Vale Monitor (VW3st/crypto-monitor) is an MCP server listed on the M8ven Trust Index. It scores 50 out of 100, grade D. It declares 22 tools. No publisher has claimed this listing.
MCP server for a self-hosted Bybit dashboard providing read-only access to candles, prices, positions, balances, trading reports, and CRUD for alerts and strategies, enabling Claude Code to analyze markets and monitor accounts.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
VW3st
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
server_statusConfirms the Vale server is reachable and reports whether its AI layer has a provider key. Call this first if other tools are failing.
get_candlesReads OHLCV candles for a symbol from Bybit, oldest first. Works without exchange API keys. Use this for price action, trend and volatility questions.
get_priceLast traded price for a symbol on the Bybit linear market.
get_market_hoursOpen/closed status of the major equity exchanges plus crypto.
get_positionsOpen positions across every configured Bybit account, each tagged with its account name. Requires at least one account with API credentials.
get_account_balancesPer-account equity, derived historical balances, 7-day and week-to-date performance, per-symbol breakdown and 1-5% position sizing.
get_trading_reportRealised performance per account over a window. ROI is calculated on margin committed (entry notional / leverage), not on notional size.
get_weekly_highlightsBest trade of the current week (Monday 00:00 UTC onward) by ROI and by absolute profit.
list_accountsConfigured exchange accounts. API credentials are never returned — only whether each account has them.
list_alertsPrice alerts, optionally filtered by status.
create_alertCreates a price alert. The server checks the symbol is priced by the exchange before accepting it, and marks the alert triggered once the threshold is crossed.
cancel_alertCancels an active alert, keeping it on record.
delete_alertPermanently deletes an alert.
list_strategiesSaved strategies with their rules and status.
get_strategyA single strategy by id.
create_strategySaves a strategy. `rules` is free-form JSON — put entry/exit conditions and risk parameters in whatever shape suits, it is stored as given and not executed.
update_strategyUpdates any subset of a strategy's fields.
delete_strategyPermanently deletes a strategy.
ai_configWhether the server's AI layer has a provider key, and which models are registered.
analyze_marketRuns the server's AI layer over a candle window. Costs tokens on the server's configured provider — prefer get_candles when you want to reason over the data yourself.
analyze_performanceRuns the server's AI layer over realised performance across accounts. Costs tokens on the server's configured provider.
review_strategyRuns the server's AI layer over a saved strategy plus recent price action for its symbol. Costs tokens on the server's configured provider.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`
axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge
Axios is Vulnerable to Denial of Service via __proto__ Key in mergeConfig
Axios is vulnerable to DoS attack through lack of data size check
Axios: Header Injection via Prototype Pollution
AI_EFFORTAI_MAX_TOKENSAI_MODELThen set =claude-sonnet-4-6.AI_PROVIDERALERT_POLL_MSHow often active alerts are re-checkedANTHROPIC_API_KEYBYBIT_API_KEYSingle-account fallback; prefer the Accounts tabBYBIT_API_SECRETSingle-account fallback; prefer the Accounts tabBYBIT_BASE_URLBYBIT_TESTNETDATABASE_PATHWhere the SQLite file livesHOSTexchange balances and add or delete accounts. defaults to 127.0.0.1OPENAI_API_KEYGoes to OpenAI using OPENAI_API_KEYVALE_API_URLBYBIT_API_KEY_HEDGEBYBIT_API_SECRET_HEDGEREPORT_TITLEREPORTS_BOT_TOKENTELEGRAM_BOT_TOKENREPORTS_CHAT_IDTELEGRAM_CHAT_IDMODELModel id to use (MODEL is accepted as an alias)OPENROUTER_API_KEYRouted via https://openrouter.ai/api/v1USE_TESTNETtrue. Then check credentials before anything trades:PORTTool annotations
15/22 tools have annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
22/22 tools missing one or more hints — server_status (missing: destructiveHint, idempotentHint, openWorldHint); get_candles (missing: destructiveHint, idempotentHint, openWorldHint); get_price (missing: destructiveHint, idempotentHint, openWorldHint), +19 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tests exist
No test files found
Add tests that exercise each declared tool.
Secrets not logged
75 secret values sent to print/logger.error/logger.info/logger.warning
Redact or omit secret values from log output.
Production dependencies are patched
0 critical, 13 high severity in production deps — axios@1.8.4 (high), axios@1.8.4 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
2 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Dependency freshness
1/33 production deps stale: tailwindcss-animate@2023-08-28 (3y)
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/vw3st/crypto-monitor)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check