Apify 上の Mamba Labs の Legal Entity Resolver アクター向けの MCP サーバーです。
企業のドメインを渡すと、その背後にある登録済みの法的エンティティ（法人名、会社番号、管轄、ステータス、LEI、VAT番号）を返します。ドメインごとに1行のフラットなレコード、24フィールドで、Clay や CRM ですぐに使えます。
npx -y @mambalabsdev/mcp-legal-entity-resolver{
"mcpServers": {
"mamba-legal-entity-resolver": {
"command": "npx",
"args": ["-y", "@mambalabsdev/mcp-legal-entity-resolver"],
"env": { "APIFY_TOKEN": "your-apify-token" }
}
}
}Apify トークンは console.apify.com/account/integrations で取得できます。
Related MCP server: Workplace Program Detector MCP Server
resolve_legal_entity企業ドメインを入力として受け取り、その背後にある登録済みの法的エンティティを出力します。
入力 | 型 | 必須 | 備考 |
| string | はい | 単一の企業ドメイン（例: monzo.com）。プロトコルとパスは取り除かれます。 |
| string | いいえ | ドメインの検索をスキップし、この名前で直接レジスタを検索します。すでに法人名が分かっていて、レジスタのレコードだけが必要な場合に使用します。 |
| string | いいえ | ISO-2 の国コード。 |
| enum | いいえ |
|
| boolean | いいえ | 企業自身のページで見つかった VAT 番号を EU VIES サービスで検証し、VIES が保持する名前を返します。レジスタ名との相互チェックとして機能します。デフォルトは |
| enum | いいえ |
|
レジスタの検索エンドポイントはファジー検索であり、常に何かを返します。検索結果の最上位を採用すると、多くの場合、自信満々で間違った会社番号を取得することになります。このアクターは、正規化後に法人名が完全に一致する場合にのみマッチを受け入れます。そのため、10件中10件ではなく、およそ10件中6件のドメインしか解決されず、その6件こそが行動に値するのです。
マッチに基づいて行動する前に、match_method、match_confidence、rejected_candidates を確認してください。厳密性を fuzzy に設定すると、リサーチモードになります。ほとんどのドメインで、自信満々で間違った企業を返すことになります。
照会されるレジスタは3つです: UK Companies House、GLEIF、SEC EDGAR。
解決されたドメインごとに課金され、さらに少額のアクター起動料金がかかります。キャッシュされた結果は、解決済みの企業で90日間、null で7日間保持されます。
料金はアクターの Apify ページに記載されています。このサーバーを実行すると Apify クレジットを消費します。
Give it a company domain and it returns the registered legal entity behind it: legal name, company number, jurisdiction, status, entity type, LEI and VAT number, as one flat row with a full audit trail of what was rejected and why. Three registers are queried: UK Companies House, GLEIF and SEC EDGAR. Register search endpoints are fuzzy and always return something, so by default a record is accepted only when the normalized legal names are identical. That is why roughly 6 domains in 10 resolve rather than 10 in 10, and why a null here is a trustworthy answer rather than a gap. Read match_method, match_confidence and rejected_candidates before acting on a match. Setting match_strictness to fuzzy will hand you a confidently wrong company on most domains and should be treated as a research mode, not a default. This is not a company database and not a credit or risk product. Requires an APIFY_TOKEN and consumes Apify credits. Read only.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | A single company domain, for example monzo.com. Protocol and path are stripped. | |
| skipCache | No | false uses the cache: 90 days for a resolved company, 7 days for a null. true forces a fresh look. Default: "false". | |
| validate_vat | No | Runs any VAT number found on the company's own pages through the EU VIES service and returns the name VIES holds for it, as a cross-check against the register name. Default: true. | |
| max_charge_usd | No | Optional spending cap for this call, in USD, passed to the actor as max_charge_usd. The run stops before any charge that would take it past this amount and keeps every row already charged. Leave empty to rely only on the maximum charge per run set on your Apify account. | |
| legal_name_hint | No | Skips the domain lookup and goes straight to the registers with this name. Use it when you already have the legal name and just want the register record. | |
| match_strictness | No | exact accepts a register record only when the normalized legal names are equal, which is the default and the recommendation. fuzzy returns the best scoring candidate with a confidence below 100 and a warning in rejected_candidates. Register search is fuzzy and always returns something, so fuzzy mode will hand you a confidently wrong company on most domains. Default: "exact". | |
| jurisdiction_hint | No | ISO-2 country code. GB or UK asks Companies House and GLEIF and returns a Companies House number. US asks GLEIF and SEC EDGAR. FR asks the French Sirene register and returns a SIREN. NO asks the Norwegian Brreg register and returns an organisasjonsnummer. Any other code asks GLEIF alone rather than guessing at a register with no adapter. Leave empty to query all five. Narrowing cuts latency, and registers_queried on the row records which were actually asked, so a null is never ambiguous. | |
| sec_requester_name | Yes | Required. Your own name or your company's name. The SEC requires every automated request to EDGAR to identify the requester by name and email, and the actor sends yours, never a default. | |
| sec_requester_email | Yes | Required. Your own working email address. Sent to the SEC with your name in the User-Agent of each EDGAR request, in the form the SEC asks for. Nothing else uses it. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations say readOnlyHint=false, which is surprisingly defensive for a lookup; the description resolves the ambiguity by stating 'Read only' and by disclosing that it consumes Apify credits and requires an APIFY_TOKEN. It goes well beyond annotations with the 6-in-10 resolution rate, the always-returns-something register behavior, the audit trail of rejections, and the fields to read before acting. This is rich behavioral context the structured fields do not carry.
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 core contract (domain in, flat row out) then layers warnings. It is dense but every sentence carries information; the only cost is that the match_method/match_confidence warning and the fuzzy warning slightly overlap.
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 9-parameter tool with no output schema, the description covers inputs, the return shape (flat row with named fields), failure semantics (nulls are meaningful), cost/auth requirements, and the caveats needed to invoke it correctly. Nothing essential is missing.
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 coverage is 100%, so the baseline is 3, but the description adds genuine value beyond the schema: it explains why match_strictness=fuzzy produces confidently wrong results, the default cache semantics for skipCache, and how jurisdiction_hint trades coverage for latency. The legal_name_hint alternative path is only lightly touched.
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 states a precise verb+resource: given a domain, it returns the registered legal entity behind it, and it enumerates the returned fields. It also draws explicit negative boundaries ('not a company database and not a credit or risk product') that no sibling tool supplies. There are no siblings, but the purpose is unmistakable.
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?
It gives clear conditions for the main behavior choice: default exact matching vs fuzzy mode, and warns fuzzy is a research mode, not a default. It also explains the null-is-trustworthy framing. It stops short of stating prerequisites like when a legal_name_hint is preferable, but the core guidance is explicit.
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.
v1.4.0resolve_legal_entity6 fields changedInput schema / additionalPropertiesRemoved value: -falseInput schema / properties / jurisdiction_hint / descriptionPrevious value: -"ISO-2 country code, for example GB or US. Narrows which registers are queried and cuts latency. Leave empty to query every register."New value: +"ISO-2 country code. GB or UK asks Companies House and GLEIF and returns a Companies House number. US asks GLEIF and SEC EDGAR. FR asks the French Sirene register and returns a SIREN. NO asks the Norwegian Brreg register and returns an organisasjonsnummer. Any other code asks GLEIF alone rather than guessing at a register with no adapter. Leave empty to query all five. Narrowing cuts latency, and registers_queried on the row records which were actually asked, so a null is never ambiguous."Input schema / properties / max_charge_usdAdded value: +{
+ "description": "Optional spending cap for this call, in USD, passed to the actor as max_charge_usd. The run stops before any charge that would take it past this amount and keeps every row already charged. Leave empty to rely only on the maximum charge per run set on your Apify account.",
+ "minimum": 0,
+ "type": "number"
+}Input schema / properties / sec_requester_emailAdded value: +{
+ "description": "Required. Your own working email address. Sent to the SEC with your name in the User-Agent of each EDGAR request, in the form the SEC asks for. Nothing else uses it.",
+ "format": "email",
+ "pattern": "^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$",
+ "type": "string"
+}Input schema / properties / sec_requester_nameAdded value: +{
+ "description": "Required. Your own name or your company's name. The SEC requires every automated request to EDGAR to identify the requester by name and email, and the actor sends yours, never a default.",
+ "maxLength": 100,
+ "minLength": 1,
+ "type": "string"
+}Input schema / requiredPrevious value: -[
- "domain"
-]New value: +[
+ "sec_requester_name",
+ "sec_requester_email",
+ "domain"
+]v1.0.0resolve_legal_entityScored across 1 tool
There is only one tool, so there is nothing to confuse it with. Its purpose (domain → registered legal entity) is stated unambiguously, including what it does not do (not a company database, not a risk product).
A single tool named resolve_legal_entity follows a clear verb_noun snake_case pattern. There is no competing convention to clash with it.
The server is deliberately scoped to one operation, and that operation is substantive (multi-register lookup with audit trail). Still, a single tool is thin for a server surface and forces any multi-domain or reverse-lookup workflow to be handled outside it.
The core read path is well covered: resolution, confidence/method metadata, rejected candidates, and multiple registers. Gaps are minor — no batch resolution of many domains and no reverse lookup (name/company number → domain), which an agent would have to loop around.
CompanyLens is a remote MCP server giving AI agents instant access to official company registry data across 19 jurisdictions in Europe, the Americas, and Asia-Pacific. Eighteen read-only tools let you search companies and people, look up officers and beneficial owners, map corporate networks through shared directors, screen names against the UK disqualified directors register, find every company at a registered address, and pull filing history — all from a single connector. Visit our website: https://companylens.io
Remote MCP server to enrich company profiles with structured B2B data and confidence scores.
Apify MCP — run web-scraping Actors and fetch their dataset results.
Identity resolution MCP server for phone/email lookups across 31+ services. Global + India coverage.
