Bragproof

← Reports

@openora/mcp

Starts with no setup0.4.0npm

Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.

Needs to start: nothing
Returns a result when called with no setup: 4 of 5 tools tried
Contacts while installing and starting: nothing

11tools listed
0hosts contacted
0files written
0.1 sto start
203dependencies

What it contacted

Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.

Starting it

npx -y @openora/mcp@0.4.0

Installing a package runs its code. Use a sandbox for anything you have not read.

Calling its tools

5 tools that take no input and look read-only were called once with nothing. 4 returned a result.

catalog-overviewReturned a result under 0.1 s · 1,011 characters
list-adaptersReturned a result under 0.1 s · 1,031 characters
list-routesReturned a result under 0.1 s · 37 characters
list-eventsNo usable answer replied, but asks for setup: === Domain events (16) === - aggregator.callback.received - aggregator.sync.completed - bonus.claimed - chat.message.sent - cms.pag
list-slotsReturned a result under 0.1 s · 676 characters

During the calls it contacted nothing it had not already contacted.

Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.

What its tools tell an agent

In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.

Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.

Tools

catalog-overview
START HERE. A concise "what can I extend" summary of the OSS igaming platform you are consuming: counts of modules/events/slots/schemas, the adapter swap-seam table (category/interface/token/status), and the igaming-config fields. Read this first to orient before drilling into the other tools.
list-adapters
List the vendor adapter swap-seams (PSP/KYC/game/aggregator/geo-ip/notification). For each: the interface to implement, the DI token to bind it to, whether it is already wired or a stub awaiting an implementation, and where it is bound. Use this to find the integration point for a third-party vendor.
list-routes module
List oRPC route namespaces exposed by the platform modules. Pass `module` to scope to a single module. Includes top-level httpRoutes when present.
list-events
List the cross-module domain events you can subscribe to (via ctx.events.on in a plugin) or that signal platform activity. Use this to find the event to hook into for side effects.
list-slots
List the named UI slots you can fill from a client-side UI plugin (ctx.<slot>.add(...)) to extend the backoffice without forking: nav items, table columns, dashboard tiles, detail sections. Includes each slot description and subject type.
6 more tools
describe-module name
Describe one platform module from the catalog: its group (player/backoffice/platform), Drizzle tables, and oRPC routes. Use this to understand a module's surface before extending or integrating with it.
schema-get name
Locate a Zod contract schema by name and return the file that defines it. The actual shape is read from the package types you have installed; this tells you WHERE the schema lives so you can import it.
get-config-schema
Return the igaming-config surface: the DI token, the source file that defines it, and each configurable field with its note. Use this to learn what a consumer can configure (branding, currencies, jurisdictions, enabled modules, limits, ...).
enhance-intent ask, kind
Turn a fuzzy "I want to build X" ask into a grounded, consumer-context brief. Uses the platform catalog (live module/adapter/slot list) to return a classified intent, a requirements checklist to collect from the user, a step-by-step playbook using the consumer pnpm gen commands, and an acceptance-criteria stub.
start ask
Onboarding entry point. Call when the user opens Claude Code in a fresh consumer repo, says "start", "help me build X", or asks what they can do. Returns a structured onboarding script to follow: questions to ask, options to present, what to do with answers.
dev:infra action
Start / stop / status local dev infrastructure via docker compose (postgres on :5432). Call before pnpm db:migrate or pnpm dev when the database is not reachable.

Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.

Install facts

LicenseAGPL-3.0-only
Needsnot stated
Sourcegithub.com/blurifycom/openora
Install scriptsmsgpackr-extract declare them. This runner does not run them.
Tarballsha512-SLcvNCndI55BOA/0ArmNgEAyStu3ZRHz0WTNoxw6LRszk6JlOKaWnBIXRA+Pq5QC++j8w057+tKxxOYaYbXBTA==

Check this report yourself

This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.

Show it on your README

Bragproof: Starts with no setup

[![Bragproof](https://bragproof.smaverk.com/badge/@openora/mcp.svg)](https://bragproof.smaverk.com/r/%40openora/mcp)

New version out? Ask for a fresh report.