Influencer Lead List Builder MCP Server

Build an Influencer Lead List End to End

build_influencer_lead_list

Read-onlyIdempotent

Turn keywords or handles into influencer lead lists in one call: find creators, read profiles, check link-in-bio pages, then return emails, agencies, and niches.

Instructions

Runs the three stages of the suite in one call: find creators by keyword or curated niche, read each profile, then follow the link in bio page. Returns one flat row per creator carrying handle, profile URL, display name, follower count, a stable creator_id and the method that produced it, the public business email, a manager email, a matched talent agency, newsletter status and the platform behind it, and what the creator sells. Start from keywords or a niche to discover creators, or hand it handles you already hold to skip discovery. Skipping the link check stops after the profile read. Every row carries row_status and error_reason, and a creator dropped by the country filter says so rather than disappearing. Charges $0.002 per run, then $0.007 per creator found, $0.006 per profile read, and $0.008 per link check, plus $0.004 per headless browser render, $0.005 per website email scan, $0.003 per agency match, and $0.01 per Instagram bio fetch when those steps run. The AI check uses your own Anthropic or OpenAI key and is billed by them. Contributes the public records in its rows to a shared creator pool, free and on by default; contribute_to_shared_pool explains it and turns it off. A run that does not succeed is returned as an error with its run ID and status. Use it when you want discovery, profile, and link data in one call; when you only need one stage, the single stage tool is cheaper. Requires an APIFY_TOKEN and consumes Apify credits. Read only.

Input Schema

Name	Required	Description
`mode`	No	Default in_process. sub_actors calls the Influencer Finder, the Influencer Profile Scraper, and the Link in Bio Scraper and Newsletter Detector by Actor ID as runs on your account, so each stage bills its own events and its own actor-start. in_process runs the same three stages inside this actor and charges the same stage events here. A complete row costs $0.021 either way, plus the add-ons you turn on.
`niche`	No	Loads a curated set of search keywords for the niche (about 60 per niche, measured in the September 2026 pre-research). `max_keywords_per_niche` caps how many are used. Leave as custom to search only your keywords. Default: "custom".
`handles`	No	One per line. A profile URL on any supported platform (https://www.tiktok.com/@name, https://www.instagram.com/name/, https://www.youtube.com/@name, a Pinterest, Twitch, or Threads profile, an Apple Podcasts show page, or a Spotify show), or platform:@handle (tiktok:@name). A bare @handle needs `platforms` and is looked up on each listed platform. One entry is a single run; a list is a batch. Duplicates are removed before any fetch.
`us_only`	No	Launch scope is US creators. A row whose country_guess is a known non US country is returned as an error row saying so. Rows with no country signal are kept. Uncheck to keep every country. Default: true.
`ai_check`	No	Off by default. When on, a model reads the rule classifier's evidence and rules on each row. Runs only with your own key in `ai_api_key`; the actor never uses a Mamba Labs key and never logs yours. Default: false.
`keywords`	No	Search phrases, one per line, for example "budget travel" or "meal prep coach". Each keyword is searched on each platform. Use `niche` instead to load a curated keyword set.
`platforms`	No	Which platforms to search, and which platforms a bare @handle is looked up on. A full profile URL carries its own platform and ignores this. Supported: TikTok, Instagram, YouTube, Pinterest, Twitch, Threads, and podcasts. Not X, not Facebook pages, not LinkedIn.
`ai_api_key`	No	Your own model API key. Used only when `ai_check` is on. Never stored, logged, or written to a row.
`batch_size`	No	Rows fetched at once. Leave empty for the measured per platform default; the measurement is in the README. Higher is faster and, above the measured point, loses rows.
`skip_links`	No	Off by default. On: discovery and profile only. The link-in-bio page is never fetched, so no links-checked, browser-render, website-scan, or agency-match event is charged and the links, newsletter, and sells columns stay null. Default: false.
`ai_provider`	No	Which API the key belongs to. Default: "anthropic".
`follower_max`	No	Drop creators whose follower count is known and above this. Default: 500000.
`follower_min`	No	Drop creators whose follower count is known and below this. A creator whose count the search did not show is kept, so a later profile read can fill it. Default: 5000.
`max_creators`	No	Hard cap on rows returned, so a broad niche cannot run away. Default: 200.
`match_agencies`	No	Matches the domain of a manager or business email against the bundled talent agency list and fills agency_name, agency_domain, and agency_match_method. Charged per matched row (event agency-match). Default: true.
`twitch_app_token`	No	Optional. An app access token for your Twitch client id (client credentials flow). Used only for Twitch reads, never stored or logged.
`twitch_client_id`	No	Optional. Your own registered Twitch application client id. With `twitch_app_token` the Twitch reads use the official Helix API instead of the public web endpoint. Never a Mamba Labs credential.
`escalate_on_block`	No	On by default. A profile fetch that comes back as a bot detection page is retried once over the residential proxy. On Instagram the bio, bio link, and following are read from the profile page over residential when the embed and the datacenter API did not carry them, and a page that comes back readable charges instagram-bio-fetch ($0.010). Uncheck it to never pay that event: a blocked profile then returns a labeled error row, and Instagram rows keep an empty bio and bio link on about half of the reads. Default: true.
`max_keywords_per_niche`	No	How many keywords from the niche set to search. 1 to 60. Default: 10.
`scan_website_for_email`	No	Off by default. For creators with their own website (not a link-in-bio page), reads the home, contact, and about pages and the footer for an email and records where it was found. Charged per creator scanned (event website-scan). Default: false.
`render_unreadable_pages`	No	Off by default. Some link-in-bio pages (Stan Store, linkin.bio, Typeform shells) return an empty shell to a plain fetch and are classified unknown_fetch_failed. Turn this on to render them in a headless browser. Charged per page rendered (event browser-render) to cover the browser compute. Default: false.
`max_creators_per_keyword`	No	Cap per search. Search engines honor the site: filter for the first page or two only, so 20 to 30 per keyword with more keywords beats deep paging. Default: 20.
`contribute_to_shared_pool`	No	On by default. Contributes the public records this run finds to a shared creator and agency pool that all users of this actor read from, so a later run reads what this one found. Only public data already in the returned rows is sent, never your Apify account, your input list, or your API keys, and a contribution is not charged. Set false to read the pool and write nothing. Default: true.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.1.2Oct 14, 2026

addedInput schema / properties / contribute_to_shared_pool

Added value: +{
+  "description": "On by default. Contributes the public records this run finds to a shared creator and agency pool that all users of this actor read from, so a later run reads what this one found. Only public data already in the returned rows is sent, never your Apify account, your input list, or your API keys, and a contribution is not charged. Set false to read the pool and write nothing. Default: true.",
+  "type": "boolean"
+}

changedInput schema / properties / mode / description

Previous value: -"Leave empty for the default. sub_actors calls the Influencer Finder, the Influencer Profile Scraper, and the Link in Bio Scraper and Newsletter Detector by Actor ID as runs on your account, so each stage bills its own events and its own actor-start. in_process runs the same three stages inside this actor and charges the same stage events here. A complete row costs $0.021 either way, plus the add-ons you turn on."New value: +"Default in_process. sub_actors calls the Influencer Finder, the Influencer Profile Scraper, and the Link in Bio Scraper and Newsletter Detector by Actor ID as runs on your account, so each stage bills its own events and its own actor-start. in_process runs the same three stages inside this actor and charges the same stage events here. A complete row costs $0.021 either way, plus the add-ons you turn on."

First observedv1.0.0Sep 22, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover read-only/idempotent/open-world, but the description adds substantial traits they cannot express: a full per-event price model, the fact that rows are contributed by default to a shared creator pool (a real external side effect), auth requirements (needs an APIFY_TOKEN and consumes Apify credits), and the failure contract (failed runs return an error with run ID and status; dropped rows carry row_status/error_reason). The default pool contribution in particular is a side effect an agent would otherwise not expect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The three-stage capability and output columns are front-loaded, and the remaining length is justified by 23 parameters and the absence of an output schema. The long pricing enumeration is dense but decision-relevant for a metered tool, though it could be tightened. Overall efficient for the complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 23-parameter, no-sibling, no-output-schema tool, the description covers what it does, the entry modes, the returned row semantics, the error contract, cost implications, auth, and the shared-pool side effect. An agent has everything needed to call it correctly and predict the outcome.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the per-parameter baseline is 3, but the description adds genuine cross-parameter behavior the schema does not: skipping the link check stops the pipeline after the profile read, the country filter emits a labeled row instead of silently dropping creators, and full profile URLs ignore the platforms list. These interactions raise it above the schema-only floor.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence names a specific verb (Runs), the composed resource (the three stages of the suite), and enumerates exactly what each stage does (find creators, read profiles, follow link-in-bio). It also lists the returned columns, so an agent knows the shape of the result without opening the schema. No siblings exist, but the purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the entry paths explicitly ('Start from keywords or a niche..., or hand it handles you already hold to skip discovery') and the core routing rule ('Use it when you want discovery, profile, and link data in one call; when you only need one stage, the single stage tool is cheaper'). It also states the cost consequence of skipping the link check. When and when-not are both covered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools

build_influencer_lead_listA