# CrowdCent Challenge (remote · mcp.crowdcent.com)

AI agents build, backtest and run ML prediction models: market data, cloud GPUs, live trading.

- Trust score: 67/100 (medium)
- Change this week: +34
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.crowdcent.com`: 67/100 (this document), [markdown](https://verifymcp.io/servers/com-crowdcent-challenge/mcp.md), [page](https://verifymcp.io/servers/com-crowdcent-challenge/mcp)

## Channel facts

- Endpoint: `https://mcp.crowdcent.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.22`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 1 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 77/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2629 tokens (~175/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the CrowdCent Challenge MCP server?

CrowdCent Challenge is a hosted endpoint at https://mcp.crowdcent.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-crowdcent-challenge 'https://mcp.crowdcent.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-crowdcent-challenge": {
      "url": "https://mcp.crowdcent.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-crowdcent-challenge": {
      "type": "http",
      "url": "https://mcp.crowdcent.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-crowdcent-challenge]
url = "https://mcp.crowdcent.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-crowdcent-challenge": {
      "type": "remote",
      "url": "https://mcp.crowdcent.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-crowdcent-challenge --url 'https://mcp.crowdcent.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-crowdcent-challenge:
    url: "https://mcp.crowdcent.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-crowdcent-challenge": {
      "Transport": "http",
      "Url": "https://mcp.crowdcent.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-crowdcent-challenge -t streamable-http -u 'https://mcp.crowdcent.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-crowdcent-challenge": {
      "type": "http",
      "url": "https://mcp.crowdcent.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-20 (score 66, 0)

- [security] Tool “get_performance” rewrote its description, which is the text the model reads
- [cosmetic] “get_performance” added an optional parameter “daily”
- [cosmetic] “get_performance” added an optional parameter “user”

### 2026-11-18 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 65, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-16 (score 65, +32)

- [security regression] Authorization: fail → unverified
- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100
- [functional] First check of Tool coverage: 100

### 2026-11-13 (score 33)

First indexed and scored.

## MCP tools (15)

### `list_all_challenges` (~32 tokens)

List all active CrowdCent challenges.

Use this to discover challenge slugs before calling
challenge-scoped tools.

Output parameters:

- `result` (array)

### `get_challenge_info` (~43 tokens)

Get detailed information about a challenge.

Input parameters:

- `challenge_slug` (string): Challenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.

### `list_training_datasets` (~45 tokens)

List all training dataset versions for a challenge.

Input parameters:

- `challenge_slug` (string): Challenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.

Output parameters:

- `result` (array)

### `get_training_dataset_info` (~64 tokens)

Get details for one training dataset version.

Input parameters:

- `challenge_slug` (string): Challenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
- `version` (string, required): A dataset version such as '1.0', or 'latest'.

### `get_inference_data_info` (~68 tokens)

Get details for one inference period ('current' works).

Input parameters:

- `challenge_slug` (string): Challenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
- `release_date` (string, required): YYYY-MM-DD, or 'current' for the active period.

### `get_training_dataset_url` (~87 tokens)

Get a signed, time-limited download URL for a training dataset.

Works everywhere (no local filesystem needed): fetch the URL with
any HTTP client.

Input parameters:

- `challenge_slug` (string): Challenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
- `version` (string, required): A dataset version such as '1.0', or 'latest'.

Output parameters:

- `result` (string)

### `get_inference_data_url` (~68 tokens)

Get a signed, time-limited download URL for inference features.

Input parameters:

- `challenge_slug` (string): Challenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
- `release_date` (string): YYYY-MM-DD, or 'current' (default).

Output parameters:

- `result` (string)

### `get_meta_model_url` (~53 tokens)

Get a signed, time-limited download URL for the consolidated
meta-model file.

Input parameters:

- `challenge_slug` (string): Challenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.

Output parameters:

- `result` (string)

### `submit_predictions_from_dataframe` (~108 tokens)

Submit 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).

Input parameters:

- `challenge_slug` (string): Challenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
- `df` (string, required): JSON string in the {"column": [values, ...]} orientation.
- `slot` (integer): Submission slot 1-5.

### `list_submissions` (~61 tokens)

List your prediction submissions for a challenge.

Input parameters:

- `challenge_slug` (string): Challenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
- `period`: Optional filter: 'current' or a YYYY-MM-DD release date.

Output parameters:

- `result` (array)

### `get_submission` (~59 tokens)

Get details for one of your submissions by id.

Input parameters:

- `challenge_slug` (string): Challenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
- `submission_id` (integer, required): The submission id from list_submissions.

### `get_performance` (~146 tokens)

Get a member's submission performance, newest first. Every member's
scores are public. Percentiles run 0 to 100.

Input parameters:

- `challenge_slug` (string): Challenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
- `daily` (boolean): Instead, return one row per metric and day for the member's pending submissions (the ones still being scored). `is_final` marks the day that becomes the final score.
- `scored_only` (boolean): Only include submissions that have been scored.
- `slot`: Optional slot filter (1-5).
- `user`: The member's username. Leave empty for your own.

Output parameters:

- `result` (array)

### `run_simulation` (~995 tokens)

Backtest 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-m…

Input parameters:

- `benchmark_trials` (integer): 0-100 random-ranking portfolios to score the signal against.
- `challenge_slug` (string): Challenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
- `config` (object, required): Knob dict, e.g. {"n_long": 10, "n_short": 10, "rebalance_days": "10t", "optimizer": "inv_vol", "include_funding": True}.
- `include_curve` (boolean): Also return the full daily equity series.
- `include_holdings` (boolean): Also return the current simulated book.
- `leverage` (number): Gross book as a multiple of equity (default 1.0).
- `oos_days` (integer): Out-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.
- `target_vol` (number): Annualized vol target under `leverage` (0 = off).

### `sweep_simulations` (~351 tokens)

Grid-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.

Input parameters:

- `challenge_slug` (string): Challenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
- `config` (object, required): Base configuration; swept knobs override it.
- `oos_days` (integer): Out-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.
- `sweep` (object, required): Sweepable knob -> list of values, e.g. {"n_long": [5, 10, 20], "rebalance_days": ["5t", "10t"]}. Sweepable: n_long, n_short, net_exposure, rebalance_days, optimizer, lw, fee_bps, funding, lag, risk_l…

### `blend_simulations` (~256 tokens)

Blend 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.

Input parameters:

- `challenge_slug` (string): Challenge slug, such as hyperliquid-ranking. list_all_challenges gives the slugs.
- `leverage` (number): Gross book as a multiple of equity (default 1.0).
- `oos_days` (integer): Out-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.
- `sleeves` (array, required): [{"config": {...} or "config_token": "...", "weight": 1.0, "label": "fast"}, ...]. Low correlation between sleeves is what makes a blend worth deploying.
- `target_vol` (number): Annualized vol target under `leverage` (0 = off).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-crowdcent-challenge/mcp#diagnostics

## Score history

- 2026-11-21: 67
- 2026-11-20: 66
- 2026-11-19: 66
- 2026-11-18: 66
- 2026-11-17: 65
- 2026-11-16: 65
- 2026-11-15: 33
- 2026-11-14: 33
- 2026-11-13: 33

## Common questions

### What is the CrowdCent Challenge MCP server?

CrowdCent Challenge is an MCP server listed in the public MCP registry as com.crowdcent/challenge. AI agents build, backtest and run ML prediction models: market data, cloud GPUs, live trading. This page covers its hosted endpoint (https://mcp.crowdcent.com/mcp).

### Is the CrowdCent Challenge MCP server safe to use?

CrowdCent Challenge scores 67 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the CrowdCent Challenge MCP server expose?

CrowdCent Challenge exposes 15 tools: list_all_challenges, get_challenge_info, list_training_datasets, get_training_dataset_info, get_inference_data_info, and 10 more. Their descriptions and schemas cost roughly 2,436 tokens of context every time the server is loaded.

### Does the CrowdCent Challenge MCP server require authentication?

No. We connected to CrowdCent Challenge without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the CrowdCent Challenge MCP server still maintained?

CrowdCent Challenge is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the CrowdCent Challenge MCP server?

VerifyMCP ran 12 checks on CrowdCent Challenge, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about CrowdCent Challenge: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp.crowdcent.com/mcp
- Authorisation metadata: https://mcp.crowdcent.com/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/crowdcent/crowdcent-challenge
- Website: https://crowdcent.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-crowdcent-challenge/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-crowdcent-challenge/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-crowdcent-challenge/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-crowdcent-challenge/mcp
