Name: Gtm Suite
Author: Mamba Labs

Gtm Suite MCP

21 Mamba Labs account-intelligence MCP tools in one server: identity, signals, ICP. Clay-ready.

Grade A Local · stdio API key 21 tools v1.12.0 · 12 Oct 2026

No reviews yet by Mamba Labsnpm 4,623 Runs on your machine, nothing hosted

96/100

trust score

516

downloads a day

local

runs on your machine

863

downloads in 30d

What it does

MCP server for the full Mamba Labs GTM Suite. Exposes all eleven account-intelligence actors as tools in one server via Apify: identity resolution, firmographics, social presence, hiring signals, tech stack, job board scanner, funding and press, change fe

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --env 'APIFY_TOKEN=${APIFY_TOKEN}' --transport stdio gtm-suite-mcp '--' npx -y @mambalabsdev/mcp-gtm-suite

# 2 — ask your agent for something these tools do
#   scan_gtm_hiring_signals, detect_gtm_tech_stack, aggregate_gtm_signals and 18 more

It needs APIFY_TOKEN: this reads it from your environment, so export it first.

Gtm Suite costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publisher

Mamba Labs54 servers

7 categories · publishing since 2026

All 54 servers

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Gtm Suite as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads APIFY_TOKEN (Apify API token from https://console.apify.com/account/integrations) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx APIFY_TOKEN … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user --env 'APIFY_TOKEN=${APIFY_TOKEN}' --transport stdio gtm-suite-mcp '--' npx -y @mambalabsdev/mcp-gtm-suite

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

It reaches a system of yours, so it needs your own credential rather than the publisher’s: APIFY_TOKEN — Apify API token from https://console.apify.com/account/integrations. You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

21 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

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. Use this for a go-to-market hiring verdict (is the company building its sales and marketing team, and how…

Parameter	Type	Required	Notes
domain	string	yes	Bare company domain, e.g. stripe.com
role_filter	array	no	Optional list of GTM role keywords to filter on. Defaults to the built-in list.
ats_slug	string	no	Optional ATS board slug override when it differs from the domain.
mode	string	no	Processing mode. "single" scores the domain. "velocity" compares this run against previous_gtm_role_count and previous_run_date. "batch" is an actor-level mode this single-call tool supplies no list f
include_role_details	boolean	no	When true, include the full per-role detail array (title, department, location, url). Default: false.
previous_gtm_role_count	integer	no	GTM role count from the previous run for this domain, used in velocity mode to compute the delta.
previous_run_date	string	no	ISO date of the previous run for this domain, used in velocity mode to report days between runs.

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.

Parameter	Type	Required	Notes
domain	string	no	Bare company domain, e.g. stripe.com. Supply this, company_domain or url.
company_domain	string	no	Deprecated alias for domain, accepted by the actor for older callers. Prefer domain.
url	string	no	Deprecated alias for domain, accepted by the actor as a full company website URL. Prefer domain.
crawl_additional_pages	boolean	no	Crawl up to 2 extra pages for better coverage. Defaults to true when omitted.
skipCache	boolean	no	By default a clean detection is cached for 7 days and reused. Set true to force a fresh detection.
technologies	array	no	Report only these tools. Omit to report every detectable tool. Only tools with a client side fingerprint are selectable. Detection is unchanged, so filtering costs nothing extra.

Aggregate a company's GTM signals into one composite score. Runs hiring and tech-stack detection by default, plus funding, events, or workplace when named in sources, in one call and returns a composite score, recommended action, and optional summary as a flat, Clay-ready JSON row. Read-only;…

Parameter	Type	Required	Notes
company_domain	string	yes	Bare company domain, e.g. stripe.com
include_summary	boolean	no	Include a plain-English gtm_signal_summary.
explain_mode	boolean	no	If true, the summary becomes a longer, more detailed explanation.
sources	array	no	Which signals to aggregate. Defaults to hiring and tech_stack. Each extra source adds one sub actor run to the bill and one dimension to the composite score, which is normalized over the sources selec

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. Use this when you choose the role categories or keywords (engineering, finance, a product name in a…

Parameter	Type	Required	Notes
company_domain	string	yes	Bare company domain, e.g. stripe.com
role_categories	array	yes	One or more of: GTM, Engineering, Finance, Operations, Executive, Custom.
custom_keywords	array	no	Keyword strings to match when Custom is included in role_categories.
enable_fallback	boolean	no	Fall back to a pre-indexed job database when the live ATS cascade finds nothing.
previous_roles_detected	string	no	Comma-separated matched role titles from a previous run, to compute deltas.
previous_run_date	string	no	ISO date of the previous run, e.g. 2026-03-15.

Resolve a company domain or name to its LinkedIn company URL, with a 0-100 confidence_score, social links, and optional firmographics from search snippets, as a flat, Clay-ready JSON row. A URL is returned only when verified: the company homepage links it, or its name is identical to the name the…

Parameter	Type	Required	Notes
company_domain	string	no	Bare company domain, e.g. stripe.com. Required if company_name is not provided.
company_name	string	no	Company name. Required if company_domain is not provided.
includeFirmographics	string	no	When "true", also reads employee count, industry, HQ, follower count and description from search result snippets about the LinkedIn company page. No request is sent to LinkedIn. Fields no snippet stat
skipCache	string	no	When "false", the default, a successful resolution is cached for 7 days and reused. Set "true" to force a fresh resolution. Sent as a string for Clay compatibility.
minConfidenceScore	string	no	A LinkedIn page is returned only when its match score is at least this value, 0 to 100. Default "70". Raise it for fewer, surer answers; lower it for more answers and more wrong ones. Sent as a string

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…

Parameter	Type	Required	Notes
company_domain	string	yes	The primary domain of the company to score, e.g. clay.com
company_name	string	no	Optional display name of the company.
template	string	no	Name of a prebuilt scoring config.
scoring_config	object	no	JSON object of scoring weights.
icp_description	string	no	Plain-English ICP description. Requires llm_api_key.
llm_api_key	string	no	Your OpenAI or Anthropic key, used only with icp_description.
llm_provider	string	no	LLM provider for icp_description: openai or anthropic.
fetch_signals	boolean	no	If true, the actor runs the GTM Hiring Signal Scraper and the GTM Tech Stack Signal Scraper for this company before scoring and fills any hiring or tech stack signal not supplied. Both bill your Apify
include_explanation	boolean	no	If true, adds a score_explanation string to the output.
tier_thresholds	object	no	Optional. Minimum score for each tier as { "tier_a": number, "tier_b": number, "tier_c": number }. Scores at or above tier_a are A, tier_b are B, tier_c are C, else D. Defaults to 80 / 60 / 40.
funded_within_days	integer	no	Optional. How recent a funding round must be to count for the recently_funded signal, in days. Defaults to 540 (18 months).
min_score_to_output	integer	no	If set, rows scoring below this threshold are skipped from output (not pushed to dataset). Skipped rows are logged only.
previous_score	integer	no	Previous ICP score for this company. If provided, output includes score_change and score_trend fields.
gtm_hiring_signal	string	no	Whether the company is actively hiring for GTM/sales roles. Accepts a boolean-like string ("true"/"false"). Sent as a string for Clay compatibility and coerced to boolean at runtime.
gtm_role_count	string	no	Number of open GTM/sales roles. Scores via the gtm_role_count_strong signal when at or above min_gtm_roles (default 2). Accepts a numeric string (e.g. "8"). Sent as a string for Clay compatibility and
uses_hubspot	string	no	Whether the company uses HubSpot. Accepts a boolean-like string ("true"/"false"). Sent as a string for Clay compatibility and coerced to boolean at runtime.
uses_salesforce	string	no	Whether the company uses Salesforce. Accepts a boolean-like string ("true"/"false"). Sent as a string for Clay compatibility and coerced to boolean at runtime.
uses_clay	string	no	Whether the company uses Clay. Accepts a boolean-like string ("true"/"false"). Sent as a string for Clay compatibility and coerced to boolean at runtime.
crm_detected	string	no	Whether any CRM was detected. Accepts a boolean-like string ("true"/"false") or any non-empty CRM name (e.g. "Salesforce"). Sent as a string for Clay compatibility and coerced to boolean at runtime. A
seq_tool_detected	string	no	Whether a sales sequencing tool (Outreach, SalesLoft, Apollo, Lemlist) was detected. Accepts a boolean-like string ("true"/"false") or any non-empty tool name (e.g. "Outreach"). Sent as a string for C

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,…

Parameter	Type	Required	Notes
company_name	string	no	Company name, e.g. Stripe. Provide at least one of company_name, domain, or linkedin_url.
domain	string	no	Bare company domain, e.g. stripe.com. The strongest canonical key when provided.
linkedin_url	string	no	LinkedIn company URL (https://www.linkedin.com/company/stripe) or bare slug (stripe).
skipCache	boolean	no	Force a fresh resolution and ignore the 7 day result cache.
minLinkedinConfidence	string	no	A LinkedIn page the actor finds is returned only when its linkedin_confidence is at least this value, 0 to 100. Default "70". A LinkedIn URL you provide is always returned as given. Sent as a string f

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…

Parameter	Type	Required	Notes
domain	string	no	Bare company domain to enrich, e.g. stripe.com. Provide this or domains.
company_name	string	no	Optional company name, used as a fallback label when the page does not expose one.
domains	array	no	List of bare domains for batch processing. Takes precedence over domain.
batchSize	number	no	Domains enriched concurrently per wave in batch mode. Default 5, maximum 10.
skipCache	boolean	no	Force a fresh enrichment and ignore the 7 day result cache.

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…

Parameter	Type	Required	Notes
company_domain	string	no	Bare company domain, e.g. stripe.com. Provide this or company_name.
company_name	string	no	Optional company name. Improves search accuracy and disambiguation. Provide this or company_domain.
platforms	array	no	Which platforms to map. Defaults to all five.
includeFollowerCounts	boolean	no	Fetch profile pages to extract follower counts (default true). Set false for URLs only, which is cheaper.
skipCache	boolean	no	Force a fresh lookup and ignore the 7 day result cache.

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.

Parameter	Type	Required	Notes
domain	string	yes	Company domain to scan, without https or www, e.g. stripe.com.
company_name	string	no	Optional company name hint, used when the domain does not match the brand name, e.g. Deel for deel.com.
signal_types	array	no	Report only these event types. Omit for every type. Narrowing also narrows the search: a funding only run issues one news query instead of four.
lookback_days	integer	no	How far back to search, in days. Default 365.

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. Pass sources to watch fewer than all five sources and min_severity to drop minor changes; each source…

Parameter	Type	Required	Notes
domain	string	yes	Company domain to monitor, without https or www, e.g. stripe.com.
company_name	string	no	Optional company name hint, used when the domain does not match the brand name, e.g. Deel for deel.com.
previous_snapshot	object	no	Snapshot object returned by a prior run. Supply it and it is the baseline instead of stored state, which is what makes a scheduled run cheap.
sub_actor_timeout_secs	integer	no	Per-child run timeout in seconds. Children run in parallel, so total wall time is about the slowest child. Default: 90.
sources	array	no	Which sources to monitor. Omit for all five. Each source left out is one fewer sub actor run per company, so a single source watch is billed for one source, not five.
min_severity	string	no	Report only changes at or above this severity. low reports every change and is the default. high keeps leadership moves, funding, acquisitions, and a CRM or sequencer appearing or disappearing.

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…

Parameter	Type	Required	Notes
domain	string	no	Company domain to analyze, without https or www, e.g. intercom.com.
domains	array	no	Batch mode: several company domains analyzed in one call. Takes precedence over domain.
check_pricing	boolean	no	Fetch and score the pricing page. Default true. Setting this false is faster but caps the result at 'deployed', because 'commercialized' can only be proven on a pricing page.
skipCache	boolean	no	Force a fresh analysis and ignore the 7 day result cache.
request_timeout_ms	integer	no	Per-request timeout in milliseconds. 3000 to 20000. Default: 9000.
vendors	array	no	Report only these AI vendors. Omit to report every one. Detection is unchanged, so filtering costs nothing extra. The ai_maturity verdict, llms.txt, robots.txt, and pricing reads are site wide and nev

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…

Parameter	Type	Required	Notes
domain	string	no	Company domain to analyze, without https or www, e.g. smartlead.ai.
domains	array	no	Batch mode: several company domains analyzed in one call. Takes precedence over domain.
scan_sending_domains	boolean	no	Scan for lookalike sending domains. Default true. The strongest signal and the slowest step; turning it off caps the verdict at what platform and deliverability signals alone can prove.
sending_domain_depth	string	no	deep (default) checks .com, .co, .io, .net and .org. standard drops .net and .org.
check_deliverability	boolean	no	Add a blacklist check and a 0-100 health score by running the separate Domain Deliverability Checker actor, which bills its own per-domain rate on top of this one. Default false. SPF, DKIM and DMARC a
skipCache	boolean	no	Force a fresh analysis and ignore the 7 day result cache.
max_sending_domain_probes	integer	no	Cap on how many candidate sending domains are probed per company. Lower it to bound run time on companies with many lookalike domains.
request_timeout_ms	integer	no	Per-HTTP-request timeout in milliseconds.
dns_timeout_ms	integer	no	Per-DNS-lookup timeout in milliseconds.

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…

Parameter	Type	Required	Notes
domain	string	no	Company domain to analyze, without https or www, e.g. zapier.com.
domains	array	no	Batch mode: several company domains analyzed in one call. Takes precedence over domain.
max_pages_to_date	integer	no	How many post pages to fetch per domain for dating. Default 400. Above this cap the counts are estimated from an even sample and counts_are_estimate is set true.
domain_time_budget_ms	integer	no	Hard wall-clock ceiling per domain, default 75000. When nearly spent the crawl stops and the row is returned with partial_result true rather than timing out.
skipCache	boolean	no	Force a fresh crawl and ignore the 3 day result cache.
page_concurrency	integer	no	How many pages are fetched concurrently within one domain.
max_sitemap_fetches	integer	no	Cap on how many sitemap files are fetched per domain. Lower it to bound run time on deeply nested sitemap indexes.
request_timeout_ms	integer	no	Per-HTTP-request timeout in milliseconds.

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…

Parameter	Type	Required	Notes
sequencer	string	yes	Which sequencer to push to. Instantly uses API v2, Smartlead uses API v1.
api_key	string	no	Your Instantly v2 API key or your Smartlead API key. An Instantly v1 key will not work: v1 was deprecated on January 19, 2026. Required for any run that calls the sequencer. A dry run with deduplicate
campaign_id	string	yes	The target campaign in the sequencer. It must already exist. Instantly campaign IDs are UUIDs; Smartlead campaign IDs are numeric.
leads	array	no	Lead rows to push. Each row needs an email at minimum. Takes precedence over dataset_id when both are set.
dataset_id	string	no	An Apify dataset ID from an upstream run, for example the output of score_icp_fit. Used only when leads is empty.
min_icp_score	integer	no	Drop leads whose icp_score is below this number. Default 0, which pushes everything. Rows with no icp_score are always kept.
deduplicate	boolean	no	Read the campaign's existing leads first and drop any email already there. Default true. This is a read, so it needs an API key even on a dry run.
dry_run	boolean	no	Run every step, return the exact payload that would be sent, and make zero write calls. Creates no leads and charges nothing. Default false.
field_mapping	object	no	Override the default Clay column to sequencer field map. Keys are your column names, values are the sequencer field names. Set a value to an empty string to drop that column. A target the sequencer do
custom_variables	array	no	Extra column names to pass through as custom variables under their own name. Columns that are neither mapped nor listed here are dropped.

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…

Parameter	Type	Required	Notes
domain	string	yes	One company domain, for example vercel.com. Protocol and path are stripped.
check_endpoints	boolean	no	Probes sitemap, OpenAPI, well known files and feeds. Adds 7 concurrent requests. Default: true.
check_structured_data	boolean	no	Parses JSON-LD, microdata, Open Graph and canonical off the homepage. Costs no extra requests. Default: true.
skipCache	string	no	Leave as false to use the 7 day cache. Set to true to re-audit the domain from scratch. Default: "false".
checks	array	no	Run only these checks. Omit for all of them. Narrowing narrows the work, and the score is rescaled over the checks selected.

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…

Parameter	Type	Required	Notes
job_title	string	yes	The contact's job title, exactly as you hold it. Classified by deterministic rules with no API key needed.
full_name	string	no	Only needed for position verification. Classification works without it. This name is never sent to any language model.
company_domain	string	no	Only needed for position verification. The company's website domain, with or without https.
verify_position	boolean	no	Check whether the person is still listed on their employer's own website. Off by default. Adds roughly 3 seconds and 9 requests per contact, and needs both the name and the domain. Default: false.
use_llm_fallback	boolean	no	Off by default. When on, titles the rules cannot place are sent to your own model using the LLM_API_KEY secret environment variable you set on your copy of this Actor. Only the title is sent, never th
llm_provider	string	no	Which provider your LLM_API_KEY belongs to. Only read when the LLM fallback is on. Default: "openai".
llm_model	string	no	Model id passed straight through to the provider. Only read when the LLM fallback is on. Default: "gpt-4o-mini".
skipCache	string	no	Set to true to ignore cached results and classify from scratch. Default: "false".

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…

Parameter	Type	Required	Notes
domain	string	yes	A single company domain, for example 6sense.com. Protocol and path are stripped.
company_name	string	no	Improves matching when the brand differs from the domain stem, for example Gong for gong.io. Derived from the domain when left empty.
years	string	no	Comma separated, for example 2025,2026. Events dated outside this set are still returned and flagged. Sent as a string so it works from Clay. Default: "2025,2026".
include_own_events	boolean	no	Reports whether the company runs its own conference as a separate field. It is never mixed into the attendance list. Default: true.
max_queries	string	no	Between 1 and 5. Each query costs roughly 0.8 seconds plus a 1.3 second pause. 2 is the measured sweet spot: search engines refuse a third query from the same container almost every time, and the thir
skipCache	string	no	false uses the 21 day result cache. true forces a fresh look. Default: "false".

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…

Parameter	Type	Required	Notes
domain	string	yes	A single company domain, for example monzo.com. Protocol and path are stripped.
legal_name_hint	string	no	Skips the domain lookup and goes straight to the registers with this name. Use it when you already have the legal name and just want the register record.
jurisdiction_hint	string	no	ISO-2 country code, for example GB or US. Narrows which registers are queried and cuts latency. Leave empty to query every register.
match_strictness	string	no	exact accepts a register record only when the normalized legal names are equal, which is the default and the recommendation. fuzzy returns the best scoring candidate with a confidence below 100 and a
validate_vat	boolean	no	Runs any VAT number found on the company's own pages through the EU VIES service and returns the name VIES holds for it, as a cross-check against the register name. Default: true.
skipCache	string	no	false uses the cache: 90 days for a resolved company, 7 days for a null. true forces a fresh look. Default: "false".

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…

Parameter	Type	Required	Notes
register	string	yes	Which award register to read. US federal contracts and grants come from USASpending, NIH SBIR and STTR from NIH RePORTER, and the two UK registers from Contracts Finder and Find a Tender. Default: "us
window_days	string	no	How many days back from today to read awards for. 1 to 90. US federal data lags about two days, so do not use a one day window on the US registers. Sent as a string so it works from Clay. Default: "7"
min_award_value	string	no	Drops awards below this amount in the register's own currency. Set to 0 to keep everything. Sent as a string so it works from Clay. Default: "100000".
max_entities	string	no	Hard cap on billed rows. 1 to 1000. Winners are sorted by total award value, and the run log says how many were dropped. Sent as a string so it works from Clay. Default: "100".
exclude_government_recipients	boolean	no	Drops winners that are themselves government, universities, or public authorities. Leave this on for the grant registers or you get state departments of education instead of companies. Default: true.
resolve_domains	boolean	no	Looks up each winner's website. Turning it off makes the run roughly 20x faster and returns recipient_domain as null with domain_status not_attempted. Default: true.
domain_confidence_floor	string	no	How sure the actor has to be before it gives you a domain. Strict returns fewer domains and almost no wrong ones. Loose returns the most domains and about a third of them are wrong. Default: "standard

Point it at LinkedIn person profiles or company pages and it returns the posts a search engine has indexed for each one, as flat rows: permalink, author, a text excerpt, and the publish date decoded from the post id. No request is sent to LinkedIn and no cookie or account is used. A result counts…

Parameter	Type	Required	Notes
profile_urls	array	no	LinkedIn person profile URLs, for example https://www.linkedin.com/in/williamhgates. Country subdomains such as uk.linkedin.com are fine. Supply this, company_urls, or both.
company_urls	array	no	LinkedIn company page URLs, for example https://www.linkedin.com/company/microsoft. Supply this, profile_urls, or both.
posted_since	string	no	ISO date or timestamp, for example 2026-08-01. Posts published before this are skipped BEFORE anything is charged. Leave empty to take everything the index holds.

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Gtm Suite or to call it, at any volume.

ATrust score 96 / 100

Release 1.12.0 · scanned 14 Oct 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score96

Findings1 threat · 3 capability

Capabilitymoderate

Coveragesource

Verificationrepo

Surface digestec0232ed59e8983dd32facd7e376fc0c25ac5e15f8c404997675a43ffbc21c15

Score vectorthreat 100 → client 96

Term	Level	What it prices	Points
capability-exposure	moderate	capability blast radius (moderate) — client exposure if the model is manipulated	−3
verification-discount	repo	publisher verification (public source) — no provenance, but the source is public and inspectable	−1
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (21 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.

Tool	Capability tags	Why the tag was assigned
scan_gtm_hiring_signals	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
detect_gtm_tech_stack	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
aggregate_gtm_signals	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
scan_job_board_keywords	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
resolve_linkedin_url	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
score_icp_fit	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
resolve_company_identity	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
enrich_company_firmographics	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
map_company_social_presence	untrusted-inputexternal-sink	untrusted-input: keyword "web_search", declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
get_funding_press_signals	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
get_company_changes	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
detect_ai_tooling	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
fingerprint_outbound_infrastructure	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
track_publication_cadence	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
push_leads_to_sequencer	external-sink	external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
audit_agent_accessibility	untrusted-inputexternal-sink	untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
classify_contact	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
map_company_event_presence	untrusted-inputexternal-sink	untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
resolve_legal_entity	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
monitor_public_awards	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104
capture_linkedin_posts_and_commenters	untrusted-inputexternal-sink	untrusted-input: declares openWorldHint: true (interacts with entities outside the server); external-sink: handler sends an HTTP POST (fetch(https://api.apify.com/v2/acts/${actorPath}/runs?timeout=${ACTOR_RUN_TIMEOUT_SECS}) at build/index.js:104

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

flow-1

Untrusted input can drive an external action even though no sensitive source is exposed.

Supply chain and provenance

Integrityfirst-seen

Surface digestec0232ed59e8983d

Scanned2026-10-14

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.