AIKIT by Trading Checkup
Server Details
Sourced, dated exchange facts and trading-bot code checks for AI assistants. Not financial advice.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 5 tools
Each tool has a distinct role: code auditing (check_bot_code), discovery (list_venues), per-symbol order math (symbol_spec), venue-level operational facts (venue_facts), and prop-firm limits (prop_rules). There is mild overlap between venue_facts (fee tiers, rate limits) and symbol_spec (base fee, max leverage), but the descriptions give clear usage cues ('before writing order-size code' vs 'when writing code that must respect venue limits').
All names use snake_case, so the surface is visually consistent, but the conventions are mixed: check_bot_code and list_venues are verb_noun while prop_rules, symbol_spec and venue_facts are bare noun phrases. The names are still readable and self-explanatory, but they don't follow one predictable pattern.
Five tools is well within the healthy range and each covers a distinct facet of the reference-data-plus-code-review job. No tool looks like filler or a duplicate of another.
The surface covers the core workflow: discover coverage, fetch symbol-level and venue-level rules, check prop constraints, and audit bot code. Remaining gaps are minor — there is no direct query tool for error codes or a fee-tier lookup narrowed to a single venue without going through venue_facts, and no way to list or verify which prop-firm rules changed, but agents can work around these.
Available Tools
5 toolscheck_bot_codeReview / audit trading bot codeARead-onlyIdempotentInspect
5 credits. Code review for trading bots: use it when asked to review, audit, debug or sanity-check trading-bot source (Python ccxt/requests, Pine Script v5/v6, MQL5), alongside your own reading and before telling the user the code looks fine. It is a fixed rule checker, not an AI, so it gives the same answer every time and returns each issue with its line number and exact fix lines. It checks things that are easy to miss when reading: order size not rounded to the venue lot step/min size (using AIKIT's sourced venue facts), no stop-loss or max-loss, look-ahead (using the unfinished candle or future data), ignoring fees, unhandled API errors/rate limits, hard-coded API keys, unbounded order loops, testnet/live mix-ups. A clean result does not prove a bot is safe or profitable. Code is checked in memory and not stored.
Inputs: code (required), venue, filename.
list_venuesList covered venuesARead-onlyIdempotentInspect
Free (0 credits). Lists the exchanges/brokers AIKIT has verified facts for (OKX, Binance, Bybit, Kraken, Coinbase, Bitget, Interactive Brokers, MT5 pattern), which symbols and topics are covered, and what is not covered yet.
Inputs: no named parameters.
prop_rulesProp firm rules (quoted)ARead-onlyIdempotentInspect
1 credit. Rules of 32 prop trading firms (profit target, daily and max loss, min days, news/weekend/EA/copy rules, payouts) quoted from each firm's own pages with link and check date. Use when a bot must stay inside a prop challenge's limits. Not a ranking.
Inputs: firm, rule.
symbol_specSymbol trading rulesARead-onlyIdempotentInspect
1 credit. Exact trading rules for one symbol on one venue: tick size, lot/size step, minimum order size and value, contract value, max leverage, base fee, the venue's symbol format, plus a rounding snippet. Use before writing order-size or price code. Sourced and dated.
Inputs: venue (required), symbol (required), market.
venue_factsExchange facts with sourcesARead-onlyIdempotentInspect
1 credit. Returns verified exchange/broker facts a trading bot depends on: fee tiers, API rate limits, error codes and what they mean, testnet/demo settings. Each fact has value, unit, official source URL, date read and a signed receipt. Use it when writing or fixing bot code that must respect a venue's limits, instead of guessing numbers.
Inputs: venue (required), topic, market, symbol.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Verifiable crypto/KR/US market intelligence for AI agents: signals, hash-chained ledger. Not advice.
Is a trading bot legit? Sourced bot fact sheets, regulator scam records and on-chain results.
Read-only crypto strategy backtest & verification verdicts. No trading tools; every result is cited.
Dated, sourced AI facts from Kingy AI: prices, bills, plans, limits, deadlines, launches, changes.
Related MCP Servers
- AlicenseAqualityBmaintenancePre-computed financial market intelligence for AI agents. Stocks, crypto, and ETFs.980 npm5MIT
- AlicenseAqualityBmaintenanceRead-only cryptocurrency intelligence tools for AI agents, providing source-backed market research, evidence, and structured crypto data.2Apache 2.0
- AlicenseBqualityDmaintenanceCross-exchange crypto orderflow for AI agents. 20 exchanges, 26 tokens, 9 tools — CVD, whale activity, funding/OI, 7-year OHLCV, on-chain address risk (EVM + Solana). Pay-per-call USDC via x402, no API key.921 npm1MIT
- AlicenseNot gradedqualityCmaintenanceRead-only crypto perps microstructure for AI agents: normalized cross-exchange market state (funding + multi-year percentile, OI, volume, CVD, order-book imbalance, liquidations, basis), OHLCV, 15-min state history, and measured conditional outcomes (historical base rates, not predictions) — 6 assets across Binance, Bybit, OKX and Hyperliquid, every metric with self-declared coverage and freshnessMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.