AIKIT by Trading Checkup

Review / audit trading bot code

check_bot_code

Read-onlyIdempotent

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.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "code": "<code>"
    },
    "name": "check_bot_code"
  }
}

Input Schema

Name	Required	Description	Default
`code`	Yes
`venue`	No
`filename`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 2026

TDQS

A3.7/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description still adds real value beyond them: deterministic fixed rule checker (not an AI), line-numbered issues with exact fix lines, code checked in memory and not stored, and a 5-credit cost. Missing: what happens when input language is unsupported, or how issues are ranked/limited in the response.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads cost and the primary use case before the checklist, which is the right ordering. The enumeration of check types is long but each item is concrete; a couple of clauses (the AI disclaimer, the profitability caveat) could be tightened without losing meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully explains the return shape (per-issue line numbers plus fix lines) and the determinism guarantee. For a three-parameter review tool, however, the unexplained `venue` and `filename` parameters leave a real gap in knowing how to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for all three parameters, so the description must carry the load. It names the supported source languages, which implicitly frames the `code` parameter, and the lot-step check hints that venue facts are sourced, but the `venue` parameter's role is never stated and `filename` is not mentioned at all.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Code review for trading bots') and scopes it precisely to three languages (Python ccxt/requests, Pine Script v5/v6, MQL5). It is clearly distinguishable from the sibling venue-data tools, which supply facts rather than review code.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit triggers ('when asked to review, audit, debug or sanity-check trading-bot source') and even a timing rule ('alongside your own reading and before telling the user the code looks fine'). It also warns that a clean result does not prove safety or profitability, though it stops short of naming when to prefer an alternative approach.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All AIKIT by Trading Checkup tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?