Use the single find_influencers MCP tool to discover influencers by keyword or curated niche across major creator platforms and return filtered creator rows.
Search TikTok, Instagram, YouTube, Pinterest, Twitch, Threads, and podcasts.
Search with custom keywords or curated niches: custom, personal_finance, business_marketing, health_fitness, beauty_skincare, parenting_family, food_cooking, travel, tech_ai.
Limit niche keywords (1–60), results per keyword, total creators, and batch size.
Filter by follower range (follower_min default 5000, follower_max default 500000); unknown follower counts are kept.
Get one flat row per creator per platform with handle, profile URL, display name, follower count, source keyword/search, stable creator_id, similar creators from the same keyword cluster, row_status, and error_reason.
Discovery only: does not read bios, emails, or link-in-bio pages.
Read-only; requires APIFY_TOKEN and Apify credits. Pricing: $0.001 per run plus $0.007 per creator returned; no creators means only the run-start charge.
us_only is accepted but has no effect on discovery (country_guess is null).
No inputs are required; unusable input returns a row with row_status and error_reason instead of failing.
Allows discovering Instagram influencers by keyword or niche, returning handles, profile URLs, and follower counts.
Allows discovering Pinterest influencers by keyword or niche, returning handles, profile URLs, and follower counts.
Allows discovering Threads influencers by keyword or niche, returning handles, profile URLs, and follower counts.
Allows discovering TikTok influencers by keyword or niche, returning handles, profile URLs, and follower counts.
Allows discovering Twitch influencers by keyword or niche, returning handles, profile URLs, and follower counts.
Allows discovering YouTube influencers by keyword or niche, returning handles, profile URLs, and follower counts.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Influencer Finder MCP Server find budget travel influencers on TikTok with 10k+ followers"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for the Mamba Labs Influencer Finder actor on Apify.
Keywords or a curated niche in, influencer handles out, one flat row per creator per platform.
npx -y @mambalabsdev/mcp-creator-finder{
"mcpServers": {
"mamba-creator-finder": {
"command": "npx",
"args": ["-y", "@mambalabsdev/mcp-creator-finder"],
"env": { "APIFY_TOKEN": "your-apify-token" }
}
}
}Get an Apify token at console.apify.com/account/integrations.
Related MCP server: Influship MCP
find_influencersFind influencers by keyword or niche across seven creator platforms, with follower counts.
Input | Type | Required | Notes |
| array | no | Search phrases, one per line, for example "budget travel" or "meal prep coach". Each keyword is searched on each platform. Use |
| string | no | Loads a curated set of search keywords for the niche (about 60 per niche, measured in the September 2026 pre-research). |
| integer | no | How many keywords from the niche set to search. 1 to 60. Default |
| array | 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. |
| integer | 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 |
| integer | no | Hard cap on rows returned, so a broad niche cannot run away. Default |
| integer | 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 |
| integer | no | Drop creators whose follower count is known and above this. Default |
| boolean | no | Launch scope is US creators. Discovery carries no country signal, so country_guess is null on every row of this actor and this field changes nothing here. It is accepted so the same input runs unchanged on the Influencer Lead List Builder. Default |
| integer | 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. |
| integer | no | Wall time allowed for each keyword on each platform, in seconds. A hung search page is given up at the budget, so a full niche set finishes as a SUCCEEDED run. 10 to 600. Default |
| string | no | Runs the search engine queries from this country so results lean to creators there: |
| boolean | 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. Only public data already in the returned rows is sent, and a contribution is not charged. Set false to read the pool and write nothing. Default |
Nothing is required. Influencer Finder answers a run with no usable input with a row carrying row_status and error_reason rather than failing, and the tool mirrors that.
Influencer Finder is pay per event on Apify. Every price below is flat across every tier: FREE, BRONZE, SILVER, GOLD, PLATINUM, and DIAMOND.
Event | Charged for | Price | Fires when |
| Actor start | $0.001 | Once per run, on start. Covers the run overhead. |
| Apify actor start | not charged | Apify's synthetic start event. This actor prices its own |
| Creator found | $0.007 | Once per creator row returned by keyword or niche discovery with a handle and a profile URL. A search that returns nothing charges nothing. |
Every row carries row_status and error_reason. A creator the actor could not read comes back as a row saying why, not as a gap in the list, so an absence is readable rather than inferred. Filter on row_status before loading a table.
The run contributes the records it finds to a shared creator and agency pool that all users of this actor read from. What one run finds, the next run can read.
The toggle is contribute_to_shared_pool. It is on by default. Set it to false and the run still reads the pool and writes nothing to it.
What this actor contributes. The creator ID, platform, and handle of every creator it finds. No profile detail, because this actor reads none.
Only public data that is already in your own output. Every field written to the pool is a field this run returned to you, read from a page the platform or the creator publishes to anyone without a login. Nothing from your Apify account, your input list, your API keys, or your own notes is sent. A contribution never deletes anything from the pool.
What a contribution is labeled with. The actor ID, the run ID, the pool key issued to the actor build, and a hash of the calling IP address, used for the rate limit and nothing else. Your Apify account and your user ID are not recorded.
Contributing is free. No event is charged for a write to the pool. If the pool is unreachable the run finishes as normal, the rows are dropped, and the run log says so.
Actor ID tpkedmloIIWtXx6sg. The wrapper calls the actor by that immutable ID rather than by its Store slug, so a Store rename never breaks it.
Actor | Actor ID | MCP server |
| ||
| ||
| ||
| ||
| ||
|
Built by Mamba Labs.
Searches TikTok, Instagram, YouTube, Pinterest, Twitch, Threads, and podcasts for creators matching your keywords or one of eight curated niche keyword sets, then filters them to a follower range. Returns one flat row per creator per platform with handle, profile URL, display name, follower count, the search that found them, a stable creator_id, and similar creators from the same keyword cluster. Discovery only: it does not read bios, emails, or link in bio pages, which is what Influencer Profile Scraper and Link in Bio Scraper and Newsletter Detector do. Every row carries row_status and error_reason, so an absence is readable rather than silent. Charges $0.001 per run plus $0.007 per creator returned; a search that returns nothing charges the run start only. Requires an APIFY_TOKEN and consumes Apify credits. Read only.
| Name | Required | Description | Default |
|---|---|---|---|
| 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". | |
| us_only | No | Launch scope is US creators. Discovery carries no country signal, so country_guess is null on every row of this actor and this field changes nothing here. It is accepted so the same input runs unchanged on the Influencer Lead List Builder, where it acts at the profile stage. Default: true. | |
| 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. | |
| 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. | |
| 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. | |
| max_keywords_per_niche | No | How many keywords from the niche set to search. 1 to 60. Default: 10. | |
| 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. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds substantial behavioral detail beyond these: it explains the flat row format, that every row carries row_status and error_reason for silent failure readability, the exact pricing model ($0.001 per run plus $0.007 per creator), and the APIFY_TOKEN requirement. It also explicitly says 'Read only,' consistent with the annotations. No contradiction found.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficiently organized: it leads with the core purpose, then the output shape, then exclusions, then error handling, then pricing, then auth. Every sentence contributes new information with no redundancy or fluff. The length is justified by the complexity of the tool (10 parameters, multi-platform, pricing, and exclusions). It is front-loaded with the most critical decision-relevant facts.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 10 parameters, no output schema, and no sibling tools, the description is remarkably complete. It covers the purpose, the exact output fields (handle, profile URL, display name, follower count, search term, creator_id, similar creators), what it does not do, error handling, pricing, auth requirements, and read-only nature. An agent has everything needed to decide when to call it and to interpret its results. There are no significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and each parameter has a detailed description in the schema, including defaults, ranges, and behavioral notes (e.g., us_only does nothing here, batch_size loses rows above measured point). The tool description itself does not add parameter-specific semantics beyond what the schema already provides. Since the schema carries the full burden, a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches multiple platforms for creators based on keywords or niche keyword sets, then filters by follower range. It explicitly names the platforms and the output structure. It also distinguishes itself from related tools (Influencer Profile Scraper, Link in Bio Scraper, Newsletter Detector) by stating what it does not do, so an agent can tell it apart even without sibling definitions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage context: it is 'Discovery only' and explicitly lists what it does not do, naming the alternatives that do those things. It also mentions that it requires an APIFY_TOKEN and consumes Apify credits, which is essential for invocation. This gives clear when-to-use and when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0find_influencersScored across 1 tool
Only one tool exists, so there is no possibility of confusion. The tool's purpose is clearly stated and references other services for adjacent functionality, further removing ambiguity.
The single name 'find_influencers' follows a clear verb_noun convention. Without additional tools, there is no inconsistency to flag.
One tool is on the low end of the scale; however, the tool is well-designed and the server explicitly scopes itself to discovery only. It still feels thin compared to a typical MCP server, so a middle score is appropriate.
For the stated discovery-only purpose, the tool covers search across multiple platforms, keyword sets, follower filtering, and stable IDs. It doesn't claim to provide profiles or contact info, so there are no major missing operations within its scope, though some minor enhancements like sorting or pagination could be useful.
Find and analyze influencers with creator search, lookalikes, profiles, posts, and transcripts.
Find Instagram creators and leads by niche, city, follower range or lookalike accounts.
Creator discovery & analytics across YouTube, Instagram, TikTok (30M+) + brand/sponsor intel.
AI influencer search on TikTok, Instagram, YouTube. Deinai MCP token required; credits per result.
