版本历史

2
  1. v0.6.0最新Oct 22, 2026
  2. v0.5.2Sep 16, 2026

评分

已满足适用检查项的 83%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分

    请声明包含 README 的 GitHub 仓库,或在 OAuth 受保护资源元数据中提供 resource_documentation。

  • 许可证不适用

    托管服务按其提供方的条款使用,因此这里不要求许可证。此检查项不计入百分比。