just now
@b2broker, a global fintech solutions provider for financial institutions, has expanded the AI capabilities of its B2TRADER platform with Model Context Protocol (MCP) support and a new in-terminal AI Chat. Traders can now connect Claude, ChatGPT or a custom AI agent to their accounts, analyse positions and, with the necessary permissions, execute trading instructions.
The release is the latest stage in the company’s wider AI development programme for B2TRADER. Earlier this year, B2BROKER introduced an embedded AI Assistant offering market forecasts, sentiment indicators, recommendation scores and trading signals. A subsequent summer update added external market statistics, including prices, market capitalisation, 24-hour trading volume and historical highs and lows, as well as recent third-party asset news. The latest integration extends these capabilities from market analysis to account-specific interaction and trading execution.
AI Agents Gain Access to Trading Functions
Through MCP, traders can give connected agents natural-language instructions such as “close all profitable positions” or “set a stop-loss on every open position.” Agents can also retrieve market data, review portfolios and examine account history.
Brokers determine how far these connections can go. Read-only access permits analysis and monitoring while excluding trading tools entirely, making it suitable for AI marketplaces. Full access enables authorised agents to place, modify or close trades. Brokers can disable MCP or choose either access level for their deployment, and each agent is restricted to accounts belonging to the trader who authorised it.
Arthur Azizov, Founder and CEO, B2BROKER Group
Arthur Azizov, Founder and CEO, B2BROKER Group said:
“For brokers, adding AI to a terminal raises an immediate question: who decides what an assistant can actually do? A trader might need analysis in one situation and automated execution in another. The broker has to define those boundaries. Our approach is to give both sides that flexibility while keeping account permissions and execution controls explicit.”
Separately, the new AI Chat operates inside the B2TRADER web terminal using the same MCP layer. Traders can ask about markets, open positions or platform features without leaving the trading screen. Trading actions proposed through the in-terminal chat require explicit confirmation. External agents granted full access follow a different model and can execute permitted trades without individual order confirmations.
For brokerage businesses, B2BROKER expects the in-terminal chat to reduce routine first-line support enquiries, while agent connectivity gives brokers an additional point of distinction when prospective clients compare trading terminals.
Found this interesting? Become a member of LiquidityFinder and get daily industry news direct to your inbox — join here.
