Name: New Hire Finder
Author: Mamba Labs

New Hire Finder MCP

Find people who started a matching role at a company inside a lookback window.

Grade A Local · stdio API key 1 tool v1.0.0

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

96/100

trust score

tool declared

local

runs on your machine

—

downloads a day

What it does

Find people who started a matching role at a company inside a lookback window.

Quickstart

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

# 2 — ask your agent for something these tools do
#   find_new_hires

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

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

Publisher

Mamba Labs57 servers

7 categories · publishing since 2026

All 57 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 New Hire Finder 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 new-hire-finder-mcp '--' npx -y @mambalabsdev/mcp-new-hire-finder

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

1 tool, 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

Find people who started a role matching your titles at a company inside a lookback window. Give company_domain (or company_domains), target_titles, and lookback_months. Returns one flat, Clay-ready JSON row per person with name, profile URL, title, start month, prior role, move type (new hire,…

Parameter	Type	Required	Notes
company_domain	string	no	One company domain, for example zapier.com. Use this or Company domains (batch); both are merged.
company_domains	array	no	A list of company domains. Each company gets its own summary row.
company_name	string	no	Optional, single company runs only. Leave empty and the name is read from the homepage.
target_titles	array	no	Title phrases to match, for example marketing, head of content, editor. A title matches when it contains every word of a phrase as a whole word. Also sent to Prospeo and web search as the title filter
seniority	array	no	Optional. Keep only these seniority levels.
departments	array	no	Optional. Keep only these departments.
exclude_titles	array	no	Optional. Drop any title that contains one of these phrases, for example intern.
expand_title_synonyms	boolean	no	Also match a short synonym list (marketing also matches growth, brand, demand generation). Off by default, because every row is charged.
lookback_months	string	no	How many calendar months back to look, including this month. 1 to 24, default 6. 6 in October means May to October. Typed as text so Clay can send it.
move_types	array	no	Which moves to return and charge. new_hire is a person who came from another employer. promotion is a new role at the same employer. unknown is a hire announcement with no work history. Default new_hi
include_year_only	boolean	no	Also return people whose start is known only to the year and could fall inside the window. They are charged like any row. Off by default.
people	array	no	People you already hold, with role histories. Each item: person_name, company_domain, profile_url (optional), and roles, a list of {title, company_name, start (YYYY-MM), end (YYYY-MM or null)}. The sa
sources	array	no	Routes to run. Default all. buyer_data is your people list; prospeo and web_search run only with your key; news, newsroom, and team_pages are free.
prospeo_api_key	string	no	Your own Prospeo key. Gives the work history behind start month and move type. One Prospeo credit per search page of 25 people and one per person enrichment, billed by Prospeo to you. Never stored. Yo
web_search_provider	string	no	Which of your search keys to use. auto takes the first key present: Serper, then SerpApi, then Exa.
serper_api_key	string	no	Your own Serper.dev key for web search. One search per company by default. Search results carry no start date, so they are dated with your Prospeo key or counted as undated. Your own key, sent as a ru
serpapi_api_key	string	no	Your own SerpApi key for web search. A different vendor from Serper. Your own key, sent as a run input; never stored by the actor.
exa_api_key	string	no	Your own Exa key. Exa people search returns work histories with start months, so its results need no enrichment. Your own key, sent as a run input; never stored by the actor.
max_people_per_company	string	no	Most person rows to return per company, newest starts first. 1 to 100, default 25.
max_search_queries_per_company	string	no	Web search queries per company on your key. 1 to 4, default 1.

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 New Hire Finder or to call it, at any volume.

ATrust score 96 / 100

Release 1.0.0 · scanned 15 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 · 1 capability

Capabilitymoderate

Coveragesource

Verificationrepo

Surface digest35e424ac1e5f8fa719b2fc2b81af5413850d1a2b2632785915dce8a69dde7540

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 (1 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
find_new_hires	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:80

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 digest35e424ac1e5f8fa7

Scanned2026-10-15

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.