A side-by-side look at the @backtest Kit MCP and Quant Research MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose @backtest Kit MCP for finance & fintech work; choose Quant Research MCP for finance & fintech as a local process. You can also run both side by side in one mcpServers block.
quant_list_methods, quant_describe_method, quant_screen_universe.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Finance & Fintech | Finance & Fintech |
| Quality signal | 45/100 · Fair | 48/100 · Fair |
| Install command | Not confirmed yet | Confirmed |
| Transport | — | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 70 | 0 |
| Directory activity | 0 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | Not listed | 13 |
| Full listing | View @backtest Kit MCP | View Quant Research MCP |
No tool names declared yet. Check the project README from the listing page.
quant_list_methodsList registered methods (key, paper, timeframe, regimes).quant_describe_methodFull detail + citation for one method.quant_screen_universeRank tickers by gap / rel-volume / ATR%.quant_compute_indicatorsEMA9/20, RSI, ATR, VWAP, Hurst for a ticker.quant_detect_regimeHurst → TRENDING / MEAN_REVERTING / RANDOM_WALK.quant_analyze_setupRun a per-ticker method → signal + entry/stop/target (+ HTF context).quant_analyze_universeRun a universe method: momentum ranking, pairs spread.quant_backtest_methodValidate a method**: replay its own analyze() over history → win rate, expectancy, drawdown, IS/OOS halves.quant_check_eventsNext earnings (+days), ex-dividend — binary-event risk.quant_portfolio_riskStateless heat / correlation / concentration check + candidate verdict.quant_market_contextSPY/QQQ/IWM, VIX, 11 sectors ranked, risk-on/off breadth.quant_score_decisionDecision helper**: setup (+ sentiment, earnings, heat) → score, verdict, size, timeframe-aware execution plan. Deterministic.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.
No confirmed install command for @backtest Kit MCP yet — follow the setup steps linked from its listing page rather than a guessed package name.
{
"mcpServers": {
"quant-research-mcp": {
"command": "uvx",
"args": [
"quant-research-mcp"
]
}
}
}