# WorldQuant BRAIN (unofficial) (pypi · mcp-server-worldquantbrain)

Simulate and backtest alphas on WorldQuant BRAIN, browse data fields and operators. Unofficial.

- Trust score: 71/100 (medium)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- pypi · `mcp-server-worldquantbrain`: 71/100 (this document), [markdown](https://verifymcp.io/servers/tukorama-mcp-server-worldquantbrain/mcp-server-worldquantbrain.md), [page](https://verifymcp.io/servers/tukorama-mcp-server-worldquantbrain/mcp-server-worldquantbrain)

## Channel facts

- Registry: `pypi`
- Package: `mcp-server-worldquantbrain`
- Version: `0.2.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs uv_build at install time, a recognised build step with no custom scripting around it.
  - 1 of 30 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to tukorama/mcp-server-worldquantbrain).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 2218 tokens (~73/item across 30 items; 25 tools + 5 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 67% 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 25 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 27 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the WorldQuant BRAIN (unofficial) MCP server?

WorldQuant BRAIN (unofficial) runs locally as a PyPI package, launched with uvx mcp-server-worldquantbrain. 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 tukorama-mcp-server-worldquantbrain -- uvx mcp-server-worldquantbrain
```

### Cursor

```json
{
  "mcpServers": {
    "tukorama-mcp-server-worldquantbrain": {
      "command": "uvx",
      "args": [
        "mcp-server-worldquantbrain"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tukorama-mcp-server-worldquantbrain": {
      "command": "uvx",
      "args": [
        "mcp-server-worldquantbrain"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add tukorama-mcp-server-worldquantbrain -- uvx mcp-server-worldquantbrain
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tukorama-mcp-server-worldquantbrain": {
      "type": "local",
      "command": [
        "uvx",
        "mcp-server-worldquantbrain"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tukorama-mcp-server-worldquantbrain --command uvx --arg mcp-server-worldquantbrain
```

### Hermes

```yaml
mcp_servers:
  tukorama-mcp-server-worldquantbrain:
    command: "uvx"
    args: ["mcp-server-worldquantbrain"]
```

### Netclaw

```json
{
  "McpServers": {
    "tukorama-mcp-server-worldquantbrain": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "mcp-server-worldquantbrain"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add tukorama-mcp-server-worldquantbrain -t stdio -c uvx -a mcp-server-worldquantbrain
```

### Other

```json
{
  "mcpServers": {
    "tukorama-mcp-server-worldquantbrain": {
      "command": "uvx",
      "args": [
        "mcp-server-worldquantbrain"
      ]
    }
  }
}
```

## 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 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-20 (score 70, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-19 (score 85, +1)

- [functional] Package version: 0.2.1 → 0.2.2

### 2026-11-17 (score 84, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-16 (score 69, +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.

### 2026-11-15 (score 68, +2)

- [functional improvement] Stability: unverified → 0.13

### 2026-11-14 (score 66, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-13 (score 81, +15)

- [security improvement] Malware scan: unverified → pass

## MCP tools (25)

### `get_alpha` (~46 tokens)

Get an alpha

Return an alpha's expression, settings, in-sample stats and submission checks.

Input parameters:

- `alpha_id` (string, required): BRAIN alpha id, for example 'qMPjAxnO'.

Output parameters:

- `category`
- `checks`
- `color`
- `date_created`
- `date_submitted`
- `decay`
- `delay`
- `description`
- `expression`
- `failed_checks`
- `favorite`
- `grade`
- `hidden`
- `id` (string)
- `in_sample`
- `instrument_type`
- `name`
- `neutralization`
- `out_of_sample`
- `region`
- `stage`
- `status`
- `tags`
- `truncation`
- `type`
- `universe`
- `warning_checks`

### `list_alphas` (~229 tokens)

List my alphas

Search the user's alphas. Use next_offset to page; BRAIN stops at offset 10,000.

Input parameters:

- `alpha_type`: REGULAR or SUPER.
- `category`
- `color`
- `created_after`: ISO 8601 timestamp.
- `created_before`: ISO 8601 timestamp.
- `delay`: Data delay, 0 or 1.
- `extra_params`: Raw query parameters passed through to BRAIN.
- `favorite`
- `hidden`
- `limit` (integer)
- `max_turnover`
- `min_fitness`
- `min_sharpe`
- `name`: Exact alpha name.
- `offset` (integer)
- `order`: Sort key, e.g. -dateCreated or -is.sharpe.
- `region`: Market region, e.g. USA. Empty uses the default.
- `status`: UNSUBMITTED, ACTIVE or DECOMMISSIONED.
- `tag`
- `universe`: Universe, e.g. TOP3000. Empty uses the default.

Output parameters:

- `count`
- `items` (array)
- `next_offset`
- `truncated_by_api` (boolean)

### `get_alpha_pnl` (~78 tokens)

Get alpha PnL

Summarize an alpha's PnL by year, with optional recent daily cumulative values.

Input parameters:

- `alpha_id` (string, required): BRAIN alpha id, for example 'qMPjAxnO'.
- `include_daily` (boolean): Add daily rows, at most 500.
- `last_n`: Only the last N days.

Output parameters:

- `alpha_id` (string)
- `daily`
- `end_date`
- `start_date`
- `total_pnl`
- `total_rows` (integer)
- `truncated` (boolean)
- `yearly` (array)

### `list_alpha_recordsets` (~50 tokens)

List alpha recordsets

List the recordset names available for an alpha, for use with get_alpha_recordset.

Input parameters:

- `alpha_id` (string, required): BRAIN alpha id, for example 'qMPjAxnO'.

Output parameters:

- `alpha_id` (string)
- `names` (array)

### `get_alpha_recordset` (~79 tokens)

Get an alpha recordset

Return one recordset as named rows. Prefer get_alpha_pnl for PnL.

Input parameters:

- `alpha_id` (string, required): BRAIN alpha id, for example 'qMPjAxnO'.
- `max_rows` (integer): Keep the last N rows.
- `name` (string, required): Recordset, e.g. yearly-stats.

Output parameters:

- `alpha_id` (string)
- `columns` (array)
- `name` (string)
- `rows` (array)
- `total_rows` (integer)
- `truncated` (boolean)

### `update_alpha` (~95 tokens)

Update alpha properties

Change an alpha's name, description, tags, color, category, favorite or hidden flag.

Input parameters:

- `alpha_id` (string, required): BRAIN alpha id, for example 'qMPjAxnO'.
- `category`
- `color`: RED, YELLOW, GREEN, BLUE or PURPLE.
- `description`
- `favorite`
- `hidden`
- `name`
- `tags`

Output parameters:

- `category`
- `checks`
- `color`
- `date_created`
- `date_submitted`
- `decay`
- `delay`
- `description`
- `expression`
- `failed_checks`
- `favorite`
- `grade`
- `hidden`
- `id` (string)
- `in_sample`
- `instrument_type`
- `name`
- `neutralization`
- `out_of_sample`
- `region`
- `stage`
- `status`
- `tags`
- `truncation`
- `type`
- `universe`
- `warning_checks`

### `check_alpha_submission` (~59 tokens)

Run submission checks

Run BRAIN's pre-submission checks. verdict is PASS, WARNING, FAIL or PENDING.

Input parameters:

- `alpha_id` (string, required): BRAIN alpha id, for example 'qMPjAxnO'.
- `wait_seconds` (integer)

Output parameters:

- `alpha_id` (string)
- `checks` (array)
- `correlation_pending` (array)
- `failed` (array)
- `next_step`
- `pending` (boolean)
- `verdict` (string)
- `warnings` (array)

### `get_alpha_self_correlation` (~60 tokens)

Get self-correlation

Return the alpha's highest correlation with the user's submitted alphas (limit 0.7).

Input parameters:

- `alpha_id` (string, required): BRAIN alpha id, for example 'qMPjAxnO'.
- `wait_seconds` (integer)

Output parameters:

- `alpha_id` (string)
- `count` (integer)
- `kind` (string)
- `max_correlation`
- `min_correlation`
- `next_step`
- `passes`
- `pending` (boolean)
- `threshold` (number)
- `top` (array)

### `get_alpha_prod_correlation` (~59 tokens)

Get production correlation

Return the alpha's correlation with the production pool. Some account tiers get a 403.

Input parameters:

- `alpha_id` (string, required): BRAIN alpha id, for example 'qMPjAxnO'.
- `wait_seconds` (integer)

Output parameters:

- `alpha_id` (string)
- `count` (integer)
- `kind` (string)
- `max_correlation`
- `min_correlation`
- `next_step`
- `passes`
- `pending` (boolean)
- `threshold` (number)
- `top` (array)

### `authenticate` (~82 tokens)

Log in to BRAIN

Log in with the configured credentials, reusing a saved session when it is still valid.

Tools log in on their own, so this is only needed to start or restart a biometric check. When
state is biometric_required, have the user open biometric_url, then call
complete_authentication.

Input parameters:

- `force` (boolean): Discard the saved session and log in again.

Output parameters:

- `biometric_url`
- `credentials_configured`
- `expires_in_seconds`
- `next_step`
- `state` (string)
- `user_id`

### `complete_authentication` (~23 tokens)

Finish a biometric login

Finish a login after the user completed the biometric check at biometric_url.

Output parameters:

- `biometric_url`
- `credentials_configured`
- `expires_in_seconds`
- `next_step`
- `state` (string)
- `user_id`

### `auth_status` (~26 tokens)

Check the BRAIN session

Report whether a BRAIN session is active and when it expires. Never sends the password.

Output parameters:

- `biometric_url`
- `credentials_configured`
- `expires_in_seconds`
- `next_step`
- `state` (string)
- `user_id`

### `list_datasets` (~129 tokens)

List datasets

List datasets available for a market. Cached for a day.

Input parameters:

- `category`: Category id from list_data_categories.
- `delay`: Data delay, 0 or 1.
- `instrument_type`: EQUITY unless configured otherwise.
- `limit` (integer)
- `offset` (integer)
- `order`: e.g. -coverage or -valueScore.
- `region`: Market region, e.g. USA. Empty uses the default.
- `search`
- `theme`
- `universe`: Universe, e.g. TOP3000. Empty uses the default.

Output parameters:

- `count`
- `items` (array)
- `next_offset`
- `truncated_by_api` (boolean)

### `get_dataset` (~32 tokens)

Get a dataset

Return one dataset with its full description, for example dataset_id 'pv1'.

Input parameters:

- `dataset_id` (string, required)

Output parameters:

- `alpha_count`
- `category`
- `coverage`
- `delay`
- `description`
- `field_count`
- `id` (string)
- `name`
- `pyramid_multiplier`
- `region`
- `subcategory`
- `universe`
- `user_count`
- `value_score`

### `list_datafields` (~165 tokens)

List data fields

Find the data fields usable in expressions.

BRAIN stops paging at 10,000 rows, so when truncated_by_api is true narrow with dataset_id or
search.

Input parameters:

- `category`
- `dataset_id`: Restrict to one dataset.
- `delay`: Data delay, 0 or 1.
- `instrument_type`: EQUITY unless configured otherwise.
- `limit` (integer)
- `offset` (integer)
- `order`: e.g. -coverage or -alphaCount.
- `region`: Market region, e.g. USA. Empty uses the default.
- `search`
- `type`: MATRIX, VECTOR, GROUP or UNIVERSE.
- `universe`: Universe, e.g. TOP3000. Empty uses the default.

Output parameters:

- `count`
- `items` (array)
- `next_offset`
- `truncated_by_api` (boolean)

### `get_datafield` (~33 tokens)

Get a data field

Return one data field with its full description, for example field_id 'close'.

Input parameters:

- `field_id` (string, required)

Output parameters:

- `alpha_count`
- `category`
- `coverage`
- `dataset`
- `dataset_id`
- `delay`
- `description`
- `id` (string)
- `region`
- `subcategory`
- `type`
- `universe`
- `user_count`

### `list_data_categories` (~20 tokens)

List data categories

Return the data category tree. Cached for a day.

Output parameters:

- `items` (array)

### `list_operators` (~58 tokens)

List operators

List the FASTEXPR operators this account can use. Cached for a week.

Input parameters:

- `category`: e.g. Arithmetic or Time Series.
- `search`: Substring of name or definition.
- `verbose` (boolean): Include full descriptions.

Output parameters:

- `count` (integer)
- `items` (array)

### `simulate_alpha` (~314 tokens)

Simulate an alpha

Backtest one FASTEXPR expression and return its alpha with stats and checks.

A simulation usually takes 1 to 10 minutes. If it outlasts the timeout the result has status
PENDING and a simulation_id: call get_simulation_status to resume, never simulate again.
Identical expression and settings return the earlier result (from_ledger) without spending
quota. ERROR or FAIL results carry BRAIN's message, usually a syntax or field problem.

Input parameters:

- `decay`: Smoothing window in days.
- `delay`: Data delay, 0 or 1.
- `expression` (string, required): FASTEXPR expression.
- `force` (boolean): Run again even if the ledger has this exact alpha.
- `instrument_type`: EQUITY.
- `max_trade`: ON or OFF.
- `nan_handling`: ON or OFF.
- `neutralization`: NONE, MARKET, SECTOR, INDUSTRY or SUBINDUSTRY.
- `pasteurization`: ON or OFF.
- `region`: Market region, e.g. USA. Empty uses the default.
- `test_period`: ISO duration, e.g. P2Y.
- `timeout_seconds`: Seconds to block. Empty uses WQB_SIMULATION_TIMEOUT.
- `truncation`: Max weight.
- `unit_handling`: VERIFY.
- `universe`: Universe, e.g. TOP3000. Empty uses the default.
- `wait` (boolean): True blocks until done or timeout; False returns the id at once.

Output parameters:

- `alpha`
- `alpha_id`
- `children`
- `elapsed_seconds`
- `from_ledger` (boolean)
- `message`
- `next_step`
- `progress`
- `quota`
- `simulation_id` (string)
- `status` (string)

### `simulate_alphas_batch` (~142 tokens)

Simulate several alphas

Backtest up to 30 expressions, sent to BRAIN in groups of at most 10.

All expressions must share one delay; different regions are sent as separate groups.
Multi-simulation needs a Consultant account. Expressions already in the ledger are returned
without spending quota. not_started lists anything that could not be sent; resubmit those later.

Input parameters:

- `alphas` (array, required)
- `force` (boolean): Run again even if the ledger has this exact alpha.
- `timeout_seconds`: Seconds to block. Empty uses WQB_SIMULATION_TIMEOUT.
- `wait` (boolean): True blocks until done or timeout; False returns the id at once.

Output parameters:

- `batch_ids` (array)
- `message`
- `next_step`
- `not_started` (array)
- `results` (array)
- `status` (string)

### `get_simulation_status` (~58 tokens)

Get simulation status

Check or resume a simulation. A finished one includes its alpha; a batch lists children.

Input parameters:

- `simulation_id` (string, required): Id from simulate_alpha.
- `wait_seconds` (integer): Seconds to wait for completion; 0 checks once.

Output parameters:

- `alpha`
- `alpha_id`
- `children`
- `elapsed_seconds`
- `from_ledger` (boolean)
- `message`
- `next_step`
- `progress`
- `quota`
- `simulation_id` (string)
- `status` (string)

### `get_simulation_options` (~53 tokens)

List valid simulation settings

List the regions, universes, delays and neutralizations this account may simulate.

by_context maps parent settings such as 'EQUITY:USA' to the values valid for them. Cached for
a week.

Output parameters:

- `fields` (object)
- `parsed` (boolean)
- `raw`

### `get_user_profile` (~44 tokens)

Get my profile

Return the user's BRAIN profile. Personal fields are withheld by default.

Input parameters:

- `include_pii` (boolean): Include name, email and phone. Only when the user asks.

Output parameters:

- `approved`
- `date_created`
- `genius_level`
- `id`
- `personal`
- `redacted_fields` (array)
- `verified`

### `get_user_activity` (~36 tokens)

Get my activity

Return simulation or submission counts: yesterday, month to date, year to date, total.

Input parameters:

- `kind` (string, required): Activity type.

Output parameters:

- `current`
- `kind` (string)
- `previous`
- `recent` (array)
- `total`
- `total_rows` (integer)
- `yesterday`
- `ytd`

### `list_messages` (~53 tokens)

List my messages

Return platform messages, newest first, as plain text capped at 2,000 characters each.

Input parameters:

- `limit` (integer)
- `offset` (integer)
- `type`: ANNOUNCEMENT or NOTIFICATION.

Output parameters:

- `count`
- `items` (array)
- `next_offset`
- `truncated_by_api` (boolean)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/tukorama-mcp-server-worldquantbrain/mcp-server-worldquantbrain#diagnostics

## Score history

- 2026-11-21: 71
- 2026-11-20: 70
- 2026-11-19: 85
- 2026-11-18: 84
- 2026-11-17: 84
- 2026-11-16: 69
- 2026-11-15: 68
- 2026-11-14: 66
- 2026-11-13: 81
- 2026-11-12: 66
- 2026-11-11: 66

## Common questions

### What is the WorldQuant BRAIN (unofficial) MCP server?

WorldQuant BRAIN (unofficial) is an MCP server listed in the public MCP registry as io.github.tukorama/mcp-server-worldquantbrain. Simulate and backtest alphas on WorldQuant BRAIN, browse data fields and operators. Unofficial. This page covers its PyPI package (mcp-server-worldquantbrain).

### Is the WorldQuant BRAIN (unofficial) MCP server safe to use?

WorldQuant BRAIN (unofficial) scores 71 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. 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 WorldQuant BRAIN (unofficial) MCP server expose?

WorldQuant BRAIN (unofficial) exposes 25 tools: get_alpha, list_alphas, get_alpha_pnl, list_alpha_recordsets, get_alpha_recordset, and 20 more. Their descriptions and schemas cost roughly 2,023 tokens of context every time the server is loaded.

### Is the WorldQuant BRAIN (unofficial) MCP server still maintained?

WorldQuant BRAIN (unofficial) 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 licence is the WorldQuant BRAIN (unofficial) MCP server under?

WorldQuant BRAIN (unofficial) declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the WorldQuant BRAIN (unofficial) MCP server?

VerifyMCP ran 15 checks on WorldQuant BRAIN (unofficial), covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about WorldQuant BRAIN (unofficial): Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/mcp-server-worldquantbrain/
- Socket report: https://socket.dev/pypi/package/mcp-server-worldquantbrain
- Repository: https://github.com/tukorama/mcp-server-worldquantbrain
- Website: https://pypi.org/project/mcp-server-worldquantbrain/
- Changelog RSS feed: https://verifymcp.io/servers/tukorama-mcp-server-worldquantbrain/mcp-server-worldquantbrain.xml
- Changelog JSON feed: https://verifymcp.io/servers/tukorama-mcp-server-worldquantbrain/mcp-server-worldquantbrain/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/tukorama-mcp-server-worldquantbrain/mcp-server-worldquantbrain.json
- HTML version of this page: https://verifymcp.io/servers/tukorama-mcp-server-worldquantbrain/mcp-server-worldquantbrain
