@mambalabsdev
基本信息
MCP server for the full Mamba Labs GTM Suite. All six GTM actors as tools in one server via Apify. Clay-ready output.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mamba-gtm-suite": {
"command": "npx",
"args": [
"-y",
"@mambalabsdev/mcp-gtm-suite"
],
"env": {
"APIFY_TOKEN": "your-apify-token"
}
}
}
}Scan company career pages to detect GTM hiring activity. Returns sales, marketing, and revenue operations job postings across Greenhouse, Lever, and Ashby as a flat, Clay-ready JSON row. Read-only; requires an APIFY_TOKEN and consumes Apify credits per call.
Detect which GTM tools a company uses from its public website. Returns CRM, sequencer, and marketing automation signals with per-tool boolean flags as a flat, Clay-ready JSON row. Read-only; requires an APIFY_TOKEN and consumes Apify credits per call.
Aggregate a company's GTM signals into one composite score. Runs hiring and tech-stack detection in one call and returns a composite score, recommended action, and optional summary as a flat, Clay-ready JSON row. Read-only; requires an APIFY_TOKEN and consumes Apify credits per call.
Scan a company's job board for roles in chosen categories across Greenhouse, Lever, Ashby, Workday, and Rippling. Returns matched role counts and titles per category as a flat, Clay-ready JSON row. Read-only; requires an APIFY_TOKEN and consumes Apify credits per call.
Resolve a company domain or name to its LinkedIn company URL with a confidence score, firmographics, and social links as a flat, Clay-ready JSON row. Provide at least one of company_domain or company_name. Read-only; requires an APIFY_TOKEN and consumes Apify credits per call.
Score a company against your ideal customer profile (ICP) using weighted signals. Returns a 0 to 100 icp_score, an A to D icp_tier, and a per-signal breakdown as a flat, Clay-ready JSON row. Define your ICP with a template, scoring_config, or plain-English icp_description (which requires llm_api_key). Read-only; requires an APIFY_TOKEN and consumes Apify credits per call.
Resolve any combination of company name, domain, or LinkedIn URL into one canonical company identity: the name, primary domain, and LinkedIn company URL, each with a 0-100 confidence score plus an overall score and a match method. Cross-checks the inputs you give it, resolves the ones you do not, and flags conflicts (a domain and a LinkedIn slug that disagree) instead of merging them. Provide at least one of company_name, domain, or linkedin_url. Read-only; requires an APIFY_TOKEN and consumes Apify credits per call.
Enrich a company domain into structured firmographics: employee band, industry, HQ, founded year, revenue estimate, logo, and description, with source provenance. Parsed from the company's schema.org/Organization JSON-LD and HTML meta tags and returned as a flat, Clay-ready JSON row with a source_signals array and a data_completeness score. Read-only; requires an APIFY_TOKEN and consumes Apify credits per call.
Map a company's social media presence across LinkedIn, X, Instagram, Facebook, and YouTube. Returns profile URLs and follower counts in flat Clay-ready JSON. Profiles are discovered from the company's own homepage links, a web search fallback, and pattern guessing, then validated against the company. Follower counts are extracted where public; X is URL-only (its count needs login) and Instagram and Facebook counts are best-effort. Provide at least one of company_domain or company_name. Read-only; requires an APIFY_TOKEN and consumes Apify credits per call.
Scan Google News and PR wires for funding rounds, executive moves, product launches, and acquisitions at any company domain. Returns deduplicated, dated events in flat Clay-ready JSON. Read-only; requires an APIFY_TOKEN and consumes Apify credits per call.
Monitor a company domain for changes across hiring, tech stack, funding, firmographics, and social since the last run. Returns only what changed as typed change events in flat, Clay-ready JSON. Read-only; requires an APIFY_TOKEN and consumes Apify credits per call.
Given a company domain, determine how far that company has gone with AI. Returns an ai_maturity tier of none, declared (says AI but nothing observable is running), deployed (AI tooling is live on the site), or commercialized (the pricing page charges for AI via credits, tokens, an add-on, an AI-named plan, or a per-outcome price), plus the detected AI vendors, validated llms.txt status, robots.txt AI-crawler policy, and the evidence behind the verdict. A domain behind a bot challenge returns blocked=true at low confidence rather than a false negative. Returns flat, Clay-ready JSON. Read-only; requires an APIFY_TOKEN and consumes Apify credits per domain analyzed.
Given a company domain, determine whether that company runs cold email outbound and on what stack. Returns a runs_outbound verdict of program (a deliberate cold outbound setup), light (one weak signal), none, or unknown, with the evidence behind it. The strongest signal is the lookalike sending domains a real program leaves behind: domains like getcompany.com or company-mail.com that carry their own mail and redirect back to the primary site. Also returns the inbox provider (Google Workspace, Microsoft 365 and others) for the primary domain and each sending domain, any detected sending platform (Outreach, Salesloft, Lemlist, Instantly, Smartlead, Apollo and more), registration clusters showing sending domains bought on the same day, cold email infrastructure vendors, and SPF, DKIM and DMARC posture. Sending platform recall is partial by design: sequencers that connect over OAuth to a customer's own mailbox leave no DNS trace, so an empty sending_platforms means little while a populated one is solid. Public DNS and HTTP redirects only. Returns flat, Clay-ready JSON. Read-only; requires an APIFY_TOKEN and consumes Apify credits per domain analyzed.
Given a company domain, measure how much long-form work that company publishes and whether the rate is rising or falling. Returns post counts for the last 30 days, 90 days and 12 months, a monthly average, and a cadence_trend of accelerating, steady, declining, dormant or unknown, with the percent change behind it. The trend compares the last 90 days against the prior 275 days, both normalized to posts per month. Also returns the blog URL, the format mix (blog posts, guides, reports, case studies, whitepapers, podcasts, videos, press releases, research), the number of distinct bylines, and how the post list was discovered. This measures EDITORIAL output volume, not product changelogs: a release feed is detected and rejected rather than counted. Publication dates are read from the post pages, because sitemap lastmod was measured to be a modification date running later than publication by a median of 151 to 1653 days. When a site's date field tracks edits rather than publication, date_source_reliable comes back false and every count is nulled rather than reported wrong, so read that field before quoting a number. Counts are a census when the archive fits the page budget and a scaled even sample otherwise, flagged by counts_are_estimate. Public sitemaps, feeds and pages only. Returns flat, Clay-ready JSON. Read-only; requires an APIFY_TOKEN and consumes Apify credits per domain analyzed.
Push enriched lead rows into an existing Instantly or Smartlead campaign. Maps common Clay column names onto each sequencer's own field names, optionally drops leads below a minimum ICP score, optionally deduplicates against the leads already in the destination campaign, and sends the rest in batches. Returns one flat summary row: how many leads were received, dropped for having no usable email, dropped by the ICP gate, dropped as duplicates, eligible, actually created by the sequencer, skipped by the sequencer, and failed, plus the vendor's own error message per failed address. The campaign must already exist; this does not create campaigns or write sequence copy. Set dry_run true to get back the exact request payload that would be sent without creating a single lead and without being charged, which is the safe way to check a mapping against a new campaign. Billing is per lead the sequencer confirms it created, so gated, duplicate, skipped, failed and dry-run leads are all free. Instantly uses API v2 and needs a v2 key; Smartlead uses API v1. Requires an APIFY_TOKEN and consumes Apify credits. This WRITES to your sequencer campaign unless dry_run is true.
Give it a domain and it returns whether an AI agent can read that site, and what the site's policy says, as one flat row of 42 fields across five families: the llms.txt family including llms-full.txt and ai.txt, robots.txt AI crawler policy including the newer Content Signal directives, structured data presence and health across JSON-LD, microdata, Open Graph and canonical, render mode, and machine readable endpoint discovery covering sitemap, OpenAPI, well known files and feeds. Every field is a fact read off a fetch. No model is called at any point, so the same domain returns the same row today and next month unless the site actually changed. Twelve requests per domain, typically 2 to 4 seconds. Built for a technical SEO or growth engineer preparing a site for AI crawlers, or an agency selling that work and needing a before and after audit across a client list. Requires an APIFY_TOKEN and consumes Apify credits. Read only.
One contact in, one classified row out. Give it a job title and it returns the department, the seniority level, a seniority_rank from 1 to 12 you can filter with a comparison, and classification_rule, the named rule that fired, so every decision is auditable. The classification is a deterministic rule table: it needs no API key, calls no model, and returns the same answer for the same title every time. Only job_title is required. full_name and company_domain are read only when verify_position is on, which checks whether the person is still listed on their employer's own website and adds roughly 3 seconds and 9 requests per contact. The optional LLM fallback for titles the rules cannot place runs on your own key, set as the LLM_API_KEY secret environment variable on your own copy of the actor, and only the title is ever sent, never the person's name. With no key set those titles come back null rather than failing the row. This actor does not discover people: the name and title come from you. Requires an APIFY_TOKEN and consumes Apify credits. Read only.
Give it a company domain. It returns the third party conferences and trade shows that company publicly says it attends, with a year for each where one can be resolved, as one flat row. The search runs against the company's own domain, which is what stops a brand collision returning another company's events. The company's own conference is reported separately and is never mixed into the attendance list. It finds events for roughly 2 companies in 10, and an empty row is an honest empty row rather than a guess: read coverage, fetch_status and queries_failed to tell a company with no published events apart from a search that could not see. Events dated outside the years you ask for are still returned and flagged, so filter on event year rather than assuming the input filtered for you. This is not an events database and not an exhibitor list: it takes a company and reports what that company publishes. Requires an APIFY_TOKEN and consumes Apify credits. Read only.
Give it a company domain and it returns the registered legal entity behind it: legal name, company number, jurisdiction, status, entity type, LEI and VAT number, as one flat row with a full audit trail of what was rejected and why. Three registers are queried: UK Companies House, GLEIF and SEC EDGAR. Register search endpoints are fuzzy and always return something, so by default a record is accepted only when the normalized legal names are identical. That is why roughly 6 domains in 10 resolve rather than 10 in 10, and why a null here is a trustworthy answer rather than a gap. Read match_method, match_confidence and rejected_candidates before acting on a match. Setting match_strictness to fuzzy will hand you a confidently wrong company on most domains and should be treated as a research mode, not a default. This is not a company database and not a credit or risk product. Requires an APIFY_TOKEN and consumes Apify credits. Read only.
Pick a public award register and a time window and it returns the companies that won public work in it, one flat row per winning company rather than one per award, with award count, total value, largest award, awarding body, award date, a deep link to the source record, and a resolved company domain. Five registers are covered: US federal contracts and US federal grants from USASpending, NIH SBIR and STTR from NIH RePORTER, and UK Contracts Finder and UK Find a Tender. This reports awards that have already been made, so it is not a tender feed and will not tell you what is open to bid on. US federal data lags about two days, so a one day window on a US register returns little or nothing. Winners are sorted by total award value and max_entities is the hard cap on billed rows. Requires an APIFY_TOKEN and consumes Apify credits. Read only.
Point it at LinkedIn person profiles or company pages and it returns their recent posts as flat rows, with the real reaction and comment counts on every one, plus the commenters LinkedIn shows publicly. No cookies, no LinkedIn account, no credentials of any kind. One dataset carries three row types told apart by row_type: post, engager and notice, so filter on row_type before loading a table. post_id is the numeric activity URN and is stable across runs and across both permalink spellings, which makes it safe as a primary key and as a have-I-already-seen-this check. Read the limits before relying on the commenters: LinkedIn renders about ten top-level comments to a logged-out visitor whatever the real total, measured whole-run coverage was 3.7 percent, and roughly 30 percent of comment rows carry no timestamp. Reactor identities are not served to a logged-out visitor at all, so every post row carries the real reaction_count and reactors_status says unavailable_without_login. Every row carries degraded and degradation_reason: filter on degraded before you trust an absence. Requires an APIFY_TOKEN and consumes Apify credits. Read only.
A single MCP server that bundles all eleven account-intelligence tools from the Mamba Labs GTM Suite. Each tool wraps a dedicated Apify actor and returns Clay-ready flat JSON, covering identity resolution, enrichment, signal detection, and ICP scoring. Designed for go-to-market teams who need a unified interface for account intelligence.
Install via npx with Node.js 18 or newer. You need an Apify account and an API token (get one at https://console.apify.com/account/integrations). Add the configuration to your Claude Desktop’s mcpServers block as shown in the README, setting APIFY_TOKEN in environment variables. Restart Claude – all eleven tools become available.
All eleven tools: resolve_company_identity, enrich_company_firmographics, map_company_social_presence, resolve_linkedin_url, scan_gtm_hiring_signals, detect_gtm_tech_stack, scan_job_board_keywords, get_funding_press_signals, get_company_changes, aggregate_gtm_signals, and score_icp_fit.
Node.js 18 or newer and an Apify account with an API token.
Log in to the Apify Console (https://console.apify.com), go to Account → Integrations, and copy your token.
No. That actor audits email‑sending infrastructure (SPF, DKIM, DMARC, blacklists) and is intentionally not bundled here because it sits outside the account‑intelligence scope.
Each tool returns flat JSON, designed to be copy‑pasted directly into Clay or other spreadsheet tools.
A curated list of references for MLOps
See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep
🚀 The fast, Pythonic way to build MCP servers and clients.
评论