Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions
Directory / onv-mcp
onv-mcp
by onv.codes · https://onv.codes/mcp
量化策略回测、组合配置与多交易所执行（14 家通道）
11 of 11 checks · 5 Nov 2026
At a glance
- Runs where
- On their server. What you send to it goes to them.
- What you need
- Nothing: it answered without a login
- Tools
- 44 tools
- Its own safety labels
- 28 read-only, 16 labeled as deleting or destroying
- Memory it takes
- About 6,000 tokens of your AI's memory, just for its tool descriptions
- Largest answer
- About 3533 KB in our test
- Tools that look alike
- 3 pairs of tools with nearly the same description, so the AI may pick the wrong one
- Speed
- Average answer in our test: 572 ms
Tokens are an estimate: the characters in its tool names, descriptions and inputs, divided by 4. The exact number depends on your AI model. Safety labels are what the server says about itself. From our latest test, 5 Nov 2026.
Is onv-mcp server safe?
- None of the hidden-instruction wordings we know were found in its 44 tool descriptions.
- Its error messages showed no secrets or internal details.
- 28 of its 44 tools are labeled read-only; the others may change or send things.
- Overall it scored 80/100 on 5 Nov 2026.
A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.
What this test does not check
- Its source code and packages.
- What a tool quietly does behind the scenes, such as writing a file or calling another service.
- Instructions hidden inside live tool answers. We only look for those in tool descriptions.
- Hidden instructions worded in a way our list doesn't know yet.
- Tools that could change something. Those are read, never run.
What QAmcp can and can't see · How to tell if an MCP server is safe · Hidden instructions · Prompt injection
Known security advisories
Not looked up yet. QAmcp tests how a server behaves. It does not scan source code.
What it can do
44 tools, in the server's own words.
platform_market_quoteread-only【行情】查询平台行情 K 线。参数 symbol 为交易标的（如 BTCUSDT / ETHUSDT），timeframe 可选 1m/5m/15m/30m/1H/4H/1D，limit 最大 299。返回该标的的 K 线数组。（cost: free）
platform_market_overviewread-only【行情】市场总览：主流币种快照、涨跌幅、成交量等市场状态概览。（cost: free）
platform_market_tickerread-only【行情】查询标的实时行情 ticker。参数 symbol 为交易标的（如 BTCUSDT，可选，缺省返回全部）。（cost: free）
platform_market_factorsread-only【行情】查询标的的市场因子数据（技术/宏观因子）。参数 symbol 为交易标的。（cost: free）
platform_symbol_searchread-only【行情】搜索平台支持的交易标的（币种/交易对）。参数 query 为关键词如 BTC。（cost: free）
platform_quick_analysisread-only【行情】对指定标的进行快速 AI 技术分析（拉取行情并生成分析结论）。参数 symbol 为交易标的，如 BTCUSDT。（cost: ≈ 22–28 credits/次（按实际 tokens 结算））
platform_list_agentsread-only【策略】列出平台上已发布的公开 Agent（策略），可按能力过滤与分页。参数 capabilities 可选（如 dex/defi）。（cost: free）
platform_get_agentread-only【策略】获取单个已发布的公开 Agent（策略）详情。参数 agentId 为策略 ID。（cost: free）
platform_plansread-only【账户与额度】查询平台订阅套餐列表（免费/付费 tier 与价格）。无需参数。（cost: free）
platform_my_strategiesread-only【策略】查询我创建的**策略市场/订阅域**策略列表（onv-backend `strategies` 表，按钱包地址归属，邮箱注册账号回退按数字 userId）。⚠️ 不含实盘策略——实盘策略在 `qd_strategies_trading`，请用 REST `GET /api/cex/strategies`（该端…
platform_backtest_resultread-only【策略】查询回测任务结果。参数 jobId 为 run_backtest 返回的任务 ID。（cost: free）
platform_backtest_historyread-only【策略】查询回测历史（可指定策略 ID 过滤）。参数 strategyId 可选。（cost: free）
platform_explain_backtestread-only【行情】解释一次回测「为什么亏 / 为什么没成交」。返回结构化卡片（数据区间、样本内外、最大回撤、数据缺失）与逐条原因。参数 runId / jobId / strategyId 至少给一个，三选一即可。（cost: free）
platform_subscription_statusread-only【账户与额度】查询对某 Agent 的订阅状态。参数 strategyId 或 agentId。（cost: free）
platform_subscription_listread-only【账户与额度】查询我的订阅列表。无需参数。（cost: free）
platform_user_subscriptionread-only【账户与额度】查询我的平台套餐订阅状态（当前套餐/到期时间）。无需参数。（cost: free）
platform_user_usageread-only【账户与额度】查询我的平台用量汇总（今日 bars / 本月 tokens / 剩余配额）。无需参数。（cost: free）
platform_run_backtest【策略】提交回测任务（写操作，需用户确认）。strategy 为策略代码字符串或已有策略 ID（纯数字），symbol 为交易标的如 BTCUSDT，timeframe 可选 1m/5m/15m/30m/1H/4H/1D。params 为指标参数覆盖（可选，写入引擎 indicator_params，与代码内 # @…
platform_manage_strategy【策略】管理自己的策略（写操作，需用户确认）。action 为 create / update / delete；update/delete 需要 strategyId；create/update 用 data 传策略数据（data.name 必填，data.strategy_category 为 dex/defi）…
platform_publish_strategy【策略】发布策略（写操作，需用户确认）。name 必填、category 为 dex/defi；code 为策略代码（可选）；subscription_price 订阅价格；strategy_id 可指定已有草稿发布。发布为公开上架。（cost: free）（写操作，外部调用将以 apikey 身份直接执行）
platform_subscribe_guide【账户与额度】订阅引导（写操作，需用户确认）：为指定 Agent 生成订阅引导信息（周期可选 day/week/month/year），确认后返回订阅链接与支付信息，不自动扣费。（cost: free）（写操作，外部调用将以 apikey 身份直接执行）
platform_subscribe_plan【账户与额度】购买平台套餐（写操作，需用户确认）：plan_id 必填（来自 platform_plans），period 可选 day/week/month/year，payment_method 可选 chain/x402。创建支付订单，支付在平台完成。（cost: free）（写操作，外部调用将以 apikey…
platform_ai_generate【策略】AI 生成策略代码（写操作，需用户确认）：输入自然语言 prompt（可选 context 传入研究流水线结构化学徒上下文），返回策略代码与解释。（cost: ≈ 36–48 credits/次（按实际 tokens 结算））（写操作，外部调用将以 apikey 身份直接执行）
platform_ai_optimize【策略】AI 多轮优化策略（写操作，需用户确认）：输入 prompt 描述策略目标，自动生成→回测→分析→改进（最多 maxRounds 轮，1-5，默认 3）。耗时较长。给了 initialCode 时第 1 轮不生成：直接回测这份既有代码作基线，第 2 轮起在其上改进（A3）。strategyParams 为指标…
and 20 more
Test results
Safe mode: only tools labeled read-only were run. How the test works
- !Ready for the newest MCP versionnote
1 warning
- !Uses an older MCP version (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
- !Every tool is describednote
3 warnings
- !platform_strategy_trades and platform_strategy_performance have nearly the same description (100% of their words are shared; the descriptions are identical), so an AI may not know which to pick
- !platform_get_agent and platform_subscription_status have nearly the same description (80% of their words are shared; the only difference: nothing vs "strategyid"), so an AI may not know which to pick
- !platform_set_risk_config and platform_reset_breaker have nearly the same description (60% of their words are shared; the only difference: "config" vs "recoverycode"), so an AI may not know which to pick
- !Tools work with good inputsnote
2 warnings
- !platform_market_overview: Answered with about 3533 KB of text. Many AI apps cut off tool answers this big, so the AI may never see the end of it.
- !platform_market_factors: Answered with about 1996 KB of text. Many AI apps cut off tool answers this big, so the AI may never see the end of it.
- –platform_run_backtest: Not run: labeled dangerous
- –platform_manage_strategy: Not run: labeled dangerous
- –platform_publish_strategy: Not run: labeled dangerous
- –platform_subscribe_guide: Not run: labeled dangerous
- –platform_subscribe_plan: Not run: labeled dangerous
- –platform_ai_generate: Not run: labeled dangerous
- and 32 more
- !Fast enoughnote
1 warning
- !platform_market_overview: Slowest tool: platform_market_overview (6.5 s): users will notice the wait
- and 3 more
- !Follows MCP best practices (not scored yet)note
3 tips (not scored)
- !16 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): platform_run_backtest, platform_manage_strategy, platform_publish_strategy, platform_subscribe_guide, platform_subscribe_plan, platform_ai_generat
- !44 tools don't say whether they reach outside services like the web (openWorldHint): platform_market_quote, platform_market_overview, platform_market_ticker, platform_market_factors, platform_symbol_search, platform_quick_analysis and 38 mo
- !8 tools answer with structured data but don't declare its shape (outputSchema): platform_market_quote, platform_market_overview, platform_market_ticker, platform_market_factors, platform_symbol_search, platform_list_agents and 2 more. If th
- ✓ConnectsConnected in 1.1 spass
- ✓Lists its toolsFound 44 toolspass
- ✓Tools are labeled safe or dangerousEvery tool has a safety labelpass
- ✓No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.pass
- ✓Bad inputs give a clean errorpass
All good
- ✓platform_market_quote: Refused missing required input "symbol" with a clear error
- ✓platform_market_quote: Refused wrong type for "symbol" with a clear error
- ✓platform_market_ticker: Refused wrong type for "symbol" with a clear error
- ✓platform_market_factors: Refused missing required input "symbol" with a clear error
- ✓platform_market_factors: Refused wrong type for "symbol" with a clear error
- ✓platform_symbol_search: Refused missing required input "query" with a clear error
- ✓platform_symbol_search: Refused wrong type for "query" with a clear error
- ✓platform_quick_analysis: Refused missing required input "symbol" with a clear error
- and 21 more
- ✓No secrets leakedChecked 78 error messages: no secrets or internal detailspass
- –Tools work togetherNo tool's answer could be fed into another tool, so there were no chains to test (not counted either way)not tested
Test it yourself
Free and open source. Same checks, same score.
npx qamcp-cli https://onv.codes/mcpShow this score on GitHub
Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.
[](https://qamcp.dev/s/codes-onv-onv-mcp.html)Score over time
- 5 Nov 202680
One test so far. New tests will show here.
Reviews
Coming soon: reviews from people who use onv-mcp, signed in with GitHub, one per person. Reviews never change the score.
QAmcp Monitor tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. Free for 1 server, no card.
Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works