DataSinking
remote (hosted) MCP serverDataSinking is a remote (hosted) MCP server: Full-text Asian financial reports (China, Korea, Japan, Taiwan) as clean Markdown for RAG agents. Connect any MCP client to https://api.datasink.ing/mcp.
Installation
Terminal
claude mcp add --transport http datasinking https://api.datasink.ing/mcp --header "Authorization: Bearer $TOKEN"
Run in your project folder. Add --scope user to use it everywhere.
Claude Desktop
Open Settings → Connectors → Add custom connector, then paste https://api.datasink.ing/mcp.
Cursor & other clients
Add to .cursor/mcp.json or your client's MCP config.
{
"mcpServers": {
"datasinking": {
"type": "http",
"url": "https://api.datasink.ing/mcp"
}
}
}Needs an API key or token in the request headers. Get one from the vendor first.
What you need
- Runtime: Nothing, it's hosted.
- MCP client: Claude Code, Codex, Antigravity, Claude Desktop, Cursor or any other client that speaks MCP over streamable HTTP.
- Credentials: a bearer token or API key from datasink.ing, sent in the Authorization header.
- Environment variables:
DATASINK_API_KEY
Summary
Full-text Asian financial reports (China, Korea, Japan, Taiwan) as clean Markdown for RAG agents.
DataSinking vs similar servers
| Server | Stars | Type | API key | Runtime |
|---|---|---|---|---|
| DataSinking | 18 | Hosted | Yes | None |
| anymd | 942 | Local | No | npm |
| fortress | 665 | Local | Yes | pypi |
| Oya Browser | 327 | Hosted | Yes | None |
| Financial Modeling Prep MCP Server | 149 | Local | Yes | npm |
Questions
Yes. The hosted endpoint expects a token in the Authorization header.
Only an MCP client such as Claude Code, Codex, Claude Desktop or Cursor. DataSinking is hosted, so there is nothing to install.
DataSinking is a remote (hosted) MCP server served at https://api.datasink.ing/mcp.
Run: claude mcp add --transport http datasinking https://api.datasink.ing/mcp --header "Authorization: Bearer $TOKEN"
Run: codex mcp add datasinking --url https://api.datasink.ing/mcp --bearer-token-env-var TOKEN
Similar MCP servers
NameStars
- anymdio.github.SylphxAI/anymd942
- fortressio.github.tiliondev/fortress665
- Oya Browserio.github.OyadotAI/oya-browser327
- Financial Modeling Prep MCP Serverio.github.imbenrabi/financial-modeling-prep-mcp-server149
- WebReaperio.github.alex-on-ai/webreaper148
- Xeroio.github.mindstone/mcp-server-xero12
- World Monitorapp.worldmonitor/mcp87K
- tldrawio.github.tldraw/tldraw51K