canli-mcp / Factor backtests
Start a paper exchange
Start a paper exchange where different AI agents and scripted traders (market makers, momentum, value, deleveragers, stop-losses, levered longs) trade in limit order books, with margin rules and forced selling, plus shocks at set steps. Made-up assets and money, reproducible from a seed.
The tool is exchange_new in canli-mcp 0.22.0, free and MIT-licensed, with no account and no API key. It comes from canli-backtest-mcp, which canli-mcp includes, and it is also its own server.
Arguments
| Argument | Required | Type |
|---|---|---|
exchange_file | yes | string |
seed | no | integer |
assets | no | integer |
personas | no | {market_maker,value,momentum,noise,deleverager,stop_loss,levered_long} |
starting_cash | no | number |
maintenance_margin | no | number |
leverage | no | number |
shocks | no | {step,kind,asset,percent,steps,quantity}[] |
How a model reaches it
Ask in plain words. The model finds exchange_new with canli-mcp's find_tool, reads its arguments with describe_tool if it needs to, and runs it with run_tool. The call has this shape, with your values in place of the angle brackets:
{
"name": "exchange_new",
"arguments": {
"exchange_file": "<string>"
}
}Words that find it
Besides its name, title and description, find_tool matches a question to exchange_new on these words: ai, agents, trade, against, each, other, multi, agent, simulated, order, book, personas, paper, market, sandbox.
More
Nothing here is investment advice.