能做什么
Find B2B leads on LinkedIn that match your ICP, with verified facts and a first message for each.
作者提供的原文
- 连接方式 在云端运行
- 账号或密钥 不填密钥也能用 · 有 Authorization 可以填上(通常能提高额度)
- 分类 营销与社交媒体
可搭配使用
教 AI 做这类工作的 Skill,可与本项一起使用
为什么排在这里
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 | 2026-11-17 |
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 2/3 项(仅展示,不用于排序)
安装
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 catchy-me。按照 https://mcp.popnx.com/i/catchy-me.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 2/3 项检查 · 你的提问会经过开发者的服务器(app.catchy-me.com) · ✓ 命令已检查 2026年11月17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
打开 Claude 的 Connectors 页面
CustomizeConnectors
点击“Add” → “Custom” → “Web”,填写这 2 项
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
Name · 名称catchy-meRemote MCP server URL · 地址https://app.catchy-me.com/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
在聊天中开启
+Connectorscatchy-me
试一试
用 catchy-me 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 catchy-me,或回答中出现 catchy-me 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
在网页版 ChatGPT 打开添加 MCP 的页面
Plugins+Add custom MCP server
填写名称和地址
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
Name · 名称catchy-meConnection · 地址https://app.catchy-me.com/mcp在聊天中选择 catchy-me
开启新聊天,输入前先从插件列表中选择 catchy-me
试一试
用 catchy-me 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 catchy-me,或回答中出现 catchy-me 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
打开终端
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
粘贴这条命令并按 Enter
claude mcp add --transport http --scope user catchy-me https://app.catchy-me.com/mcp在 Claude Code 中输入 /mcp
应能看到 catchy-me 在列表中并显示已连接
试一试
用 catchy-me 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 catchy-me,或回答中出现 catchy-me 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
在 Cursor 中以 Agent 模式打开 AI 聊天
试一试
用 catchy-me 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 catchy-me,或回答中出现 catchy-me 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
在 VS Code 中以 Agent 模式打开 AI 聊天
试一试
用 catchy-me 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 catchy-me,或回答中出现 catchy-me 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://app.catchy-me.com/mcpJSON 设置在下方“开发者专用”中
开发者专用:终端命令和 JSON 设置
通过网页连接
Claude Code
claude mcp add --transport http --scope user catchy-me https://app.catchy-me.com/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"catchy-me": {
"url": "https://app.catchy-me.com/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"catchy-me": {
"type": "http",
"url": "https://app.catchy-me.com/mcp"
}
}
}需要你填写的值
- Optional. A catchy-me API key from Settings (catchy_...), sent as a Bearer token. Without it, clients that support MCP OAuth sign in through the browser when an account tool is called; public tools w…
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。
一览
哪些应用可以使用它
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
它能做什么
工具名称和描述与服务器在 2026年11月17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。
catchy_infoWhat Catchy is and how it works: lead search with facts and AI outreach, plans, briefs and credits, how to connect this MCP server (OAuth or an API key), how an agent signs up by itself, and the links to the Terms of Use and the Privacy Policy. No sign-in needed.
sign_upRegisters a new Catchy account and emails a 6-digit code to confirm it (then confirm_sign_up). Set accept_terms=true ONLY after the user has read and agreed to the Terms of Use and the Privacy Policy (their links: catchy_info terms_of_use / privacy_policy) — ask them first. Witho
resend_sign_up_codeSends a new code for a pending registration (at most once a minute; the answer is the same whether or not one is pending). [REST: POST /api/auth/register/resend]
confirm_sign_upConfirms the registration with the emailed code and the signup_token of sign_up, and returns an API key for this MCP server (shown once). [REST: POST /api/auth/register/verify]
sign_inAn existing Catchy account: email and password -> an API key for this MCP server (shown once). The web's login limits apply. [REST: POST /api/auth/login]
request_password_resetEmails a code to reset the password of an account (the answer is the same whether or not the account exists). Then reset_password. [REST: POST /api/auth/password/forgot]
reset_passwordSets a new password with the emailed code (every session of the account ends). Then sign_in with it. [REST: POST /api/auth/password/reset]
get_accountThe signed-in Catchy account: name, email, language, plan («тариф»: code, status, period end), briefs («брифы») left this period and when they renew, the free brief, the balance in whole credits (available = balance minus holds of running work) and the search limits (max leads pe
accept_legalRecords that the user accepted the current Terms of Use (https://catchy-me.com/terms) and took note of the current Privacy Policy (https://catchy-me.com/privacy). Use it when a tool answered legal_pending: first show the user both links and ask whether they accept the updated Ter
get_balance_historyThe account's balance lines, newest first: top-ups, grants and charges (search, facts on request, outreach) in whole credits, with the search each charge was for. [REST: GET /api/account/balance/history]
list_plansThe tariff catalog: each plan's monthly price (USD, RUB, EUR), credits and briefs a period, and the Enterprise contact. A subscription is bought with subscribe (a LavaTop payment link) or arranged with Catchy (Enterprise). No sign-in needed. [REST: GET /api/plans]
suggest_company_descriptionStep 1 of a new search («Компания»): reads the user's company site (url) or a text about it and writes a short plain-language description of what it sells, to whom and why it matters. The user may edit it before create_search. Takes up to a minute. Part of a new search's onboardi
suggest_goalsStep 2 («Цель»): four goals for the outreach to the people found (e.g. invite to a call), from the company description. The user picks or writes one. Part of a new search's onboarding: the first assistant call of an onboarding spends one brief (a free account has one search brief
suggest_audiencesStep 3 («Кому пишем»): three customer profiles (ICP) to search for, from the company and the goal; each with a short title, the profile text and why. The chosen text is the `icp` of create_search. Part of a new search's onboarding: the first assistant call of an onboarding spends
parse_exclusions_file«Исключить уже знакомых»: a CSV, TSV, TXT or XLSX file with the people the user already knows (LinkedIn links in any column) -> the profile links found (pass them as exclude_urls of create_search) and the company pages (exclude_company_urls). Part of a new search's onboarding: th
extract_site_file_textWhen the site cannot be read: a saved page (HTML), a PDF or a text file -> its text, to describe the company with suggest_company_description(text=...). Part of a new search's onboarding: the first assistant call of an onboarding spends one brief (a free account has one search br
list_previous_onboardingsThe user's earlier search onboardings (company, goal, audience), newest first. A new search can start from one of them (get_onboarding_prefill) without the assistants. [REST: GET /api/onboardings]
get_onboarding_prefillThe answers of an earlier onboarding (company, goal, icp, language) to reuse in create_search; pass its id as source_task there too, so the search plan made then is reused when the brief stays the same. [REST: GET /api/onboardings/{id}]
list_exclusion_sourcesThe user's earlier searches whose people can be left out of a new one (exclude_tasks of create_search): all analysed or only the leads. [REST: GET /api/exclusions/sources]
create_searchCreates a new lead search («поиск лидов») from the onboarding answers and starts compiling its requirements (~1-2 minutes; nothing is charged in credits, but it spends the onboarding's brief if no assistant did). Then poll get_search every 20-30 s until status is `ready`, review
get_subscriptionThe account's subscription: plan, status (active, past_due, cancelling, ended), who manages it (admin or lavatop), price and currency, period end, whether it renews, credits and briefs a period. null: no subscription (list_plans, then subscribe). [REST: GET /api/billing/subscript
subscribeCreates a LavaTop payment for a monthly plan (start, growth, scale; prices in list_plans) and returns its payment_url and order id. Confirm the plan, price and currency with the user first. GIVE THE LINK TO THE USER: a person pays on LavaTop's page by card, SBP or PayPal (an agen
get_payment_statusThe status of a payment order made by subscribe: pending, paid, failed, expired, cancelled. When paid, get_account shows the plan and credits. [REST: GET /api/billing/orders/{id}]
cancel_subscriptionStops the renewal of a LavaTop subscription: the plan stays until the period's end and the credits stay on the balance after it. Ask the user to confirm and pass confirm=true. [REST: POST /api/billing/subscription/cancel]
list_leadsThe people of a search by kind: fit («Подходят»: the leads, in their order), partial («Частично»: some requirement not proven, with what was assumed), miss («Не подходят», with the reason). Compact rows; paginate with offset/limit. get_lead gives one person's dossier with facts.
get_leadOne person of a search: the profile card, the company, the verdict and why they fit, each criterion's status with how it was checked, and the facts found (dated, with source links) — the material for a personal message. [REST: GET /api/tasks/{id}/candidates/{cid}]
quote_facts_on_requestAfter a search: the price in credits of finding facts for chosen partial people and moving them to fit («перевести в подходящие», promote=true), or facts only (promote=false). Free, changes nothing; the answer's `credits` is the confirm_credits of start_facts_on_request, `skipped
start_facts_on_requestSPENDS CREDITS: quote_facts_on_request first, show the price to the user and after their yes pass its `credits` as confirm_credits. The work runs in the background; poll get_search / list_leads. [REST: POST /api/tasks/{id}/manual]
demote_leadAfter a search: moves chosen fit people to partial («в частично подходящие»), e.g. the user disagrees with the verdict. Free, at once. [REST: POST /api/tasks/{id}/demote]
diagnose_searchThe criteria revision («Изменить критерии»): while a search asks about a higher price, or when a finished search ran out of people, works out which criteria hold it back and proposes changes, each combination with its price in credits and the leads it may give. Takes up to ~75 s.
revise_searchApplies chosen proposals of diagnose_search. SPENDS CREDITS: show the price of that combination and pass it as confirm_credits after the user's yes, with the diagnosis' `version`. For a finished search whose people ran out, `more` (and stop_at_target) say how many more leads to f
get_search_funnelA finished search's funnel in plain words: how many people were seen, checked, rejected and why, and how many became leads. [REST: GET /api/tasks/{id}/funnel]
export_searchA download link for the search's leads as Excel (xlsx) or PDF: chosen kinds (default fit and partial), with the facts and the brief. The link works for one hour without signing in; give it to the user. [REST: GET /api/tasks/{id}/export.xlsx|pdf?kinds= (signed link /api/dl/{token}
get_outreachThe outreach («Рассылка») of a finished search: the campaign (sender with its card, essence = offer / ask / tone / rules / language, the accounts, counts, the current generation, credits charged) and the fit people with their state (paginated), plus what to do next (`next`). [RES
list_outreach_presetsThe user's saved outreach setups across searches (sender, offer, ask, language, accounts, source search), newest used first; new_outreach with preset_id copies one into a fresh generation. [REST: GET /api/outreach/presets]
new_outreachA fresh outreach generation of the search: empty, or with this search's previous setup (reuse_previous) or a saved one (preset_id). Free; the first paid setup step of the generation spends one brief. [REST: POST /api/tasks/{id}/outreach/new]
set_outreach_senderWho writes the messages: mode=linkedin with the sender's LinkedIn link (the profile and posts are analysed, about a minute), or mode=text with a few sentences about them. The first paid setup step of a generation spends its brief. Then poll get_outreach. [REST: PUT /api/tasks/{id
edit_sender_cardCorrect the sender's card the analysis made (name, role, company, voice = how they write, summary, background, interests). [REST: PATCH /api/tasks/{id}/outreach/sender/card]
suggest_outreach_essenceA draft of «Что предлагаем» (the offer) from the search's onboarding. Free for the user (it may spend the generation's brief). [REST: POST /api/tasks/{id}/outreach/essence/suggest]
set_outreach_essence«Суть»: offer (what we offer), ask (what we want from the person), optional tone and client_rules, and the message language. [REST: PUT /api/tasks/{id}/outreach/essence]
set_outreach_funnel«Аккаунты»: what the user can write from — email (bool), linkedin (none | basic | sales_navigator), threads (bool), linkedin_comments (public comments on LinkedIn posts, bool). At least one. The route of each person's messages is chosen from these. [REST: PUT /api/tasks/{id}/outr
quote_outreachThe price in credits of researching and writing messages for the chosen fit people (per person, total, the most it may hold), the balance, and who is skipped. Free. Its `credits` is the confirm_credits of start_outreach. [REST: POST /api/tasks/{id}/outreach/quote]
start_outreachSPENDS CREDITS: quote_outreach first, show the price to the user and after their yes pass its `credits` as confirm_credits. Needs the sender ready, the essence and the accounts. Runs in the background (minutes); poll get_outreach every 30-60 s. [REST: POST /api/tasks/{id}/outreac
quote_outreach_retryThe price in credits of retrying the people whose messages failed, from where they stopped. Free; its `credits` is the confirm_credits of retry_outreach. [REST: POST /api/tasks/{id}/outreach/retry/quote]
retry_outreachSPENDS CREDITS: quote_outreach_retry first, show the price, after the user's yes pass its `credits` as confirm_credits. [REST: POST /api/tasks/{id}/outreach/retry]
get_outreach_leadOne person of the outreach: the messages by step (network, kind, text, character limit, hook and the fact it uses, the post of a comment), the route and why, the findings of the research with sources, contacts. step_id, result_id and the revision are what the edit, rewrite and va
edit_outreach_messageSaves the user's own text of one message step (free). result_id and expected_revision from get_outreach_lead protect against an edit made meanwhile. [REST: PATCH /api/tasks/{id}/outreach/leads/{cid}/steps/{step_id}]
quote_message_rewriteThe price in credits of rewriting one message by AI (mode). Free; answers result_id, expected_revision and `credits` for rewrite_message. [REST: POST /api/tasks/{id}/outreach/leads/{cid}/steps/{step_id}/rewrite/quote]
rewrite_messageSPENDS CREDITS: quote_message_rewrite first, show the price, after the user's yes pass its credits, result_id and expected_revision. The new text comes in a few seconds: get_outreach_lead. [REST: POST /api/tasks/{id}/outreach/leads/{cid}/steps/{step_id}/rewrite]
get_message_variantA finished AI variant of a person's messages that was not applied because the text was edited meanwhile (its id from get_outreach_lead). [REST: GET /api/tasks/{id}/outreach/leads/{cid}/candidates/{candidate_id}]
apply_message_variantReplaces the person's messages with that variant (free); result_id and expected_result_revision from get_outreach_lead. [REST: POST /api/tasks/{id}/outreach/leads/{cid}/candidates/{candidate_id}/apply]
export_outreachA download link for the whole outreach as one Excel sheet (every person with the messages by touch, the route, the facts). Works for one hour without signing in; give it to the user. [REST: GET /api/tasks/{id}/outreach/export.xlsx (signed link /api/dl/{token})]
list_searchesThe user's searches («Мои поиски»), newest first: id, title, status, leads / partial found, target, credits charged, progress of a running one. [REST: GET /api/tasks]
get_searchOne search: status, progress, counts, credits charged, the estimate (price examples), what to do next (`next`); for a search that asks about a higher price, the question (`ask`). detail=spec adds the requirements as the review screen shows them (criteria with ids, pains, counter-
get_search_requirementsThe requirements of a search as the results sheet shows them (how each criterion is checked, where the facts come from). [REST: GET /api/tasks/{id}/requirements]
edit_search_specBefore the run (status ready): change the role of criteria (required = must be proven, plus = a bonus) and how strictly they are proven (inference = may be inferred, explicit = needs an explicit source; dearer), and the order of the sources. No AI call; the estimate is counted ag
edit_criterionBefore the run: action=add (a new requirement in words; an AI call adds it), edit (new wording and/or role / standard of criterion_id), remove («Неверно»: drop it; `confirm` true when the answer warned that it is the only job-title criterion), restore («Вернуть»: undo the last ch
edit_painBefore the run: the pains («боли») the search looks for in a lead's facts. action=edit (new text of pain_id), remove, restore. [REST: POST /api/tasks/{id}/pains/{pid}/edit|remove|restore]
edit_counter_signalBefore the run: the counter-signals («контрсигналы») that make a lead partial or a miss. action=remove or restore. [REST: POST /api/tasks/{id}/counter-signals/{sid}/remove|restore]
set_search_strategyBefore the run: the search method («способ поиска») — people (search people directly), companies_first (find the companies, then the people in them), via_related_people; only the options get_search detail=spec lists for this spec. The plan and the estimate are made again. [REST:
基础检查i
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
- ! 注意
作者与仓库一致
注册中心没有列出源代码仓库,因此无法将发布者(catchy-me.com)与代码对应起来
- … 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
- … 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
- ✓ 通过
端点有响应
在 644 毫秒内响应(HTTP 200)
- – 不适用
使用 OAuth 登录
无需登录
- ✓ 通过
工具描述中没有隐藏指令
已读取 60 个工具描述,未发现针对 AI 的隐藏指令
作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章
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/catchy-me)讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
用户评价
还没有评价
与“营销与社交媒体”中的其他服务器比较i
- 星标数多于此分类中其他 4243 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 4243 个服务器的 89% 更新
- 基础检查结果等于或优于此分类中其他 4243 个服务器的 56%
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。
常见问题
catchy-me 安全吗?
它在 3 项适用的基础检查中通过了 2 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。
它需要哪些密钥或代码?
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。
它在我的电脑上运行还是在云端?
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
它还在维护吗?
GitHub 仓库最后更新于–,最新版本(1.0.0)于3天前进入注册中心。
哪些应用可以使用它?
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)。
有什么可以替代它?
同一分类中有:Relaticle, ChatbotX, X (Twitter) MCP Server by Xquik, Betterlytics, BibiGPT YouTube Video Summarizer
功能相近的其他选择
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
Relaticle
Open-source CRM your AI agents can write to: companies, people, opportunities, tasks and notes.
ChatbotX
Omnichannel customer messaging, CRM contacts, flows, sequences, broadcasts, and AI automation.
X (Twitter) MCP Server by Xquik
Xquik is the world's fastest and cheapest X (Twitter) data API with the most complete X data.
Betterlytics
Query your Betterlytics web analytics from AI agents: traffic, funnels, journeys, errors, uptime.
BibiGPT YouTube Video Summarizer
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
| 本项 catchy-me | Relaticle | ChatbotX | X (Twitter) MCP Server by Xquik | Betterlytics | BibiGPT YouTube Video Summarizer | |
|---|---|---|---|---|---|---|
| 运行位置 | 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 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 是 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 否 | 否 |
| 基础检查 | 2/3 | 4/4 | 4/4 | 4/4 | 4/4 | 4/4 |
| 许可证 | – | AGPL-3.0 | NOASSERTION | MIT | AGPL-3.0 | MIT |
| 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 |
作者的 README
仓库中没有找到 README