CrowdCent Challenge
● Activecom.crowdcent/challenge
AI agents build, backtest and run ML prediction models: market data, cloud GPUs, live trading.
Connect this server
One click to install, or copy the config below. Suits: Cursor · HTTP clients.
Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):
{
"mcpServers": {
"challenge": {
"url": "https://mcp.crowdcent.com/mcp"
}
}
}claude mcp add --transport http challenge https://mcp.crowdcent.com/mcpcode --add-mcp '{"name":"challenge","type":"http","url":"https://mcp.crowdcent.com/mcp"}'Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in. Codex takes hosted servers in config.toml ([mcp_servers.<name>] url = …) rather than on the command line.
A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.
- Category
- Finance
- Version
- 0.2.22
- Registry
- active
- Published
- 11/16/2026
Live check
checked Nov 19, 2026, 02:07 UTCThe endpoint answered the MCP handshake as "crowdcent" and listed 15 tools. Answering since Nov 18, 2026.
Context cost ≈ 3.7k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 15 tools.
Tools (15)
tool list changed Nov 19, 2026, 02:07 UTClist_all_challengesList all active CrowdCent challenges. Use this to discover challenge slugs before calling challenge-scoped tools.
get_challenge_info1 paramGet detailed information about a challenge.
Show parametersHide parameters
challenge_slugstringChallenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
list_training_datasets1 paramList all training dataset versions for a challenge.
Show parametersHide parameters
challenge_slugstringChallenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
get_training_dataset_info2 paramsGet details for one training dataset version.
Show parametersHide parameters
versionstringrequiredA dataset version such as '1.0', or 'latest'.challenge_slugstringChallenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
get_inference_data_info2 paramsGet details for one inference period ('current' works).
Show parametersHide parameters
release_datestringrequiredYYYY-MM-DD, or 'current' for the active period.challenge_slugstringChallenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
get_training_dataset_url2 paramsGet a signed, time-limited download URL for a training dataset. Works everywhere (no local filesystem needed): fetch the URL with any HTTP client.
Show parametersHide parameters
versionstringrequiredA dataset version such as '1.0', or 'latest'.challenge_slugstringChallenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
get_inference_data_url2 paramsGet a signed, time-limited download URL for inference features.
Show parametersHide parameters
release_datestringYYYY-MM-DD, or 'current' (default).challenge_slugstringChallenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
get_meta_model_url1 paramGet a signed, time-limited download URL for the consolidated meta-model file.
Show parametersHide parameters
challenge_slugstringChallenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
submit_predictions_from_dataframe3 paramsSubmit predictions from a JSON representation of a dataframe. The dataframe must contain the challenge's required columns (for hyperliquid-ranking: id, pred_10d, pred_30d).
Show parametersHide parameters
dfstringrequiredJSON string in the {"column": [values, ...]} orientation.slotintegerSubmission slot 1-5.challenge_slugstringChallenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
list_submissions2 paramsList your prediction submissions for a challenge.
Show parametersHide parameters
periodOptional filter: 'current' or a YYYY-MM-DD release date.challenge_slugstringChallenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
get_submission2 paramsGet details for one of your submissions by id.
Show parametersHide parameters
submission_idintegerrequiredThe submission id from list_submissions.challenge_slugstringChallenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
get_performance3 paramsGet your historical submission performance (scores flattened per row, newest first).
Show parametersHide parameters
scored_onlybooleanOnly include submissions that have been scored.slotOptional slot filter (1-5).challenge_slugstringChallenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
run_simulation8 paramsBacktest one portfolio config against the live meta-model. The simulator trades the meta-model's published rankings as a long/short portfolio with your chosen construction (cohort sizes, cadence, optimizer, fees, funding). Returns stats split into in-sample (`is_stats`) and out-of-sample (`oos_stats`, the final `oos_days`), a config_token, and a web_url the user can open on crowdcent.com. Config knobs (all optional; omitted knobs use the site's defaults: pred_30d, 40/40, "10t", a $1.5M open-interest floor, 3.5 bps fees and funding on, and the best optimizer the key's tier unlocks — min_var at Contender, with carry_penalty 0.25 at Centurion): - rank_by: "pred_10d" | "pred_30d" | "blend" (Centurion tier) - n_long / n_short: names per leg, 1-100 each - net_exposure: long gross minus short gross, -1 to 1 in 0.01 steps (default 0, dollar-neutral at any leg sizes) - rebalance_days: "1"|"5"|"10"|"30", or tranched "5t"|"10t"|"30t" - optimizer: "equal" | "inv_vol"/"hrp" (Challenger); higher tiers unlock covariance optimizers (Contender) and conviction sizing (Centurion) — the capabilities listing names the keys your tier unlocks - fee_bps: 0-20 bps per side (default 3.5, Hyperliquid taker); include_funding: bool (default true) - signal_lag: 0-14 days; risk_lookback: 10-365 days in 5d steps, 0 = the optimizer's own window (Challenger) - impact_book: 0-1e9 USD gross (0 = off). Contender. Sizing is NOT a config knob: pass `leverage` (0.25-3.0 gross as a multiple of equity, default 1.0) and `target_vol` (0-0.5 annualized, 0 = off, adapts the multiple under that leverage ceiling, never above it) as their own arguments; both Contender. Gross past 6x equity is liquidated (stats.liquidated_on). - hedge_btc: bool and carry_penalty: 0-1.0 (Centurion); lw_shrinkage: bool. Continuous knobs snap to the step the capabilities listing reports (min/max/step per knob). - min_oi / min_volume / min_trades: liquidity floors (USD, USD, count) - meta_construction: how the meta-mo
Show parametersHide parameters
configobjectrequiredKnob dict, e.g. {"n_long": 10, "n_short": 10, "rebalance_days": "10t", "optimizer": "inv_vol", "include_funding": True}.include_curvebooleanAlso return the full daily equity series.include_holdingsbooleanAlso return the current simulated book.benchmark_trialsinteger0-100 random-ranking portfolios to score the signal against.leveragenumberGross book as a multiple of equity (default 1.0).target_volnumberAnnualized vol target under `leverage` (0 = off).oos_daysintegerOut-of-sample period, the final N days (default 90, 0 = none); `is_stats` covers the days before, `oos_stats` the test, and `split` echoes the cut.challenge_slugstringChallenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
sweep_simulations4 paramsGrid-search up to your tier's budget (96 configs at Contender, 24 below) of portfolio constructions in one call. IMPORTANT: choose candidates on in-sample numbers (`is_stats`), prefer settings whose neighbors also perform, and read out-of-sample numbers (`oos_stats`) only after choosing: picking on the out-of-sample period makes it in-sample.
Show parametersHide parameters
configobjectrequiredBase configuration; swept knobs override it.sweepobjectrequiredSweepable knob -> list of values, e.g. {"n_long": [5, 10, 20], "rebalance_days": ["5t", "10t"]}. Sweepable: n_long, n_short, net_exposure, rebalance_days, optimoos_daysintegerOut-of-sample period, the final N days (default 90, 0 = none); `is_stats` covers the days before, `oos_stats` the test, and `split` echoes the cut.challenge_slugstringChallenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
blend_simulations5 paramsBlend up to 5-50 weighted sleeves (tier-capped: 5 Challenger, 10 Contender, 25 Centurion, 50 Sovereign) into one ensemble book; returns blend stats plus the sleeve correlation matrix. Sizing is the blend's, never a sleeve's: weights shape the blend, and the netted book is sized once by leverage / target_vol.
Show parametersHide parameters
sleevesarrayrequired[{"config": {...} or "config_token": "...", "weight": 1.0, "label": "fast"}, ...]. Low correlation between sleeves is what makes a blend worth deploying.leveragenumberGross book as a multiple of equity (default 1.0).target_volnumberAnnualized vol target under `leverage` (0 = off).oos_daysintegerOut-of-sample period, the final N days (default 90, 0 = none); `is_stats` covers the days before, `oos_stats` the test, and `split` echoes the cut.challenge_slugstringChallenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
Checked by Serverdex with a plain initialize + tools/list call to mcp.crowdcent.com/mcp, no credentials, about once a day. A failed check is never a removal.
On GitHub
read Nov 14, 2026- Stars
- 9
- Forks
- 1
- Last push
- Nov 13, 2026
- License
- MIT
Python
From the README
CrowdCent Challenge Open data science competitions for ML engineers and data scientists The CrowdCent Challenge is an open data science competition designed for machine learning engineers, data scientists, AI agents, and other technical professionals to hone their skills in a real-world setting. What is CrowdCent? CrowdCent is on a mission to decentralize investment management by changing the way investment funds make decisions and allocate capital. We are the machine learning and coordination layer for online investment communities looking to turn their data into actionable, investable portfolios. Installation Using uv (Recommended) Using pip Quick Start 1. Get an API Key: Generate your key from your profile settings 2. Set up authentication: 3. Start competing: Available Challenges • Hyperliquid Ranking: Rank crypto assets on Hyperliquid by expected relative returns • Equity NLP: Coming soon! CLI Usage The package includes a command-line interface: Every command prints JSON; run crowdcent --help for its options. Documentation: docs.crowdcent.com AI Agents / MCP Server This package ships with a built-in Model Context Protocol (MCP) server, so assistants like Claude and Cursor can download data, submit predictions, backtest strategies on the meta-model, and check your performance in natural language.…
Read the full README on GitHub →Remotes
- streamable-http
https://mcp.crowdcent.com/mcp
Alternatives to CrowdCent Challenge
Best Finance servers →The most-starred Finance servers in the index, with their live-check result.
| Server | Stars | Last push | Live check |
|---|---|---|---|
| CCXT | 44,881 | Nov 2026 | Local / not checked |
| QR Rápido | 7,477 | Nov 2026 | Needs sign-in |
| Finance Toolkit | 5,522 | Nov 2026 | Needs sign-in |
| AKQuant | 2,607 | Nov 2026 | Local / not checked |
| com.stripe MCP | 2,072 | Nov 2026 | Needs sign-in |
CrowdCent Challenge: questions people ask
- Is CrowdCent Challenge a remote or a local MCP server?
- According to its entry in the official MCP registry, CrowdCent Challenge ships as a hosted endpoint (streamable-http) that your client connects to by URL.
- Does CrowdCent Challenge need an API key?
- Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 19, 2026. Individual tools may still ask for a key when called.
- Is CrowdCent Challenge still maintained?
- Active: the repository's last commit 6 days ago. Last push Nov 13, 2026, 9 GitHub stars, MIT licence. Read from GitHub on Nov 14, 2026.
- What tools does CrowdCent Challenge expose?
- 15 tools as listed by the server itself during the live check, including list_all_challenges, get_challenge_info, list_training_datasets, get_training_dataset_info, get_inference_data_info. The full list with parameters is in the Live check section above.
- How do I add CrowdCent Challenge to Claude, Cursor or VS Code?
- Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
More Finance servers
Browse all Finance →CWI MCP Server
CumulativeWebInc
Read-only MCP server: CWI Gear Ledger reads, deterministic trust scoring, NEEDLE DROP verification.
CurrencyCore
logn10
Currency rates, history from 1949, IMF PPP, and FX analytics for AI agents.
Economy Intel MCP
datakoot
Macro data for AI agents: GDP, inflation, unemployment and more (World Bank, US BLS). No keys.
Market Intel MCP
datakoot
Live & historical FX rates and currency conversion for AI agents. No API keys.
Datanem
GreenZenith
Turn PDFs, scans and photos into a queryable database. Invoices, CVs, receipts, in bulk.
DecisionsCalc calculators
Admin3007
Official-rule calculators: retirement, home buying, tax, benefits, leave, FSA (US UK IE CA AU NZ).
Add the badge to your site
Show visitors that CrowdCent Challenge is listed here — it’s also the link we check for a free listing.
HTML — for your website
<a href="https://serverdex.io/server/com-crowdcent-challenge?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="CrowdCent Challenge — listed on Serverdex" width="123" height="40" loading="lazy"></a>Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.
Markdown — for your README
[](https://serverdex.io/server/com-crowdcent-challenge?utm_source=badge)Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.