timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
freehire.me: search 3.3M+ IT jobs from 294K company boards, track applications, tailor CVs.
教 AI 做这类工作的 Skill,可与本项一起使用
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…
scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place
此项在“连接 AI 的应用”标签中,该标签不使用星标,按以下顺序排列
| 1. 在 Claude 连接器目录中 | 否 | |
|---|---|---|
| 2. 团队实测过 | 否 | |
| 3. 适合泰国用户 | 否 | |
| 4. 不计星标的使用量 | 20/100 | 热度 0 · 新鲜度 12 · 仍在响应 8 · 用户喜欢 +0 |
| 5. 登记日期 | 2026-10-28 |
用户喜欢: 0 · 最多加 5 分(每人 1 分),不能用钱买。
质量: 基础检查通过 6/6 项(仅展示,不用于排序)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 freehire。按照 https://mcp.popnx.com/i/me-freehire-freehire.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 6/6 项检查 · 你的提问会经过开发者的服务器(freehire.me) · ✓ 命令已检查 2026年11月14日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
CustomizeConnectors
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
freehirehttps://freehire.me/api/v1/mcp在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
+Connectorsfreehire
用 freehire 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 freehire,或回答中出现 freehire 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
Plugins+Add custom MCP server
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
freehirehttps://freehire.me/api/v1/mcp开启新聊天,输入前先从插件列表中选择 freehire
用 freehire 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 freehire,或回答中出现 freehire 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --transport http --scope user freehire https://freehire.me/api/v1/mcp应能看到 freehire 在列表中并显示已连接
用 freehire 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 freehire,或回答中出现 freehire 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor · 约 2 分钟
不需要密钥,不用安装程序
用 freehire 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 freehire,或回答中出现 freehire 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 2 分钟
不需要密钥,不用安装程序
用 freehire 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 freehire,或回答中出现 freehire 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看
通过网页连接的应用使用的地址
https://freehire.me/api/v1/mcpJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user freehire https://freehire.me/api/v1/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"freehire": {
"url": "https://freehire.me/api/v1/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"freehire": {
"type": "http",
"url": "https://freehire.me/api/v1/mcp"
}
}
}Claude Code
claude mcp add --scope user freehire -- npx -y freehire-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"freehire": {
"command": "npx",
"args": [
"-y",
"freehire-mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"freehire": {
"command": "npx",
"args": [
"-y",
"freehire-mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"freehire": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"freehire-mcp"
]
}
}
}FREEHIRE_TOKEN 机密 envFREEHIRE_API_URL env说明仍为英文原文。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
工具名称和描述与服务器在 2026年11月19日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
add_cvStore the person's own CV, as text, for an account that has no CV yet. Pass the CV they supplied verbatim — text they pasted, or the content of a CV file they gave you. Never compose, summarise or embellish a CV: it is stored as theirs and its work history is recorded as their ow
answer_bank_deleteDelete one of the person's saved screening answers by the id answer_bank_list shows.
answer_bank_listList the person's saved answers to employers' open-ended screening questions ("Why do you want to work here?", "Desired start date?"). Automatic applications reuse them on every form that asks the same question.
answer_bank_saveSave the person's answer to one screening question an employer's form asks, so automatic applications can send it — use the question's wording from auto_apply_get. The answer is sent to employers in the person's name: pass on what THEY said, never an answer you composed or guesse
apply_jobMark a vacancy as applied to. This records the user's own application; it does not submit anything to the employer.
auto_apply_cancelWithdraw an automatic application that has not been submitted. Refused while it is being submitted. Its history is kept.
auto_apply_getRead where one automatic application stands: its status, the questions it stopped on, the answers still missing before submission, its full history, and what to do next. Call it again to follow progress — history only grows.
auto_apply_listList the person's automatic applications: every live one with its status and when anything last happened to it, and the ones submitted in the last 30 days. Use auto_apply_get for one attempt's questions and history.
auto_apply_retryRestart an automatic application that stopped — on an unanswered question, after repeated errors, or because the CV could not be tailored — or refresh one awaiting review so newly saved answers are reflected. Answer the open questions with answer_bank_save or screening_answers_se
auto_apply_reviewRecord the review of an automatic application whose status is pending_review. "approved" lets freehire submit it to the employer with the tailored CV and the answers auto_apply_get shows; "declined" stops it for good. One decision per attempt.
auto_apply_startStart applying to a vacancy automatically on the person's behalf. freehire tailors their CV to the vacancy, checks the employer's application form against their saved answers, and waits for a review (auto_apply_review) before submitting. Spends one of today's auto-apply allowance
buddy_joinJoin freehire's interview buddy network under a generated anonymous handle, or rejoin under the old one. Members can book and host 60-minute mock interviews with each other. Returns the membership status.
buddy_leaveLeave the interview buddy network. Closes the person's buddy conversations and cancels every upcoming mock interview they host or attend; the other participants are told. Rejoining later restores the same handle.
buddy_mock_bookBook a 60-minute mock interview with a host, the person attending as guest. starts_at must be one of the host's open slots exactly (RFC 3339) and topic one of the topics that host offers. Returns the booked mock with the counterpart's handle and the meeting link. A guest may hold
buddy_mock_cancelCancel one of the person's upcoming mock interviews, by id, before it starts. The other participant is told.
buddy_mock_hostsMembers of the buddy network the person could book a 60-minute mock interview with now, soonest available first: each host's handle, a coarse card (category, seniority, country), the topics they offer, their next open slot and their review rating. Never includes a meeting link.
buddy_mock_listThe person's own mock interviews, upcoming and past, as host or guest: id, role, the counterpart's handle, times, topic, status, the meeting link while confirmed, whether it can still be cancelled, and the reviews.
buddy_mock_schedule_add_overrideAdd one dated override to the person's hosting schedule: on that date they host between start and end (HH:MM) instead of their weekly hours. An equal start and end closes the date. Returns the stored rule with its id.
buddy_mock_schedule_deleteDelete one rule (weekly or dated override) of the person's hosting schedule, by its id.
buddy_mock_schedule_getThe person's own mock-interview hosting setup: settings (time zone, meeting link, topics offered, paused) or null before they were first saved, and the schedule rules — weekly rules by weekday (0 = Sunday) and dated overrides, each with the id needed to delete it.
buddy_mock_schedule_set_weeklyReplace the person's whole recurring weekly hosting schedule with these weekday rules (an empty list clears it). Times are HH:MM in their settings' time zone. Dated overrides are kept and are not accepted here.
buddy_mock_settings_setReplace the person's mock-interview hosting settings as a whole: the time zone their schedule is in, the meeting link guests receive, the topics they offer, and whether hosting is paused. Returns the saved settings.
buddy_mock_slotsThe open 60-minute mock-interview slots of one host, by handle, and the topics that host offers. Each slot's starts_at is the exact RFC 3339 instant to book. Covers the next 30 days unless from/to say otherwise, at most 62 days. Never includes a meeting link.
buddy_statusWhether the person is a member of freehire's interview buddy network, and their anonymous handle there. Members are known to each other only by handle. Membership is needed for every mock-interview action.
check_jobs_openCheck whether postings are still open, by the slugs search results carry — up to 50 per call. Use before acting on a saved shortlist: each posting answers open, closed or not_found, with when it closed or was last seen live.
facetsList the live filter vocabulary. Without `facet`: every filter's name with how many values it has, plus numeric ranges. With `facet`: that filter's values with a vacancy count each, optionally only those containing `contains`. Filter values are the market's own; an invented one m
fetchRead one posting in full by an id search returned: its full text, the employer, the board it came from and whether it still looks live.
get_companyRead what freehire holds about one employer by the slug a result carries: what they do, which industries they are in, where they are based, and how many postings they have open.
get_jobRead one posting in full by the slug a search result carries: the whole description, the stated requirements, which applicant tracking system handles applications, and whether the posting still looks live — when it was last seen open, a reality class, and any observed signs that
get_planRead the signed-in account's plan ("free", "pro" or "ultra") and today's allowance of each metered AI feature: limit, used and remaining, all resetting at resets_at (UTC). paid_until is the end of the current paid period (it may renew; see plan_url). Here the metered feature is "
get_profileRead the user's saved job-search profile: the roles and skills they want, the skills they want to avoid, where and how they will work, and their CV (headline, years, experience, education — contacts are not included). Call this before asking the user what they are looking for; on
get_setup_statusReport what this account still needs to get value from freehire: a CV (and whether reading it has finished), job-search preferences, an active job alert, and — only needed for applications prepared on the person's behalf — a paid plan and the switch letting connected agents apply
job_market_statsHow many open postings match a set of filters, and their most common role families, seniorities, skills, work modes, countries and regions. Takes the same filters as a job search.
list_filter_valuesThe values one job-search filter accepts — skills, categories, seniorities, sources, countries and the rest — each with how many open postings carry it, most common first. A value not listed matches no posting. Use it before filtering on a value you are not sure of.
list_subscriptionsList the person's job alerts with every setting: id, name, a readable filter summary AND the search as the structured object the alert tools take (query, filters, salary_min/max; `other` holds website-only filters an update keeps), whether it is paused, and each delivery channel
list_unread_mailThe person's newest unread application mail in their freehire inbox: the sender's display name and address, subject, received time, the label freehire classified it as (interview_invitation, rejection, offer, …) and, when it is attached to a tracked job, that company and job slug
market_fitScore a skill list against the live open-vacancy market for a filtered role: what share of vacancies list at least one of the skills, which must-have skills are held, and which missing skills unlock the most vacancies. Here `skills` is the MEASURED set, not a filter.
my_jobsList the vacancies the user is tracking — saved, applied, viewed or the whole board — with each one's stage and note.
report_jobFile a report on a vacancy that looks fake, spam, a scam, irrelevant, or that never answers. It goes to freehire's moderators, who review it by hand; it does not hide the job or change the user's own board. Only report when the user asks for it, or after you have told them what y
report_problemReport a freehire operation you could not complete, a missing capability, or unexpected behavior for the team to triage. Give concise summaries of the user's goal, expected result, and actual failure. Include a tool name and error code when known. Do not include conversations, CV
salary_statsSalary percentiles (25th, median, 75th) from open postings that state pay, scoped by role family, seniority and country, with the sample size behind each figure. Currencies and pay periods are reported separately, never converted.
save_jobBookmark a vacancy for the user. Idempotent.
screening_answers_getRead the person's answers to the six screening questions that repeat across application forms: countries they may work in, visa sponsorship, desired salary, notice period, relocation, and being 18 or older — plus privacy_consent, whether they agree to an employer's privacy / pers
screening_answers_setRecord the candidate's own answer to one or more of the six screening questions that repeat across job-application forms: which countries they are authorized to work in, whether they need visa sponsorship, their desired salary, their notice period, whether they are willing to rel
searchSearch freehire's IT job postings by free text. Returns matching postings as {id, title, url}.
search_companiesFind employers in freehire's catalogue by name or by where they hire, with how many postings each has open. Use when the question is about a company rather than about a role.
search_jobsSearch freehire's catalogue of IT job postings. Use for any question about which jobs are open — by technology, seniority, location, pay or employer. Returns a short preview of each posting. A role has several names: join two or three in one query with OR, e.g. title:SRE OR title
similar_jobsPostings most similar to one posting, by its slug, nearest first — for "show me more like this". Empty for the newest postings, whose neighbours are not computed yet.
subscribeCreate a job alert: a saved search over ANY of the job search's filters whose new postings are delivered to the person on the channels their account has connected (email, Telegram, the mobile app, a webhook) — this conversation is not notified. e.g. remote senior Go roles in the
subscription_updatesList the new postings the person's job alerts have matched — the same matches their alerts are built from, newest first, still-open postings only. Narrow to one alert by id, and to a window by since (RFC 3339) or days (default 7, max 30). An alert only matches postings that appea
suggest_dictionary_termRequest review of a missing specialization, skill or company industry, as on freehire's dictionary page. This records a suggestion, not a new working filter or a vacancy. Existing terms and aliases are refused. Repeated requests share the existing queue entry and increase request
track_jobSet the application stage and/or a free-text note on a vacancy the user is tracking. Omit a field to leave it unchanged. Valid stages: preparing, applied, screening, responded, interview, offer, accepted, rejected, withdrawn, expired.
unsave_jobRemove a vacancy from the user's bookmarks. Idempotent.
unsubscribeStop one job alert by its id, on every channel or on the one named. Effect: deletes the alert's delivery on those channels and their record of matches; the saved search itself stays on the account as a bookmarked search.
update_profileChange the user's saved profile: the preferences (roles, skills, seniority, languages, location) and the headline and summary text shown on their profile page. This changes their account, so say what you are about to change and get the user's agreement first. Call get_profile fir
update_subscriptionChange one of the person's job alerts by its id. Every field is optional and only the ones given change: name; the search (query, filters, salary_min, salary_max — each replaces that part, an empty filters object clears the facet filters, a salary bound of 0 clears it; website-on
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日
注册名称已通过域名 freehire.me 验证(注册中心会核实域名所有权)
代码最后更新于15天前
使用 MIT
在 22 毫秒内响应(HTTP 401)
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
已读取 56 个工具描述,未发现针对 AI 的隐藏指令
云端地址最近 5 次检查中有 5 次响应 · 最近一次 22 ms · 检查于 2026年11月19日
OSV.dev 中没有 freehire-mcp@0.8.0 的记录
只检查这个版本的包本身,不包括所有依赖 · 检查于 2026年11月15日
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/me-freehire-freehire)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 6 项适用的基础检查中通过了 6 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于15天前,最新版本(0.8.0)于22天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
同一分类中有:OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Keyword research, site audits, rank tracking and AI visibility for your AI agent.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls
| 本项 freehire | OpenSEO | Exa | Microsoft Learn MCP | Docs | COTAL actions (cotal.ai) | |
|---|---|---|---|---|---|---|
| 运行位置 | 云端或安装在电脑上都可以 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 是 | 是 | 是 | 否 | 否 |
| 基础检查 | 6/6 | 5/5 | 2/4 | 4/4 | 4/4 | 4/4 |
| 许可证 | MIT | MIT | MIT | CC-BY-4.0 | NOASSERTION | Apache-2.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Search 4.9M+ unique open jobs from 437 sources inside Claude, ChatGPT or your coding assistant. Find roles by stack, salary, seniority, work mode and location, inspect employers, and keep your shortlist and application progress in one place. The catalogue includes 680K+ company profiles and 178 ATS platforms. Figures are from the exact catalogue snapshot on 5 November 2026 (live figures).
The hosted MCP connection offers public search without an account and personal tools through OAuth at one address. The local npm server uses a personal API key and also provides CV and experience-bank tools. Saving or marking a job applied updates tracking; employer submission is a separate OAuth workflow that requires explicit permission and review.
The local server mirrors the freehire CLI: same API, same credentials, exposed as MCP tools instead of shell commands.
The plugin connects to https://freehire.me/api/v1/mcp over Streamable HTTP. Public catalogue tools work without sign-in. Connect your account with OAuth for personal tools. It includes job search and market research, plus your profile, saved jobs, application tracking, reports, alerts and account-enabled automatic applications. In Claude Code, install it as a plugin:
/plugin install freehire --marketplace strelov1/freehire-mcp
In other OAuth-capable hosts, add the canonical URL as a custom remote connector and complete the sign-in flow. In Claude Code, use /mcp to select Freehire and authenticate before personal calls; for a custom server named freehire, use claude mcp login freehire. Do not assume every host opens sign-in automatically from a tool-level challenge. The included skill automatically submits the user's original unrecognized skill, specialization or company industry for dictionary review through suggest_dictionary_term. It also sends a minimal report_problem for a failed operation or missing capability, excluding credentials, CV content, conversations and personal contact details. These two workflow reports require no separate confirmation; empty search results alone trigger neither. The agent confirms submission only after success and continues the original task. Other account changes and application sending require your confirmation; automatic applications also require the account setting that permits connected agents to apply.
The ChatGPT package is freehire (display name Freehire), with a freehire MCP connection to the original URL and mixed public/OAuth authentication. Upload updates to the existing Freehire plugin. The separate Freehire Account plugin and its /api/v1/mcp/account endpoint remain available during client migration.
Every push to main, pull request, and manual run of the CI workflow builds two ZIP files after the checks pass. Open a successful run and download the freehire-plugins- artifact:
freehire-chatgpt- .zip: upload this ZIP as the ChatGPT plugin package. It includes the portable plugin manifest, hosted MCP connection, icon, and the current find-tech-jobs skill.freehire-claude-skill- .zip: upload this ZIP in claude.ai under Customize → Skills. Add https://freehire.me/api/v1/mcp as a remote connector separately and complete OAuth sign-in; uploading a skill does not configure an MCP connection.Run npm run build:plugins locally to write both archives to dist/plugins/. Packaging uses Python 3.9+ and its standard library; it needs no API credentials, live server access, or sibling checkout. The version comes from package.json, and all packaged metadata, assets and skills come from the checked-out commit. Both archives include the same skills/find-tech-jobs/SKILL.md source and its dictionary and problem-reporting workflow. The hosted MCP connection discovers the live server's tools rather than bundling a fixed tool list; existing account tools remain available. The project-local .agents/skills/verify-freehire-mcp skill verifies the archives, local stdio discovery, hosted public access and OAuth using real transports and the official MCP Inspector CLI. CI runs the archive/local checks and uploads the freehire-verification- proof artifact. Hosted checks additionally need the deployed unified backend and a dedicated reviewer OAuth grant.
This workflow builds download artifacts; directory submission and publication remain separate steps.
For the public Claude directory, submit this repository with Plugin path set to plugins/claude and track main. Pair the bundle with the existing Freehire MCP connector in the same Claude organization. The bundle includes the skill and the same hosted MCP URL, so it does not install the local npm server or its dependencies. The existing connector remains the source of authentication and tool health information.
npm run build:plugins also refreshes the committed plugins/claude folder from the current skill, Claude manifest, connection configuration, README template and license. Commit that folder with changes to those sources. CI checks it before building the ZIPs and fails if the directory bundle is stale. After the initial directory review, Claude can scan new commits on the tracked branch; publishing still follows the listing's review settings.
The hosted tools use names such as search_jobs, get_job, get_profile, save_job, track_job and my_jobs; discover their current schemas in your host. The unified hosted search uses top-level public filter fields; discover its live schema. Personal tools may use nested filters, so inspect each tool separately. CV tailoring and experience bank tools in the local server below are not part of this account connection.
No global install needed — the host runs it via npx. Add it to your host's MCP configuration (Claude Desktop → Settings → Developer → Edit config, or ~/.claude.json for Claude Code):
{
"mcpServers": { "freehire": { "command": "npx", "args": ["-y", "freehire-mcp"], "env": { "FREEHIRE_TOKEN": "fhk_xxxxxxxx" } } } }
Create the fhk_… key in the web app (freehire.me → account menu → API keys). If you already use the freehire CLI (freehire auth login), you can omit `env` — the server reads the same ~/.freehire/creds.json.
The token and API base URL resolve with precedence env → `~/.freehire/creds.json` → default `https://freehire.me`:
| What | Sources |
|---|---|
| Token | FREEHIRE_TOKEN → creds file |
| API base URL | FREEHIRE_API_URL → creds file → https://freehire.me |
The server only reads the credentials file (it never writes it — logging in stays the CLI's job). If no token is configured, tools return a clear "not authenticated" error rather than the server failing to start.
| Tool | Purpose |
|---|---|
whoami | Authenticated user (verify the key). |
profile | The candidate's saved job-search profile (skills, preferences, contact-free CV). |
facets | The filter/skill vocabulary: every facet's live values with counts. Call first. |
search | Keyword + facet job search; returns jobs with their full description as markdown and the total match count. |
market_fit | Score a skill list against live market demand (coverage + gaps). |
job | A single job's full content by slug. |
check_jobs_open | Whether postings are still open (up to 50 slugs). Run it on a shortlist before presenting it. |
similar_jobs | Postings most similar to one posting. |
salary_stats | Salary percentiles by role family, seniority and country, with sample sizes. |
job_market_stats | How many open postings match a set of filters, and what they ask for. |
list_filter_values | The values one filter accepts, with counts (golang finds go). |
company | A company and its open jobs by slug. |
apply | Mark a job applied. |
save / unsave | Bookmark / remove a bookmark. |
stage | Set the application stage (server-validated). |
note | Attach a free-text note. |
my | The caller's tracked jobs (all/viewed/saved/applied) with stage + note. |
subscribe | Create a job alert: a saved search delivered by email, Telegram, the app or a webhook. |
list_subscriptions | The caller's job alerts with every setting. |
update_subscription | Change an alert's name, search, channels, or pause it. |
unsubscribe | Stop an alert on every channel or one. |
subscription_updates | The new postings the caller's alerts have matched. |
cv_tailor | Start (or reopen) tailoring for a vacancy; returns the CV id the other cv_* tools take. |
cv_list | The caller's tailored CVs with the vacancy each was written for. |
cv_context | The fit analysis a tailored CV should reframe toward (missing_have vs missing_gap). |
cv_get | A tailored CV's full document. |
cv_edit | Apply a batch of path-addressed edits to a tailored CV, atomically (server-validated; uncited claims are refused). |
cv_render | Render a tailored CV to a PDF, returned as a base64 application/pdf resource. |
experience_list | The candidate's experience bank, with each achievement's provenance. cv_edit's evidence_id comes from here. |
experience_add_employment / experience_add_achievement | Record a place, or one piece of evidence. |
experience_update_employment / experience_update_achievement | Correct one. Field-level: what you do not name is kept. |
experience_remove_employment / experience_remove_achievement | Delete one. No undo; a place must be empty first. |
submit | Submit a vacancy for moderation. |
my_submissions | The caller's submissions with status. |
contribute | Hand over a vacancy or company career board link to the catalogue intake. |
my_contributions | The caller's contributed links and boards with ingestion status. |
jobs_add / jobs_edit | Moderator: author / edit a job (403 without the role). |
submissions_pending | Moderator: the review queue. |
submission_approve / submission_reject | Moderator: decide on a submission. |
Filters. search, market_fit, and facets share the same market-filter parameters: remote, region, country, city, company, category, role, seniority, employment_type, english_level, exclude_skill, salary_min, visa, plus a generic facets map ({"source": "greenhouse"}) for any other facet in the vocabulary. Discover valid values with the facets tool — do not invent them. In search, skills is a filter; in market_fit, skills is the measured set.
Geography widens. region, country and city are ONE OR-group: region: ["eu"] with country: ["IT"] means "in Europe or in Italy" and returns everything the region alone would. To search a single country, pass country and omit region. The three name a single concept — *where* — so picking two places reads as "either", which is what makes region: ["eu"] with country: ["BR"] ("Europe or Brazil") useful. There is no AND to switch on: _mode=and does not apply to geography.
Unknown values are named, not guessed. A filter value the API does not recognise (a misspelt skill such as golangg) is reported in ignored_values, e.g. {"skills": ["golangg"]}, beside total in search and in the {data, ignored_values} wrapper of facets and market_fit. Unlike an unread param it still narrows — to nothing — so