DataSinking vs Flox MCP

A side-by-side look at the DataSinking and Flox MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

DataSinking logoDataSinkingFinance & Fintech · Local subprocess (stdio)Full-text Asian financial reports (China, Korea, Japan) as clean Markdown — 6 tools for RAG agents.67GreatAuth: api key requiredFlox MCP logoFlox MCPFinance & Fintech · Local subprocess (stdio)MCP server for the FLOX trading systems framework. 30 tools to run backtests, scaffold strategies, validate for lookahead bias, place orders, query PnL via Claude/Cursor. C++23 core with Python/Node/Codon/QuickJS strategy bindings. Same code from backtest to live (CcxtBroker or native connectors). Install: pip install flox-mcp.65GreatAuth: no auth required

Verdict: choose DataSinking for finance & fintech work as a local process; choose Flox MCP for finance & fintech as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

DataSinking logoChoose DataSinking when

  • You need dedicated capabilities in the Finance & Fintech domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: API key required.
  • You have the keys it needs: DATASINK_API_KEY.
  • You want tools like list_exchanges, list_stocks, list_reports.
Explore DataSinking

Flox MCP logoChoose Flox MCP when

  • You need dedicated capabilities in the Finance & Fintech domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: No auth required.
  • You want tools like list_indicators, lookup_error_code, list_capi_functions.
Explore Flox MCP

Feature & specification comparison

Rows where the two servers differ are marked.

SpecDataSinking logoDataSinkingFlox MCP logoFlox MCP
CategoryFinance & FintechFinance & Fintech
Quality signal67/100 · Great65/100 · Great
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Local subprocess (stdio)
AuthAPI key requiredNo auth required
PricingNot declaredFree
Required env varsDATASINK_API_KEYNone listed
Verified ownerCommunity listingCommunity listing
GitHub stars21228
Directory activity 1 views 0 installs 0 upvotes 5 views 0 installs 0 upvotes
Tools613

Tools & capabilities

DataSinking tools 6

  • list_exchangesList the exchanges DataSinking covers. Returns exchange codes (nyse / nasdaq / cboe / sse / szse / bj / jpx / ksc / koe / knx / twse / tpex / lse) with the number of reports available per exchange. Call this first to discover coverage. Sources: US = SEC EDGAR, A-shares = cninfo.com.cn, Japan = EDINET, Korea = DART, Taiwan = MOPS, UK = FCA NSM.
  • list_stocksList the stocks on one exchange, including the report count per company.
  • list_reportsList a company's reports — metadata only (id, title, period), no body text. Each item carries a `source` field naming the official disclosure platform; keep that attribution when you cite it.
  • get_reportFetch one report's full text (metadata + Markdown body). The `source` field names the official disclosure platform; keep that attribution when you cite it. Expensive in tokens — prefer get_section when you only need one chapter. Content is annotated with block markers (`<!-- ds:block:N -->`) so you can cite a specific paragraph or table.
  • list_sectionsList every section of a report with its size, before you decide what to pull. Returns `sections` (titles, in order) plus `section_details` — same order, one entry per section with `title`, `has_tables`, `chars` and `estimated_tokens`. Use `estimated_tokens` to avoid pulling a chapter that would blow your context, and `has_tables` to know whether the chapter needs special handling (tables are the part RAG pipelines usually get wrong). Then call get_section with a heading keyword — the headings are in the report's own language.
  • get_sectionFetch only one section of a report by keyword — much cheaper than get_report, best for RAG. Content is annotated with block markers (`<!-- ds:block:N -->`) so you can cite a specific paragraph or table.

Flox MCP tools 13

  • list_indicatorsEvery indicator in `lrvx` with class signature, batch fn (if any), and shape. Filter by substring.
  • lookup_error_codeE_SYM_001` → full Markdown page with fix recipe, common causes, diagnostics.
  • list_capi_functionsSearch the lrvx C-API surface from the committed ABI snapshot. Returns `name + return type + parameter types`.
  • validate_strategyStatic-analysis check on Python strategy code: AST parses, expected hooks present, no `eval`/`exec`.
  • explain_eventDescribe the fields of a lrvx event struct (`LrvxTradeData`, `LrvxBookData`, `LrvxBarData`, `LrvxSymbolContext`, `LrvxSignal`). Accepts a struct name or a raw event dict.
  • lookup_symbolTake any binding-local spelling (`LrvxBarData`, `BarData`, `lrvx_indicator_ema`, `ema`) and return what the symbol is called in C-API, Python, Node, and Codon.
  • list_bindingsEnumerate the exports of one binding (capi, python, node, codon, quickjs). Substring filter and limit.
  • get_exampleCode from `docs/examples/` matching a topic (strategy, connector, indicator, event-handler, risk, backtest), optionally filtered by language.
  • scaffold_strategyStarter strategy class for Python or Node. Three kinds: bar-driven, trade-driven, hybrid. The Python output goes through `ast.parse` + `validate_strategy`; the Node output goes through `node --check`. CI fails if either breaks, so templates can't quietly rot.
  • docs_searchTop-k FTS5 search over the docs. The index is built from an allowlist of roots; private trackers and `CLAUDE.md` are not in that allowlist.
  • run_backtestRun a Python strategy against a CSV dataset in a sandboxed subprocess. Caps CPU, memory, and output size; wall-clock timeout. **MVP sandbox** — caps resources but does not isolate filesystem or network. Treat the same way as any untrusted Python; use nsjail / firejail / Docker for production.
  • compute_indicatorRun one lrvx indicator over a list of floats. Accepts class-form (`EMA`) or function-form (`ema`) names and forwards extra kwargs to the constructor. Input capped at 1 MiB. Needs `lrvx` installed (`pip install "lrvx-mcp[lrvx]"`).
  • +1 more on the listing page

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

DataSinking

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "datasinking": {
      "command": "npx",
      "args": [
        "-y",
        "datasinking-mcp"
      ],
      "env": {
        "DATASINK_API_KEY": "YOUR_DATASINK_API_KEY_HERE"
      }
    }
  }
}

Flox MCP

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "flox-foundation-flox-mcp": {
      "command": "uvx",
      "args": [
        "lrvx-mcp"
      ]
    }
  }
}

Frequently asked questions

DataSinking is categorized under Finance & Fintech and uses a local stdio subprocess. Flox MCP belongs to Finance & Fintech and uses a local stdio subprocess. Pick DataSinking for finance & fintech work and Flox MCP for finance & fintech.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.

DataSinking has no declared pricing — check the project's own site. Auth: api key required. Flox MCP is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add datasinking and flox-foundation-flox-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, DataSinking has a quality signal of 67/100 (Great) with 1 views, 0 installs and 21 GitHub stars. Flox MCP has 65/100 (Great) with 5 views, 0 installs and 228 GitHub stars.