Resolves a company domain to its Trustpilot business unit and returns TrustScore, star rating, review counts, one-to-five star breakdown, claimed and verified status, and categories via Trustpilot's Business Units API.
An MCP server that resolves a company domain to its Trustpilot rating, review count and claimed status. It wraps the Mamba Labs Trustpilot Reputation Enricher actor on Apify and returns a Clay-ready flat JSON row to any MCP client.
Related MCP server: mcp-legal-entity-resolver
Give it a company domain and it resolves that company's Trustpilot business unit and returns the TrustScore, review count, star score, the one to five star breakdown, claimed and verified status and categories, through Trustpilot's documented Business Units API. One flat row per company.
This route needs your own Trustpilot API key. Without one every row reports skipped rather than pretending to have looked. The tool keeps four kinds of empty apart: a refused request reports blocked, a domain with no business unit reports not_found, a value nobody could read reports not_extractable, and a source that was never queried reports skipped. G2, Capterra and Glassdoor ship as explicit skipped status columns, so the row shape does not change when a source is added.
All of the lookup runs on Apify. This package is a thin client that calls the actor and hands back the result unchanged.
You need Node.js 18 or newer and an Apify account with an API token.
Add this to your Claude Desktop config:
{
"mcpServers": {
"mamba-review-platform-reputation-enricher": {
"command": "npx",
"args": ["-y", "@mambalabsdev/mcp-review-platform-reputation-enricher"],
"env": {
"APIFY_TOKEN": "your-apify-token"
}
}
}
}Get your token at https://console.apify.com/account/integrations, paste it in, and restart Claude Desktop. The get_trustpilot_reputation tool will be available.
You also need your own Trustpilot API key, free to create at developers.trustpilot.com. It is passed as a tool argument rather than an environment variable, so the model supplies it per call.
Node.js 18 or newer
An Apify account with an API token
Your own Trustpilot API key, free at developers.trustpilot.com. The Business Units API is not open, so this is required.
"Get the Trustpilot rating for mattressonline.co.uk. Here is my Trustpilot key."
"What is the star breakdown for this company on Trustpilot?"
"Look up this domain's Trustpilot reputation and flag it only if it has at least 100 reviews."
"Is this company's Trustpilot profile claimed and verified?"
company_domain (optional): bare company domain, for example stripe.com. Trustpilot business units are keyed on the company website domain, so this is the correct and only lookup key.
company_name (optional): carried through to the output row for joining. The lookup is keyed on the domain, so the name does not change which business unit is returned.
trustpilotApiKey (optional in the schema, required in practice): your own Trustpilot API key, free to create at developers.trustpilot.com. Without a key the tool reports skipped rather than guessing.
minReviewCount (optional): one of none, 10, 50, 100 or 500. It sets rating_is_meaningful on the row. A 5.0 rating from two reviews and a 4.2 from nine hundred are not comparable numbers, and this is the column that says which one you are looking at. It never drops a row and never changes the rating returned.
includeCategories (optional): when true (the default) the Trustpilot categories the business is listed under are returned. They are a cheap proxy for what a company actually sells, which is often not what its homepage says.
sources (optional): which review sources to query. Version 1 serves trustpilot only. G2, Capterra and Glassdoor appear as columns and always report skipped, with the reason on the row. This setting exists so a saved configuration keeps working when a source is added.
skipCache (optional): when false (the default) a successful lookup is cached for seven days and reused. Set true to force a fresh fetch.
The tool returns the actor's flat JSON row for the company, with 31 snake_case fields and no nested objects. trustpilot_status is the field to read before any rating, trustpilot_route and trustpilot_id_source say how the business unit was resolved, and rating_is_meaningful reflects the review count threshold you set. See the Apify Store page for the full output schema.
{
"degraded": false,
"degradation_reason": null,
"company_domain": "mattressonline.co.uk",
"company_name": "Mattress Online",
"trustpilot_business_id": "4992d8e10000640005041a9a",
"trustpilot_url": "https://www.trustpilot.com/review/www.mattressonline.co.uk",
"trustpilot_name": "MattressOnline.co.uk",
"trustpilot_rating": 4.8,
"trustpilot_review_count": 72332,
"trustpilot_stars": 5,
"trustpilot_one_star": 1618,
"trustpilot_two_stars": 768,
"trustpilot_three_stars": 1485,
"trustpilot_four_stars": 5850,
"trustpilot_five_stars": 62611,
"trustpilot_country_code": "GB",
"trustpilot_route": "widget",
"trustpilot_id_source": "homepage_embed",
"trustpilot_claimed_status": "not_extractable",
"trustpilot_is_claimed": null,
"rating_is_meaningful": true,
"trustpilot_status": "ok",
"g2_status": "skipped",
"capterra_status": "skipped",
"glassdoor_status": "skipped",
"coverage": 1,
"fetch_status": "ok",
"run_date": "2026-08-23T06:39:38.824Z"
}TrustScore, star score and total review count
The full one to five star breakdown, not just the average
Claimed and verified status, plus Trustpilot categories
Four kinds of empty, each with its own status, so a refusal is never a zero
G2, Capterra and Glassdoor ship as explicit skipped columns
31 flat snake_case fields, one row per company
This server is a thin client and holds no lookup logic. For the complete input and output reference, pricing, and run history, see the Apify Store page:
https://apify.com/mambalabs/review-platform-reputation-enricher
This server is one of the Mamba Labs GTM Suite MCP servers. Every actor in the suite takes a domain or a company and returns one flat row, so they stack in the same Clay table without reshaping anything. The actor behind this server is the Trustpilot Reputation Enricher, immutable Apify actor ID 3lIqfCt61j4hqE1xz.
Built by Mamba Labs | npm | Apify Store
MIT
Built by Mamba Labs. https://apify.com/mambalabs
Resolve a company domain to its Trustpilot business unit and return the TrustScore, review count, star score, claimed and verified status and categories, through Trustpilot's documented Business Units API. Returns one flat Clay ready row. Requires the CALLER's own Trustpilot API key; without one every row reports skipped rather than pretending to have looked. A refused request reports blocked and a domain with no business unit reports not_found, and those two are never conflated. G2, Capterra and Glassdoor ship as skipped status columns so the row shape does not change when a source is added. Read only; requires an APIFY_TOKEN and consumes Apify credits per call.
| Name | Required | Description | Default |
|---|---|---|---|
| sources | No | Which review sources to query. v1 serves Trustpilot only. G2, Capterra and Glassdoor appear as columns and always report skipped, with the reason on the row, because all three refused every documented route and none publishes an API we can use as documented. This setting exists so a saved configuration keeps working when a source is added. Sent as a string for Clay compatibility. | |
| skipCache | No | When "false" (default) a successful lookup is cached for seven days and reused, which costs you nothing on a repeated run. Set "true" to force a fresh fetch. Sent as a string for Clay compatibility. | |
| company_name | No | Optional. Carried through to the output row for joining. The Trustpilot lookup is keyed on the domain, so the name does not change which business unit is returned. | |
| company_domain | No | Bare company domain, for example stripe.com. Trustpilot business units are keyed on the company website domain, so this is the correct and only lookup key. | |
| minReviewCount | No | Sets rating_is_meaningful on the row. A 5.0 rating from two reviews and a 4.2 from nine hundred are not comparable numbers, and this is the column that says which one you are looking at. It never drops a row and never changes the rating returned. Sent as a string for Clay compatibility. | |
| trustpilotApiKey | No | YOUR OWN Trustpilot API key, free to create at developers.trustpilot.com. REQUIRED: the Business Units API is not open, so without a key this actor reports skipped rather than guessing. Marked secret, so the value never renders on this page. | |
| includeCategories | No | When "true" (default) the Trustpilot categories the business is listed under are returned. They are a useful cheap proxy for what a company actually sells, which is often not what its homepage says. Sent as a string for Clay compatibility. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnly/idempotent annotations, the description discloses failure modes ('blocked' vs 'not_found' are never conflated), the skipped behavior without an API key, stable row shape across sources, and Apify credit consumption. This gives the agent accurate expectations for side effects and error handling.
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 front-loaded with the primary function, then moves to output shape, prerequisites, error semantics, and cost. Each sentence carries distinct information and the length is justified by the tool's nuanced behavior.
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 supplies the return shape and key statuses, while the input schema handles parameter details. The combination fully covers expected inputs, outputs, failure states, and operational requirements for an agent to invoke it correctly.
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?
The input schema already covers all seven parameters with 100% description coverage, so the description does not need to repeat parameter details. It adds only high-level context (e.g., API key requirement and source limitations) rather than new per-parameter semantics, which keeps it at the baseline 3.
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 opens with a specific verb+resource: 'Resolve a company domain to its Trustpilot business unit' and enumerates returned fields (TrustScore, review count, star score, claimed/verified status, categories). It also adds the output shape ('one flat Clay ready row'), so an agent knows exactly what this tool produces.
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?
Although there are no sibling tools, the description gives clear when-to-use context: it is for Trustpilot reputation from a domain, and it explicitly says G2, Capterra and Glassdoor are not queried and always report skipped. It also sets the prerequisite of the caller's own Trustpilot API key and warns that without one rows report skipped.
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.
v1.0.0get_trustpilot_reputationScored across 1 tool
With only one tool, there is no possibility of confusing it with another tool. Its sole purpose — resolving a domain to Trustpilot reputation data — is clearly described.
The single tool name follows a clear get_<source>_<data> convention and reads consistently with standard API naming. There are no other tools to conflict with the pattern.
One tool is on the thin side for a server named as a review-platform reputation enricher, especially since G2, Capterra, and Glassdoor are only represented as skipped statuses. However, the one tool is non-trivial and performs a complete Trustpilot lookup, so the count is borderline rather than extreme.
The tool covers Trustpilot reputation retrieval well, but the server's broader reputation-enrichment scope is not met: G2, Capterra, and Glassdoor are explicitly not fetched, only marked as skipped. An agent needing reputation data from those platforms would hit a dead end.
Remote MCP server to enrich company profiles with structured B2B data and confidence scores.
MCP server for Tomba email finder, verification, and contact enrichment API
Apify MCP — run web-scraping Actors and fetch their dataset results.
Remote MCP server for hotel rate monitoring, parity checks, and pricing intelligence via Apify.
