hkex-filing-scraper

# HKEx Filing Scraper

<!-- mcp-name: io.github.simonmak-ascent/hkex-filing-scraper -->

> **An open-source scraper for 25+ years of HKEx regulatory filings** — into any of nine databases, with full-text extraction, graph linking, and a read-only MCP server for AI agents.

![HKEx Filing Scraper — one scraper, many databases](https://raw.githubusercontent.com/simonmak-ascent/hkex-filing-scraper/main/docs/social_preview.png)

[![CI](https://github.com/simonmak-ascent/hkex-filing-scraper/actions/workflows/ci.yml/badge.svg)](https://github.com/simonmak-ascent/hkex-filing-scraper/actions/workflows/ci.yml)
[![MCP Registry](https://img.shields.io/badge/MCP%20Registry-io.github.simonmak--ascent%2Fhkex--filings-4CAF50)](https://registry.modelcontextprotocol.io/v0/servers?search=io.github.simonmak-ascent/hkex-filings)
[![Glama MCP](https://glama.ai/mcp/servers/simonmak-ascent/hkex-filing-scraper/badges/score.svg)](https://glama.ai/mcp/servers/simonmak-ascent/hkex-filing-scraper)
[![GitHub Release](https://img.shields.io/github/v/release/simonmak-ascent/hkex-filing-scraper?color=green)](https://github.com/simonmak-ascent/hkex-filing-scraper/releases)
[![PyPI](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fpypi.org%2Fpypi%2Fhkex-filing-scraper%2Fjson&query=%24.info.version&label=PyPI&color=blue)](https://pypi.org/project/hkex-filing-scraper/)
[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
[![Docs](https://img.shields.io/badge/docs-hkex--listco--updates.ascent--partners.com-blue)](https://hkex-listco-updates.ascent-partners.com/)
[![MCP](https://img.shields.io/badge/MCP-server-blueviolet)](https://hkex-listco-updates.ascent-partners.com/ai-agents/)
[![Ruff](https://img.shields.io/badge/lint-ruff-261230.svg)](https://github.com/astral-sh/ruff)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

## Overview

**The US has EDGAR full-text search. Japan has EDINET. Hong Kong has a search form that returns
one page at a time.** There is no bulk, machine-readable, full-text corpus of HKEx filings. This
builds one.

An open-source Python tool that scrapes 25+ years of Hong Kong Stock Exchange (HKEx)
regulatory filings and ingests them into **any combination of nine databases** — with
full-text and table extraction, chunk-level coverage, optional graph linking, and a
**read-only MCP server** so AI agents can query the corpus or the live site.

<!-- mcp-name: io.github.simonmak-ascent/hkex-filings -->

It speaks the undocumented HKEx JSON API directly, which is faster and more resilient than
driving a browser.

## Vendors & Integrations

**Databases** — nine first-class destinations, in documented popularity order (see the
[support matrix](docs/sinks/README.md)):

- [PostgreSQL](docs/sinks/postgresql.md) — production-grade open-source relational
- [MySQL](docs/sinks/mysql.md) / [MariaDB](docs/sinks/mysql.md) — GPL relational servers, one driver
- [SQLite](docs/sinks/sqlite.md) — zero-server file database, no install needed
- [MongoDB](docs/sinks/mongodb.md) — document database
- [Neo4j](docs/sinks/neo4j.md) — property-graph database
- [ClickHouse](docs/sinks/clickhouse.md) — columnar analytics engine
- [DuckDB](docs/sinks/duckdb.md) — in-process analytical engine
- [SurrealDB](docs/sinks/surrealdb.md) — multi-model graph + document database

**AI clients** — any MCP-capable agent; ready-made configuration for
[Claude, ChatGPT, Cursor, VS Code/Copilot, Gemini CLI, opencode, Manus, and Perplexity](docs/ai-agents.md).

**Available on** — [PyPI](https://pypi.org/project/hkex-filing-scraper/) ·
[Glama](https://glama.ai/mcp/servers/simonmak-ascent/hkex-filing-scraper) ·
[MCP Registry](https://registry.modelcontextprotocol.io/) ·
[hosted gateway](https://hkex-listco-updates.ascent-partners.com/api/mcp).

## Two Ways to Use It

| | **Hosted MCP gateway** | **Local pipeline** |
| --- | --- | --- |
| What | A public endpoint you point an AI agent at | The `hkex-scraper` CLI |
| Setup | None — paste a URL | `pip install` + one environment variable |
| Data | Live from HKEx, nothing stored | Stored in your database(s) |
| Docs | [Live MCP gateway](docs/live-mcp.md) · [AI agent support](docs/ai-agents.md) | [Getting started](docs/getting-started.md) |

![Example: install, scrape filings into SQLite, then query the hosted MCP gateway from an AI agent](https://raw.githubusercontent.com/simonmak-ascent/hkex-filing-scraper/main/docs/assets/demo.svg)

## Use the Hosted MCP Gateway

POST, Streamable HTTP, **no API key**:

```text
https://hkex-listco-updates.ascent-partners.com/api/mcp
```

Four read-only tools: `get_server_info`, `search_filings` (a window of at most 31 days, with
optional stock-code, title, document-type, category, and stock-name filters),
`list_filing_facets` (browse what a window contains), and `get_filing` (downloads one
document and extracts its text and tables).

![Two ways to reach HKEx filings from an AI agent: the hosted MCP gateway or the local stdio server](https://raw.githubusercontent.com/simonmak-ascent/hkex-filing-scraper/main/docs/assets/mcp.png)

Point a client at it — for example opencode:

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "hkex-live": {
      "type": "remote",
      "url": "https://hkex-listco-updates.ascent-partners.com/api/mcp"
    }
  }
}
```

Then ask:

```text
Use hkex-live to list the filings published between 2026-09-01 and 2026-09-18,
then summarise the interim report.
```

Ready-made configuration for Claude, ChatGPT, Cursor, VS Code/Copilot, Gemini CLI, opencode,
Manus, and Perplexity is in [AI agent support](docs/ai-agents.md) — and for a stored corpus,
the [stdio MCP server](docs/mcp.md) exposes a wider tool catalog and is published on
[Glama](https://glama.ai/mcp/servers/simonmak-ascent/hkex-filing-scraper). The gateway is listed
in the [official MCP Registry](https://registry.modelcontextprotocol.io/) as
`io.github.simonmak-ascent/hkex-filings`.

> **Featured on Glama** — the read-only [stdio MCP server](docs/mcp.md) is also published on
> [Glama](https://glama.ai/mcp/servers/simonmak-ascent/hkex-filing-scraper), where Glama scans the
> built server and scores tool-definition quality (currently 4.7/5).

## Quick Start (Local)

```bash
pip install hkex-filing-scraper        # core; SQLite needs no server
pip install "hkex-filing-scraper[all]" # Excel + dotenv + every driver + the MCP server
cp .env.example .env                   # then set DATABASE_TARGET (below)
hkex-scraper --metadata-only --limit 100
```

Optional extras: `excel`, `postgres`, `mysql`, `duckdb`, `mongodb`, `clickhouse`, `neo4j`,
`mcp`, `pdf`, `all`, `dev`.

`DATABASE_TARGET` is an ordered, comma-separated list of sink ids; the order decides which
sink serves reads. To start with no server:

```ini
DATABASE_TARGET=sqlite
SQLITE_PATH=hkex.db
```

`hkex-scraper` runs the full pipeline (metadata + documents + graph); `hkex-scraper
--full-history` covers everything since April 1999. The schema is created automatically.
Full install options and per-sink settings are in [Getting started](docs/getting-started.md).

## Database Support

Every sink is a first-class destination; rows are in documented popularity order. The full
matrix — licenses, capability differences, per-engine notes — is in
[Database sinks](docs/sinks/README.md).

| Sink | Model | License | Extra | Idempotent upsert |
| ---- | ----- | ------- | ----- | ----------------- |
| `postgres` | relational | PostgreSQL License | `postgres` | `ON CONFLICT DO UPDATE` |
| `mysql` / `mariadb` | relational | GPLv2 | `mysql` | `ON DUPLICATE KEY UPDATE` |
| `sqlite` | relational | Public domain | — | `ON CONFLICT DO UPDATE` |
| `mongodb` | document | SSPL¹ | `mongodb` | `update_one(upsert=True)` |
| `neo4j` | graph | GPLv3 (Community) | `neo4j` | `MERGE` |
| `clickhouse` | columnar | Apache-2.0 | `clickhouse` | `ReplacingMergeTree` + read-merge |
| `duckdb` | relational | MIT | `duckdb` | `ON CONFLICT DO UPDATE` |
| `surrealdb` | graph + document | BSL 1.1¹ | — | `UPSERT` / `RELATE` |

¹ Source-available, not OSI-approved — labeled exceptions per
[ADR 0003](docs/adr/0003-sink-support-policy.md).

Valid sink ids, in documented order: `postgres`, `mysql`, `sqlite`, `mongodb`, `mariadb`, `neo4j`, `clickhouse`, `duckdb`, `surrealdb`. Set one variable and the same run feeds every sink:

```ini
# Order sets read precedence.
DATABASE_TARGET=postgres,sqlite
POSTGRES_DSN=postgresql://user:password@localhost:5432/hkex
SQLITE_PATH=hkex.db
```

## How This Compares

Four ways to get HKEx filings, and what each one costs you.

| | This project | HKEXnews web search | Browser automation you write | Licensed HKEx feed |
| --- | --- | --- | --- | --- |
| Bulk export | Yes | No — page-at-a-time | Yes | Yes |
| History to April 1999 | Yes | Yes, manually | Depends on your code | Yes |
| Full text of documents | Extracted from PDF/HTML/Excel | No — you open each file | You build the extractor | Varies by contract |
| Structured tables | Extracted to Markdown | No | You build it | Varies |
| Coverage verification | Per-chunk, auditable | Not applicable | You build it | Vendor SLA |
| Lands in your engine | 9 engines, any combination | No | Whatever you wire up | Usually one format |
| Speed | JSON API, no browser | Manual | Slower — renders pages | Fast |
| Cost | Free, MIT | Free | Your time | Subscription |
| Commercial redistribution | See [docs/legal.md](docs/legal.md) | Restricted | Restricted | Licensed |

If you need licensed, redistributable, SLA-backed data, buy the feed. If you need a complete
local corpus for research, compliance, or RAG, this replaces the pipeline you would otherwise
write yourself.

## How It Works

```mermaid
flowchart LR
    A[HKEx JSON API] --> B[Phase 1: metadata]
    B --> C[Canonical record]
    C --> D{DATABASE_TARGET}
    D --> E[(PostgreSQL)]
    D --> F[(MySQL / MariaDB)]
    D --> G[(SQLite)]
    D --> H