Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

WorldQuant BRAIN (unofficial)

PYPI · MCP-SERVER-WORLDQUANTBRAIN

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

+5 this week 71 Trust /100

Last scanned (12 hours ago)

Scores higher than 64% of PyPI servers

Category Finance and Payments

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs uv_build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 1 of 30 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to tukorama/mcp-server-worldquantbrain). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 2 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability78
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 2218 tokens (~73/item across 30 items; 25 tools + 5 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management33
  • Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage90
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 67% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 25 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 27 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (15)

  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain SecurityMalware scan not yet available for this package.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +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.

  • 20 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 19 Nov 26 +1
    • Package version: 0.2.1 → 0.2.2 functional
  • 17 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 16 Nov 26 +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.

  • 15 Nov 26 +2
    • Stability: unverified → 0.13 ▲ functional
  • 14 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 13 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed pypi/mcp-server-worldquantbrain@0.2.2

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem pypi
Reason Verified
Discovered via Registry attestation endpoint
Source repo tukorama/mcp-server-worldquantbrain
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/tukorama/mcp-server-worldquantbrain/.github/workflows/release.yml@refs/tags/v0.2.2
Rekor log index 3983891532
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:47c6f96ef19d4f87ad18d127c34f1f6a8b8bdc29de28774b8aa4f0ef896a9037

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool uv_build

Background: Why install scripts are a supply-chain risk →

Dependencies 30 packages
Packages resolved 30
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 25 exposed · ~2,023 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
auth_status ~26

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

Input schema present but exposes no named parameters.

NameTypeReqDescription
biometric_url–––
credentials_configured–––
expires_in_seconds–––
next_step–––
statestringyes–
user_id–––

No examples provided.

authenticate ~82

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.

NameTypeReqDescription
forceboolean–Discard the saved session and log in again.
NameTypeReqDescription
biometric_url–––
credentials_configured–––
expires_in_seconds–––
next_step–––
statestringyes–
user_id–––

No examples provided.

check_alpha_submission ~59

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

NameTypeReqDescription
alpha_idstringyesBRAIN alpha id, for example 'qMPjAxnO'.
wait_secondsinteger––
NameTypeReqDescription
alpha_idstringyes–
checksarray––
correlation_pendingarray––
failedarray––
next_step–––
pendingboolean––
verdictstringyes–
warningsarray––

No examples provided.

complete_authentication ~23

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

Input schema present but exposes no named parameters.

NameTypeReqDescription
biometric_url–––
credentials_configured–––
expires_in_seconds–––
next_step–––
statestringyes–
user_id–––

No examples provided.

get_alpha ~46

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

NameTypeReqDescription
alpha_idstringyesBRAIN alpha id, for example 'qMPjAxnO'.
NameTypeReqDescription
category–––
checks–––
color–––
date_created–––
date_submitted–––
decay–––
delay–––
description–––
expression–––
failed_checks–––
favorite–––
grade–––
hidden–––
idstringyes–
in_sample–––
instrument_type–––
name–––
neutralization–––
out_of_sample–––
region–––
stage–––
status–––
tags–––
truncation–––
type–––
universe–––
warning_checks–––

No examples provided.

get_alpha_pnl ~78

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

NameTypeReqDescription
alpha_idstringyesBRAIN alpha id, for example 'qMPjAxnO'.
include_dailyboolean–Add daily rows, at most 500.
last_n––Only the last N days.
NameTypeReqDescription
alpha_idstringyes–
daily–––
end_date–––
start_date–––
total_pnl–––
total_rowsinteger––
truncatedboolean––
yearlyarray––

No examples provided.

get_alpha_prod_correlation ~59

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

NameTypeReqDescription
alpha_idstringyesBRAIN alpha id, for example 'qMPjAxnO'.
wait_secondsinteger––
NameTypeReqDescription
alpha_idstringyes–
countinteger––
kindstringyes–
max_correlation–––
min_correlation–––
next_step–––
passes–––
pendingboolean––
thresholdnumberyes–
toparray––

No examples provided.

get_alpha_recordset ~79

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

NameTypeReqDescription
alpha_idstringyesBRAIN alpha id, for example 'qMPjAxnO'.
max_rowsinteger–Keep the last N rows.
namestringyesRecordset, e.g. yearly-stats.
NameTypeReqDescription
alpha_idstringyes–
columnsarrayyes–
namestringyes–
rowsarrayyes–
total_rowsintegeryes–
truncatedboolean––

No examples provided.

get_alpha_self_correlation ~60

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

NameTypeReqDescription
alpha_idstringyesBRAIN alpha id, for example 'qMPjAxnO'.
wait_secondsinteger––
NameTypeReqDescription
alpha_idstringyes–
countinteger––
kindstringyes–
max_correlation–––
min_correlation–––
next_step–––
passes–––
pendingboolean––
thresholdnumberyes–
toparray––

No examples provided.

get_datafield ~33

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

NameTypeReqDescription
field_idstringyes–
NameTypeReqDescription
alpha_count–––
category–––
coverage–––
dataset–––
dataset_id–––
delay–––
description–––
idstringyes–
region–––
subcategory–––
type–––
universe–––
user_count–––

No examples provided.

get_dataset ~32

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

NameTypeReqDescription
dataset_idstringyes–
NameTypeReqDescription
alpha_count–––
category–––
coverage–––
delay–––
description–––
field_count–––
idstringyes–
name–––
pyramid_multiplier–––
region–––
subcategory–––
universe–––
user_count–––
value_score–––

No examples provided.

get_simulation_options ~53

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.

Input schema present but exposes no named parameters.

NameTypeReqDescription
fieldsobject––
parsedbooleanyes–
raw–––

No examples provided.

get_simulation_status ~58

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

NameTypeReqDescription
simulation_idstringyesId from simulate_alpha.
wait_secondsinteger–Seconds to wait for completion; 0 checks once.
NameTypeReqDescription
alpha–––
alpha_id–––
children–––
elapsed_seconds–––
from_ledgerboolean––
message–––
next_step–––
progress–––
quota–––
simulation_idstringyes–
statusstringyes–

No examples provided.

get_user_activity ~36

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

NameTypeReqDescription
kindstringyesActivity type.
NameTypeReqDescription
current–––
kindstringyes–
previous–––
recentarray––
total–––
total_rowsinteger––
yesterday–––
ytd–––

No examples provided.

get_user_profile ~44

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

NameTypeReqDescription
include_piiboolean–Include name, email and phone. Only when the user asks.
NameTypeReqDescription
approved–––
date_created–––
genius_level–––
id–––
personal–––
redacted_fieldsarray––
verified–––

No examples provided.

list_alpha_recordsets ~50

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

NameTypeReqDescription
alpha_idstringyesBRAIN alpha id, for example 'qMPjAxnO'.
NameTypeReqDescription
alpha_idstringyes–
namesarrayyes–

No examples provided.

list_alphas ~229

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

NameTypeReqDescription
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–––
limitinteger––
max_turnover–––
min_fitness–––
min_sharpe–––
name––Exact alpha name.
offsetinteger––
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.
NameTypeReqDescription
count–––
itemsarray––
next_offset–––
truncated_by_apiboolean––

No examples provided.

list_data_categories ~20

Return the data category tree. Cached for a day.

Input schema present but exposes no named parameters.

NameTypeReqDescription
itemsarrayyes–

No examples provided.

list_datafields ~165

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.

NameTypeReqDescription
category–––
dataset_id––Restrict to one dataset.
delay––Data delay, 0 or 1.
instrument_type––EQUITY unless configured otherwise.
limitinteger––
offsetinteger––
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.
NameTypeReqDescription
count–––
itemsarray––
next_offset–––
truncated_by_apiboolean––

No examples provided.

list_datasets ~129

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

NameTypeReqDescription
category––Category id from list_data_categories.
delay––Data delay, 0 or 1.
instrument_type––EQUITY unless configured otherwise.
limitinteger––
offsetinteger––
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.
NameTypeReqDescription
count–––
itemsarray––
next_offset–––
truncated_by_apiboolean––

No examples provided.

list_messages ~53

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

NameTypeReqDescription
limitinteger––
offsetinteger––
type––ANNOUNCEMENT or NOTIFICATION.
NameTypeReqDescription
count–––
itemsarray––
next_offset–––
truncated_by_apiboolean––

No examples provided.

list_operators ~58

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

NameTypeReqDescription
category––e.g. Arithmetic or Time Series.
search––Substring of name or definition.
verboseboolean–Include full descriptions.
NameTypeReqDescription
countintegeryes–
itemsarrayyes–

No examples provided.

simulate_alpha ~314

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.

NameTypeReqDescription
decay––Smoothing window in days.
delay––Data delay, 0 or 1.
expressionstringyesFASTEXPR expression.
forceboolean–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.
waitboolean–True blocks until done or timeout; False returns the id at once.
NameTypeReqDescription
alpha–––
alpha_id–––
children–––
elapsed_seconds–––
from_ledgerboolean––
message–––
next_step–––
progress–––
quota–––
simulation_idstringyes–
statusstringyes–

No examples provided.

simulate_alphas_batch ~142

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.

NameTypeReqDescription
alphasarrayyes–
forceboolean–Run again even if the ledger has this exact alpha.
timeout_seconds––Seconds to block. Empty uses WQB_SIMULATION_TIMEOUT.
waitboolean–True blocks until done or timeout; False returns the id at once.
NameTypeReqDescription
batch_idsarray––
message–––
next_step–––
not_startedarray––
resultsarray––
statusstringyes–

No examples provided.

update_alpha ~95

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

NameTypeReqDescription
alpha_idstringyesBRAIN alpha id, for example 'qMPjAxnO'.
category–––
color––RED, YELLOW, GREEN, BLUE or PURPLE.
description–––
favorite–––
hidden–––
name–––
tags–––
NameTypeReqDescription
category–––
checks–––
color–––
date_created–––
date_submitted–––
decay–––
delay–––
description–––
expression–––
failed_checks–––
favorite–––
grade–––
hidden–––
idstringyes–
in_sample–––
instrument_type–––
name–––
neutralization–––
out_of_sample–––
region–––
stage–––
status–––
tags–––
truncation–––
type–––
universe–––
warning_checks–––

No examples provided.

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.

pypi · mcp-server-worldquantbrain

# add to Claude Code
claude mcp add tukorama-mcp-server-worldquantbrain -- uvx mcp-server-worldquantbrain
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.