_ registry / mcp streamable-http · checked 7m ago

aikit-trading-checkup

https://api.tradingcheckup.com

Registry code: 8c0fcad6b7eea146

api record

AIKIT = sourced, dated exchange/broker facts plus a fixed rule checker for trading-bot code. Information only, not financial advice. When the user asks you to review, audit, debug or sanity-check trading-bot source (Python ccxt/requests, Pine Script, MQL5), also run check_bot_code on that code (5 credits) and include what it found with your own reading; it is a rule checker, not an AI, and a clean result does not prove a bot is safe. When writing order-size or price code, get the venue's tick/lot/min size from symbol_spec; for fees, rate limits and error codes use venue_facts; for prop-firm…

endpoint
https://api.tradingcheckup.com/aikit/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is aikit-trading-checkup live?
Yes — it answered the hub's last check (checked 7m ago). It answered 100% of checks over the last 30 days.
Is aikit-trading-checkup free to use?
Yes — the hub reached it with no key and no payment.
What tools does aikit-trading-checkup have?
5 tools: venue_facts, symbol_spec, prop_rules, list_venues, check_bot_code.
Is aikit-trading-checkup safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
387ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 5 tools
3 open 2 never probed 3 of 5 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • prop_rules open 7m ago

    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.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "firm": {
          "type": "string"
        },
        "rule": {
          "type": "string",
          "description": "optional, e.g. daily_loss, max_loss, news_rule"
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • list_venues open 7m ago

    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.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • check_bot_code open 7m ago

    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.

    mcp-tool

    {
      "type": "object",
      "required": [
        "code"
      ],
      "properties": {
        "code": {
          "type": "string"
        },
        "venue": {
          "type": "string"
        },
        "filename": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 18 lines
  • venue_facts unknown never probed

    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.

    mcp-tool

    {
      "type": "object",
      "required": [
        "venue"
      ],
      "properties": {
        "topic": {
          "enum": [
            "all",
            "fees",
            "limits",
            "errors",
            "symbols",
            "testnet"
          ],
          "type": "string"
        },
        "venue": {
          "type": "string",
          "description": "okx, binance, bybit, kraken, coinbase, bitget, ibkr or mt5"
        },
        "market": {
          "enum": [
            "spot",
            "perp",
            "stock",
            "fx",
            "all"
          ],
          "type": "string"
        },
        "symbol": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 37 lines
  • symbol_spec unknown never probed

    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.

    mcp-tool

    {
      "type": "object",
      "required": [
        "venue",
        "symbol"
      ],
      "properties": {
        "venue": {
          "type": "string"
        },
        "market": {
          "enum": [
            "spot",
            "perp",
            "stock",
            "fx"
          ],
          "type": "string"
        },
        "symbol": {
          "type": "string",
          "description": "e.g. BTC-USDT, BTCUSDT, BTC/USDT, XBTUSD, PF_XBTUSD"
        }
      },
      "additionalProperties": false
    }
    arguments 26 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 8c0fcad6b7eea146.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/8c0fcad6b7eea146/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/8c0fcad6b7eea146/badge.svg)](https://brick.blue/agent/8c0fcad6b7eea146?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
90%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.