Mcp Career Change Signal Engine

com.mambabuilt由 mambabuilt.com 发布v1.0.2更新于 Nov 7, 2026

Watch your contacts and get back only job changes: leavers, landings, replacements, new hires.

已验证STDIO仅桌面数据与分析商业与电商

概览

AI 生成的概览

面向 Apify actor 的轻量 MCP 客户端，监控联系人名单并只返回职位变动：离职、去向、接替者与新入职。

可以做什么
  • 运行联系人观察名单，只返回自上次运行以来的变化：谁离职、去了哪里、谁接替、职位关闭后谁新入职
  • 每行附带匹配依据、来源日期、细分标签、开场白草稿，以及 Slack、HubSpot、HeyReach、Instantly 载荷
  • 可控制状态保存方式、读取模式、首次运行基线或报告、花费上限、扫描间隔与并发
  • 可选传入回复、退信、招聘岗位变化、屏蔽名单、ICP 分层及自有服务商密钥
  • 可选将每次最多 100 条信号行推送到带签名的 webhook
适用场景
适合销售、招聘或合作团队定期跟踪老客户、潜在客户或交易联系人名单，只获取职位变动摘要而不必重新读取全部资料。也适合把变动推送到 CRM 或外联工具的工作流。
运行要求
通过 npx 本地运行，需要 Node.js 18 或更高版本、Apify 账户以及 APIFY_TOKEN 环境变量。调用会消耗 Apify 额度。可选的服务商密钥（serper 或 serpapi、prospeo、bounceban、findymail、exa）与 webhook 密钥作为运行输入传入。
安装前请注意
调用按事件计费并计入你的 Apify 账户（联系人检查、信号交付、运行启动），费用随名单规模增长，可设置花费上限。APIFY_TOKEN、服务商密钥和 webhook 密钥会发送给 Apify，服务商密钥以秘密输入形式存储。联系人数据、回复和退信会发送给第三方服务商及你配置的 webhook 地址；回复文本仅保留哈希。结果包含外联文案草稿，发送前请审核。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Mcp Career Change Signal Engine，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。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Career Change Signal Engine MCP Server

[Glama score] [MCP Registry] [npm version] [npm downloads] [license] [mcpservers.org]

[Career Change Signal Engine MCP server]

An MCP server for the Mamba Labs Career Change Signal Engine actor on Apify. Career Change Signal Engine reads the people on your watch list and returns only what changed since you last checked: who left, who landed where, who replaced them, and who started after a role closed. Every row says how the person was matched, which source answered, and how old that source is.

What's Inside

What it does

Read a watch list of contacts and return only what changed since the last run: who left, who landed where, who replaced them, and who started after a role closed. Each row carries evidence, a source date, a segment, a first line draft, and Slack, HubSpot, HeyReach, and Instantly payloads. Pass people (required) and, optionally, replies, bounces, posting changes, suppression, and your own provider keys in providerKeys; it never fetches LinkedIn and holds no key of its own. State is kept per watch_list_id. A run that does not succeed is returned as an error with its run ID. Requires an APIFY_TOKEN and consumes Apify credits per call.

All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.

Quick start

You need Node.js 18 or newer and an Apify account with an API token.

Add this to your Claude Desktop config (claude_desktop_config.json), Cursor, or any MCP client:

json
{  "mcpServers": {    "mamba-career-change-signal-engine": {      "command": "npx",      "args": [        "-y",        "@mambalabsdev/mcp-career-change-signal-engine"      ],      "env": {        "APIFY_TOKEN": "your-apify-token"      }    }  }}

Restart the client. The watch_career_changes tool appears.

Prerequisites

Example prompts

  • "Check my 50 past champions and tell me who left and where they landed."
  • "Run my watch list and draft a first line for each person who changed jobs."

Tool

watch_career_changes. One tool. Example arguments:

json
{  "people": [    {      "person_name": "Jane Doe",      "company_domain": "example.com",      "company_name": "Example Inc",      "title": "Head of Content",      "external_id": "example-1"    }  ],  "watch_list_id": "default"}

Inputs

Every buyer facing input of the live actor, unchanged. Omitted inputs take the actor's own defaults.

InputTypeRequiredDescription
peoplearrayyesYour watch list, one object per person: person_name, profile_url (optional), company_domain, company_name, title, work_email, relationship (prospect, mgl, deal_contact, customer_champion), external_id, crm_id, deal_id, known_history (a HeyReach copy, a Proofed LinkedIn reader row, or generic roles), last_reading (with state_source caller). The engine reads only these people. At most max_people_per_run per run.
watch_list_idstringnoNames the list. State is kept per watch list id when state_source is actor.
state_sourcestringnoactor: the engine keeps state between runs in a named store. caller: you send last_reading per person and keep state yourself.
read_modestringnostored_first: your known_history first, then your keys. live_only: ignore known_history. stored_only: only known_history, no key calls.
first_run_modestringnoreport: the first run returns every change it finds. baseline: the first run stores state and returns nothing, charging only contact_checked.
max_people_per_runintegernoA list longer than this fails the run before any read or charge. Default 150, at most 1,000.
providerKeysobjectnoYour own keys: serper or serpapi (web search), prospeo, bounceban (verifier), findymail, exa. Never written to state, output, logs, or the webhook. Your own key, sent as a run input; never stored by the actor.
linkedin_reader_dataset_idstringnoOptional: the dataset id of a Proofed LinkedIn reader run on the same Apify account. Rows join to people by profile URL.
repliesarraynoOptional reply texts: external_id or work_email or profile_url, text, received_at, channel, is_auto_reply. Text is classified and dropped; only its sha1 is kept.
bouncesarraynoOptional bounces: work_email, bounce_type, smtp_code, smtp_text, bounced_at.
posting_changesarraynoOptional Account Hiring Watch rows. A closed posting starts a new hire search at that company.
suppressionobjectnoemails, profile_urls, opted_out_emails, opted_out_profile_urls, company_domains, company_names. Suppressed people are dropped before the read and cost nothing.
icp_tiersobjectnoOptional map of company domain to tier, shown on landed rows. Never blocks a row.
featuresobjectnoSwitches: replacement, closed_posting, contact_data, first_line, icp, include_promotions. Defaults on except include_promotions.
sender_contextstringnoOptional topic phrase for the first line draft, for example: content production at scale.
max_replacement_candidatesintegernoCandidates proposed per leaver. A person confirms each.
max_spend_usdintegernoStops the run before a charge that would cross it.
sweep_interval_daysintegernoWith state_source actor, a person read within this many days is skipped.
concurrencyintegernoPeople read at once.
webhook_urlstringnoOptional: signed Standard Webhooks POST of up to 100 signal rows per request.
webhook_secretstringnoSigning secret; a whsec_ value is base64 decoded. Your own key, sent as a run input; never stored by the actor.

Pricing

Pay per event on Apify, billed to your Apify account. Prices in USD.

EventFree planBronzeSilverGold
contact_checked, per contact checked$0.02$0.019$0.018$0.017
signal_delivered, per change row delivered$0.068$0.0646$0.0612$0.0578
apify-actor-start, per run start$0.001$0.001$0.001$0.001

Your keys

The actor holds no provider key of its own. Every paid provider key is yours, passed as an input and stored by Apify as a secret input. Without a key, the actor skips that step and says so in the run.

Full actor documentation

apify.com/mambalabs/career-change-signal-engine

License

MIT. See LICENSE.

来源：README.md，提交 5ab2873

工具

1

watch_career_changes

Watch career changes

Read a watch list of contacts and return only what changed since the last run: who left, who landed where, who replaced them, and who started after a role closed. Each row carries evidence, a source date, a segment, a first line draft, and Slack, HubSpot, HeyReach, and Instantly payloads. Pass people (required) and, optionally, replies, bounces, posting changes, suppression, and your own provider keys in providerKeys; it never fetches LinkedIn and holds no key of its own. State is kept per watch_list_id. A run that does not succeed is returned as an error with its run ID. Requires an APIFY_TOKEN and consumes Apify credits per call.

输入参数people必填bouncesrepliesfeaturesicp_tiersread_modeconcurrencysuppressionwebhook_urlproviderKeysstate_sourcemax_spend_usd另有 9 个

版本历史

3
  1. v1.0.2最新Nov 5, 2026
  2. v1.0.1Oct 16, 2026
  3. v1.0.0Oct 14, 2026

评分

已满足适用检查项的 90%

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25 分
  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分