Enables searching Google for manufacturers, wholesalers, and distributors based on a product and country, then checking company websites to identify relevant suppliers.
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., "@Manufacturer and Supplier Finder MCP Server Find 20 cast iron cookware manufacturers in the United States."
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.
An MCP server for the Mamba Labs Manufacturer and Supplier Finder actor on Apify. Give it a product and a country. It searches Google for manufacturers, wholesalers, and distributors, reads each company's own website, and returns only the companies whose pages say they make, wholesale, or distribute the product, with the quoted text and the page as evidence.
Related MCP server: OpenDirectories MCP Server
Directories, marketplaces, and social networks are never returned. Each candidate site is checked by the Mamba Labs Website Phrase and Business Model Classifier, which the actor runs on your Apify account. When nothing qualifies, one free summary row says how many sites were found and checked. All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.
You need Node.js 18 or newer and an Apify account with an API token.
Add this to your Claude Desktop config (claude_desktop_config.json), Cursor, or any MCP client:
{
"mcpServers": {
"mamba-manufacturer-supplier-finder": {
"command": "npx",
"args": [
"-y",
"@mambalabsdev/mcp-manufacturer-supplier-finder"
],
"env": {
"APIFY_TOKEN": "your-apify-token"
}
}
}
}Restart the client. The find_suppliers tool appears.
Node.js 18 or newer.
An Apify API token from console.apify.com/account/integrations, set as APIFY_TOKEN. The server lists its tool without a token; a call needs one.
"Find 20 cast iron cookware manufacturers in the United States."
"Which UK wholesalers sell organic coffee beans? Show me the evidence from their sites."
"Find private label skin care manufacturers in Germany."
find_suppliers. One tool. Example arguments:
{
"product": "corrugated boxes",
"country": "US",
"role": "manufacturer",
"max_results": "20"
}Every buyer facing input of the actor, unchanged. Omitted inputs take the actor's own defaults. Numbers and booleans are sent as strings.
Input | Type | Description |
| string | What the suppliers make or sell. Required |
| string | Two letter code, 20 countries. Default US |
| string | any (default), manufacturer, wholesaler, or distributor |
| string | 1 to 100. Default 20 |
| string | true (default) or false |
| array | Up to 5 extra search words |
| array | Domains never to return |
| string | Optional cap on the whole run, website checks included |
Pay per event on Apify, billed to your Apify account. Prices in USD.
Event | Free plan | Bronze | Silver | Gold |
| $0.025 | $0.02375 | $0.0225 | $0.02125 |
| $0.001 | $0.001 | $0.001 | $0.001 |
Website check by the classifier ( | $0.0045 | $0.004275 | $0.00405 | $0.003825 |
Classifier start ( | $0.0005 | $0.0005 | $0.0005 | $0.0005 |
About 2 sites are checked for each supplier returned. A summary row is free, and a site that cannot be read is not charged.
The actor needs no key and holds none. Proxy and Google search traffic add nothing to your price: Mamba Labs pays the platform costs of the run.
apify.com/mambalabs/manufacturer-supplier-finder
MIT. See LICENSE.
Find manufacturers, wholesalers, and distributors for a product in one of 20 countries. Give product (for example cast iron cookware) and optionally country, role, and max_results. The actor searches Google, checks each company's own website with the Mamba Labs Website Phrase and Business Model Classifier, and returns one row per supplier: company_name, domain, website_url, roles_detected, product_evidence_text and role_evidence_text quoted from the site with their page URLs, and a 0.6 to 0.95 confidence. Directories, marketplaces, and social networks are never returned. When nothing qualifies, one free summary row says why. A run that does not succeed is returned as an error with its run ID. Read-only; requires an APIFY_TOKEN; Apify charges per supplier returned plus the classifier's price per site checked.
| Name | Required | Description | Default |
|---|---|---|---|
| role | No | Supplier type to search for and return. Default any. | |
| country | No | Two letter country code to search in. Default US. | |
| product | Yes | What the suppliers make or sell, for example cast iron cookware. | |
| max_results | No | Most supplier rows to return, 1 to 100. Default 20. About twice this many company sites are checked. | |
| extra_keywords | No | Up to 5 extra search words, for example private label. | |
| max_charge_usd | No | Optional cap on the whole run, website checks included. | |
| exclude_domains | No | Company domains never to return. | |
| require_product_mention | No | true (default): return a company only when its own pages name the product. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the annotations by disclosing the internal pipeline (Google search plus the Mamba Labs Website Phrase and Business Model Classifier), the exact return shape, the 0.6-0.95 confidence band, the free summary row on empty results, error behavior with run ID, APIFY_TOKEN requirement, and the per-supplier plus per-site pricing model.
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?
Purpose is front-loaded in the first sentence and most sentences carry operational weight (exclusions, empty-result behavior, auth, billing). The enumeration of every return field in prose is somewhat dense for a single paragraph, but justified given there is no output schema.
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?
With no output schema, the description must carry return semantics, and it does so by listing the per-supplier fields, quoting conventions, confidence range, and the fallback summary row. It also covers auth, cost, and failure modes, so an agent has everything needed to call and interpret it.
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%, so the schema already documents role, country, product, max_results, extra_keywords, max_charge_usd, exclude_domains, and require_product_mention. The description reinforces only a subset (product example, country/role/max_results) and adds a hint that about twice max_results sites are checked, which is already in the schema. Baseline 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?
States a specific verb and resource set ('Find manufacturers, wholesalers, and distributors for a product') and constrains scope to one of 20 countries. An agent immediately knows what it produces and how it differs from a generic company-search tool. No siblings exist, so no differentiation is needed.
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?
Explains how to invoke it ('Give product ... and optionally country, role, and max_results') and defines implicit boundaries via the exclusion note that directories, marketplaces, and social networks are never returned. It lacks an explicit 'use this when / not when' statement, but with no sibling tools there is little to route against.
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_suppliersSearch verified U.S. manufacturers with provenance, freshness, and live directory statistics.
Find suppliers ranked for fit across customs records, catalogues and directories
Verified, long-tail company search: describe what you want, get an LLM-verified company shortlist.
Local business leads from Google Maps in any country: phone, website, email and socials, website audit, lead score and AI-written outreach, with a businesses-without-a-website filter. Runs on Apify, $0.03 per lead.
