Mcp B2b Prospect Engine

com.mambabuilt由 mambabuilt.com 發布v1.2.1更新於 Nov 7, 2026

Enrich companies, discover hiring signals and find verified contacts in one actor.

概覽

AI 產生的概覽

封裝 Apify 上的 B2B 開發客源 actor,讓助理一次執行就能補齊公司資料、找出招募訊號並尋找聯絡人。

可以做什麼
  • 補齊公司資料:依網域或公司名稱解析身分、企業概況、LinkedIn 與社群帳號
  • 找出招募訊號:依關鍵字、國家與地點搜尋職缺,並辨識職缺背後真正的雇主
  • 尋找聯絡人:在目標公司中依職稱、職級與部門篩選人員,可選擇電子郵件瀑布查詢與驗證
  • 全流程執行:依序完成補齊、探索與聯絡人查找,中間以 ICP 評分作為篩選門檻
  • 評分與個人化:依 ICP 預設將結果分為 A 至 D 級,並可為聯絡人撰寫簡短開場白
適用情境
適合業務或商務開發研究:把一份公司名單或目標職務交給助理,取得補齊後的公司資料、招募訊號與潛在聯絡人。較適合已使用 Apify、並接受按次計費與選用第三方廠商金鑰的使用者。
執行需求
透過 npx 在本機執行,需要 Node.js。需要 Apify 帳號與 APIFY_TOKEN 環境變數。選用廠商金鑰可提升覆蓋率:serpapi_key(職缺探索與 full 模式必需)、serper_api_key、findymail_api_key、icypeas_api_key、prospeo_api_key、bounceban_api_key 與 claude_api_key。需能連線至 Apify 及上述廠商。
安裝前請注意
每次執行都會消耗 Apify 額度,依補齊公司數、驗證聯絡人數與探索職缺數計費;廠商 API 呼叫由各廠商另行收費。max_spend_usd 只限制廠商支出,max_charge_usd 才限制 Apify 費用。多個 API 金鑰以工具輸入傳入,README 表示 claude_api_key 不會被儲存。執行可能耗時數分鐘,逾時可能只回傳執行 ID。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Mcp B2b Prospect Engine,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

Prospect Engine MCP Server

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

[B2b Prospect Engine MCP server]

MCP server for the Mamba Labs Prospect Engine actor on Apify.

Four modes in one actor: enrich companies you already have, discover who is hiring for your keywords, find contacts at a company, or run the whole chain end to end with an ICP gate in the middle.

Install

bash
npx -y @mambalabsdev/mcp-b2b-prospect-engine

Claude Desktop

json
{  "mcpServers": {    "mamba-b2b-prospect-engine": {      "command": "npx",      "args": ["-y", "@mambalabsdev/mcp-b2b-prospect-engine"],      "env": { "APIFY_TOKEN": "your-apify-token" }    }  }}

Get an Apify token at console.apify.com/account/integrations.

Tool

run_prospect_engine

Four modes in one actor: enrich companies you already have, discover who is hiring for your keywords, find contacts at a company, or run the whole chain end to end with an ICP gate in the middle.

InputTypeRequiredNotes
modeenumnoWhat to run. enrich_companies resolves identity, firmographics, LinkedIn and social for each company. discover_jobs finds who is hiring for your keywords and resolves the real employer from the job description. find_contacts finds people at each company. full chains all three. Default: "enrich_companies". One of: enrich_companies, discover_jobs, find_contacts, full.
domainsarraynoOne domain per line. Used by enrich_companies and find_contacts.
company_namesarraynoOne name per line. Used when you have a name but no domain.
keywordsarraynoRoles to search for. Used by discover_jobs and full. Example: copy editor, proofreader, content editor. Default: ["copy editor", "proofreader", "content editor"].
countrystringnoTwo letter country code for job search, for example us or gb. Default: "us".
locationstringnoOptional location filter for job search, for example New York.
lookback_daysstringnoDrop postings older than this many days. Sent as a string because Clay sends every field as a string. Default: "30".
max_resultsstringnoCap on postings returned per run. Keeps a broad keyword set from running away. Default: "25".
max_pagesstringno1 to 5. Each page is one SerpAPI call, so this is the main cost dial on discovery. Default: "1".
new_postings_onlystringnotrue to return only postings not seen in a previous run. Default: "false".
previous_run_datestringnoYYYY-MM-DD watermark for delta detection when the cross-run cache is unavailable.
remote_onlystringnotrue to keep only postings flagged remote by the board. Default: "false".
company_size_minstringnoDrop companies below this headcount. Only takes effect once headcount is known, so it applies in full mode and to any discovery row that carried an employee count. Discovery alone does not enrich.
company_size_maxstringnoDrop companies above this headcount. Same condition as the minimum.
exclude_staffingstringnotrue to drop postings from staffing and recruitment agencies. Default: "true".
exclude_marketplacesstringnotrue to drop Upwork, Fiverr, Freelancer and similar gig listings. Default: "true".
extra_marketplacesarraynoAdditional marketplace names to filter out.
fetch_posting_pagestringnotrue to open the job posting when the description alone does not identify the employer. Slower, and it is what catches a job board posting on an employer's behalf. Default: "true".
target_contactsstringno1 to 25. Default: "3".
target_rolesarraynoOnly enrich contacts whose title plausibly matches one of these roles. Filters after discovery and before any paid email lookup, so a non-matching contact costs nothing. Leave empty to keep every contact the seniority and department filters allow.
deny_tokensarraynoWhole words that disqualify a contact even when the title matched a target role, for example product refuses Product Owner and keeps Production Editor. Applies even when no target roles are set.
company_concurrencystringnoHow many companies to work at once. Simultaneous provider calls are this times contact_concurrency; 6 x 3 = 18 sits under the tightest documented provider ceiling. Default: "6".
contact_concurrencystringnoHow many contacts to enrich at once within one company. The email waterfall itself always runs in order. Default: "3".
max_spend_usdstringnoStop making paid vendor calls once this much of your own vendor spend (Findymail, Icypeas, Prospeo, BounceBan) is committed, and return everything completed so far. Caps your vendor bills, not the Apify charge for this actor. Leave empty for no cap.
max_charge_usdnumbernoYour cap on this actor's Apify charge for the run, in USD. A charge that would cross it is not made, the run stops, and one notice row says so. Separate from max_spend_usd, which caps your own vendor bills.
job_titlesarraynoTitles to search for when finding contacts.
seniorityarraynoc_level, vp, director, manager, senior.
departmentsarraynomarketing, sales, engineering, product, finance, hr, operations, legal.
include_emailstringnotrue to run the email waterfall. Needs an Icypeas or Prospeo key, which you supply and are billed for directly. Default: "false".
verify_emailstringnotrue to verify each address. Needs a BounceBan key. Default: "true".
verify_positionstringnotrue to ask a model whether each contact's title on record is consistent and plausibly current, from the supplied evidence only. Needs claude_api_key; skipped without it. Contacts found on the company's own website are skipped. Default: "true".
personalizestringnotrue to write a one or two sentence opener per contact that has an address, referencing something specific about the company. Needs claude_api_key; skipped without it. Default: "true".
brand_voicestringnoHow the opener should sound. Leave empty and it writes plainly and directly.
score_icpstringnotrue to score every row against the ICP rules and tier it A to D. Default: "true".
icp_presetenumnoWhich scoring model to apply. "editorial_services" scores for a seller of managed copy editing and proofreading. "generic_b2b" scores on hiring intent, employer resolvability and headcount with no service-specific vocabulary. Default: "editorial_services". One of: editorial_services, generic_b2b.
min_icp_scorestringnoIn full mode, only companies scoring at or above this go on to contact discovery. Default 45: at 25 the filter passed every keyword-discovered editorial posting, because 25 is the floor such a posting can score. Default: "45".
extra_exclude_namesarraynoAny company whose name contains one of these is excluded.
signal_taxonomyarraynoOverride the default signal types. Each entry is an object with type, strength, title_keywords, and optional also_keywords and description_keywords.
include_socialstringnotrue to resolve Facebook, Instagram, X and YouTube alongside LinkedIn. Default: "true".
source_timeout_secsstringno5 to 120. A source that exceeds this is marked degraded and the run continues. Default: "30".
skip_cachestringnotrue to ignore the 7 day cross-run cache and recompute everything. Default: "false".
serper_api_keystringnoYour Serper.dev key. Powers people search in find_contacts, which is the highest-coverage layer. Without it the free fallback is measurably poor.
findymail_api_keystringnoYour Findymail key. First provider in the email waterfall.
icypeas_api_keystringnoYour Icypeas key. Runs on Findymail misses.
prospeo_api_keystringnoYour Prospeo key. Runs on the residual after Findymail and Icypeas.
bounceban_api_keystringnoYour BounceBan key. Second verifier, used for the catch-all case.
serpapi_keystringnoYour SerpApi key. Required by discover_jobs and full. Distinct from a Serper key: different vendor.
claude_api_keystringnoYour own Anthropic key, used for position verification and the personalized opener. Both steps are skipped when it is absent. Never stored.

Billing

You are charged per company enriched, per contact verified and per job posting discovered, at different rates for basic and full enrichment. Vendor API calls are billed to you by those vendors directly. Set max_spend_usd to cap that vendor spend per run, and target_roles to skip paid lookups for contacts outside the roles you want. verify_position and personalize run on your own Anthropic key (claude_api_key) and are skipped without it.

Price per event on the Apify FREE plan, from the live pricing record; paid Apify plans pay less per event.

EventPrice (USD)
Company enriched, basic (company-enriched-basic)0.02
Company enriched, full (company-enriched-full)0.08
Contact verified (contact-verified)0.015
Job posting discovered (job-posting-discovered)0.01
Company enriched, basic, chained run (company-enriched-basic-composed)0.015
Company enriched, full, chained run (company-enriched-full-composed)0.06
Contact verified, chained run (contact-verified-composed)0.01125
Job posting discovered, chained run (job-posting-discovered-composed)0.0075
Company enriched, full, reserved rate (company-enriched-full-founding)0.05
Contact verified, reserved rate (contact-verified-founding)0.009
Job posting discovered, reserved rate (job-posting-discovered-founding)0.005

Pricing is on the actor's Apify page. Running this server consumes Apify credits.

What this server does and does not do

It is a thin client for the Apify actor. It passes your input through and returns the actor's output unchanged. Every behavior described above lives in the actor, not here.

Errors are surfaced, never swallowed. An invalid input, an invalid token, an exhausted balance, a timeout, or a run that returns anything other than a dataset all come back as an explicit tool error rather than as an empty result.

The tool starts the actor run and polls it to a finished status, so a long run is not cut off at 300 seconds. The run is allowed 1,800 seconds. If it is still going two minutes after that, the call stops waiting and returns the run ID with a link to it in the Apify Console, where the results land when it finishes. A run that does not succeed comes back as an error with its run ID and status. A full or find_contacts run over many companies can take several minutes, which is why this matters here.

Source

The actor is on the Apify Store. This wrapper is MIT licensed.

Built by Mamba Labs

來源:README.md,提交 9a11aa2

工具

1

run_prospect_engine

Run Prospect Engine

A composed prospecting actor with four modes. enrich_companies resolves identity, firmographics, LinkedIn and social for each domain or company name you supply, and needs no vendor key at all. discover_jobs finds who is hiring for your keywords and resolves the real employer behind each posting, including postings a job board placed on an employer's behalf. find_contacts finds people at the companies you name, with optional email discovery and verification. full runs discovery, enrichment, ICP scoring and then contact discovery, passing only the companies at or above min_icp_score through to the contact stage. Every row comes back flat and Clay ready with per field provenance. Vendor keys are yours: you supply them, those vendors bill you directly, and the per event price covers the actor only. discover_jobs and full require a SerpApi key, which is a different vendor from the Serper key that powers people search. Use it when you need companies, hiring signals, or contacts in one flat table. Do not use it to verify a single email you already have (that is the Work Email Waterfall) or to score a list you already enriched (that is the ICP Fit Scorer). Cost controls: max_results and max_pages bound discovery, target_contacts bounds contacts per company, target_roles skips paid lookups for non-matching contacts, and max_spend_usd caps your own vendor spend. Requires an APIFY_TOKEN and consumes Apify credits. Read only: it enriches and discovers, it writes nothing.

輸入參數modecountrydomainskeywordslocationmax_pagesscore_icpseniorityicp_presetjob_titlesskip_cachebrand_voice另有 36 個

版本歷史

6
  1. v1.2.1最新Nov 5, 2026
  2. v1.2.0Oct 16, 2026
  3. v1.1.2Oct 16, 2026
  4. v1.1.1Oct 6, 2026
  5. v1.1.0Oct 6, 2026
  6. v1.0.2Sep 16, 2026

評分

已滿足適用檢查項的 90%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分
  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分