Skip to main content
Glama

Hk Company Search

hk_company_search
Read-onlyIdempotent

Search Hong Kong companies newly incorporated, registered, or renamed on the Companies Registry (香港公司註冊處, cr.gov.hk) since 30 Dec 2024, official open data via data.gov.hk, updated weekly. Match by company name (English or Chinese, substring, case-insensitive; Ltd/Limited, a trailing full stop and & vs and are treated as the same name, and each row says how it matched) or an exact Business Registration (BR) number. Returns each match's BR number, English and Chinese name, company type (Hong Kong local / non-Hong Kong), incorporation-or-registration date, and any name-change date, plus the matching HKEX ticker when the name resolves to a listed stock (joined via the same Yahoo Finance lookup hk_resolve_symbol uses, only attached on a confident name match, never guessed). LIMITATION: this only covers companies newly incorporated, registered, or renamed since 2024-12-30, it is NOT the full historical company register and does NOT return registered address or company status for companies outside that window (Hong Kong publishes no open API for those; only the Companies Registry's paid Cyber Search Centre does). Use for "is there a new HK company called X", "HK BR number for Y", "香港新註冊公司 X".

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "Holdings"
    },
    "name": "hk_company_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
brnNoExact Business Registration (BR) number, e.g. "81129706".
nameNoCompany name substring, English or Chinese, e.g. "HSBC" or "滙豐". Case-insensitive.
typeNoRestrict to Hong Kong local companies ("local") or non-Hong Kong companies registered in HK ("non_hk"). Omit to search both.
limitNoMax matches to return, 1-100 (default 25).
sinceNoOnly search weeks on/after this date (YYYY-MM-DD). Default: last 12 weeks. Earliest possible: 2024-12-30 (the dataset start).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / examples
      Previous value: -[
      -  {
      -    "name": "HSBC"
      -  },
      -  {
      -    "brn": "80846040"
      -  }
      -]New value: +[
      +  {
      +    "name": "Holdings"
      +  },
      +  {
      +    "brn": "80846040"
      +  }
      +]
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, and the description still adds substantive behavior: data provenance (data.gov.hk), weekly refresh cadence, row-level match provenance ("each row says how it matched"), and the conservative ticker-join rule ("only attached on a confident name match, never guessed"). It also discloses what is NOT retrievable for older companies, which materially shapes expectations.

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?

Purpose and matching semantics are front-loaded and the LIMITATION is capitalized and placed before the use cases, which is good ordering. The prose is dense and runs long with parenthetical asides (the Yahoo Finance lookup reference), so a small amount of trimming would help, but nearly every clause carries operational information.

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?

With no output schema, the description fully enumerates returned fields (BR number, English/Chinese name, company type, dates, ticker) and explains the temporal window and its consequences. For a five-parameter, zero-required search tool this leaves nothing an agent needs to call it correctly unstated.

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 a baseline of 3 applies, but the description goes further by defining name-matching normalization rules — substring, case-insensitive, Ltd/Limited, trailing full stop, and & vs and treated as the same — which the schema does not state. It also clarifies the name/BR duality (substring vs exact), though it does not add meaning for since, limit, or type beyond their schema text.

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 description opens with a specific verb and resource ("Search Hong Kong companies newly incorporated, registered, or renamed") and pins the scope to the Companies Registry via data.gov.hk since 2024-12-30. The explicit LIMITATION sentence separates it from a full historical register, so an agent can tell exactly what universe this tool covers.

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

Usage Guidelines4/5

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

It gives concrete when-to-use phrasings ("is there a new HK company called X", "HK BR number for Y", and the Chinese equivalent) and names the boundary case — for registered address or status outside the window, only the paid Cyber Search Centre works. It does not name sibling tools such as hk_company or hk_company_name_changes as alternatives, so routing to a sibling is left to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.