# cTrader Admin MCP server: ChatGPT and Claude enter broker workflows > cTrader Admin 10.4 introduces an MCP server that securely connects ChatGPT, Claude and other AI assistants to broker data for trading investigations, risk analysis, account reviews and more. Source: https://www.spotware.com/news/ctrader-admin-mcp-server/ By Spotware team Published 09 Nov 20264 min read AI is moving into broker operations. cTrader introduces the cTrader Admin MCP server in version 10.4, enabling managers to connect compatible AI apps, including ChatGPT Desktop and Claude, to broker data. Through natural-language requests, managers can investigate trading events, review exposure and account performance and inspect platform settings within their existing access permissions. Finding out why an order was rejected or how a disputed trade was executed takes time. A manager has to check the order history, the linked deals, the account permissions and the symbol settings, then put the picture together. The cTrader Admin MCP server hands that job to an AI assistant. It collects relevant records and prepares an analysis, helping the manager review the evidence, identify further checks and decide what action is needed. ### Trading incidents and client complaints A typical case is a client complaint about a rejected order. The assistant retrieves the order history and the linked deals, reconstructs the sequence of events and checks it against the account permissions, symbol settings and trading conditions. For a disputed execution price, it compares the recorded deal with the order timeline, pricing settings and historical market data. If the evidence does not point to an exact cause, the assistant says what remains uncertain and which checks are needed. ### Risk and exposure Risk review works the same way, but across the whole client base. A manager can ask which symbols carry the largest exposure at the moment and which accounts contribute to that exposure. The assistant breaks down bought, sold and net volumes by symbol, currency and book, treats A-book and B-book separately and converts notional values into one currency for comparison. For open positions, it identifies the largest unrealised gains and losses and traces them to the accounts behind them. ### Account reviews Which accounts are closest to stop-out? To answer, the assistant compares equity, used margin, free margin and margin level with the settings of the relevant group. Realised results can be reviewed the same way: a manager picks a period, compares accounts and looks at weekly trading activity. Everything is based on retrieved account data. The assistant does not monitor accounts automatically and makes no predictions. ### Financial investigations Balance movements can be examined too. The assistant retrieves the charges recorded for the position and checks them against the group and symbol settings, swap rates and charging schedules. Anything the data does not confirm is marked for further verification. It can also review available balance and bonus histories, alongside trading records, to explain deposits, withdrawals, credit adjustments, fees and other recorded movements. ### Configuration review The assistant can also look at the platform setup. It reads symbol specifications, sessions, limits and markups, compares them with the broker’s requirements and lists the differences in a checklist for manual review. For prices, it goes through historical bars and ticks and flags gaps and other unusual behaviour that need further investigation. ### Setup and access control The manager enables the MCP server in cTrader Admin and connects a supported AI application, such as ChatGPT Desktop, Claude Desktop, Claude Code, Codex CLI or another MCP-compatible AI application. The server runs locally within cTrader Admin. Access to broker data requires an authenticated manager session and follows that manager’s permissions, so the assistant cannot retrieve anything outside their authorised scope. Every operation is read-only. The assistant gathers data from different parts of the platform and reports its findings in one conversation, but it cannot execute trades or change account settings or configuration. Findings still need to be verified before any operational decision. > Irina Olyaeva, Product Manager for cTrader Admin at Spotware, commented: _"Our goal is to make AI genuinely useful for the people running brokerages every day. A manager investigating a trading complaint should be able to ask a question and get the relevant evidence without spending time collecting records from different sections of the platform. With the cTrader Admin MCP server, we're making broker data easier to work with while keeping access and operational decisions firmly under the broker's control."_ ### **About Spotware Systems** [Spotware Systems](https://www.spotware.com/) is a leading fintech company founded in 2010, based in Limassol, Cyprus, with a global team of 200+ professionals. It designs and delivers innovative trading technology and custom solutions for brokers worldwide, supporting long-term growth and scalability. Spotware’s solutions include cTrader, the flagship trading platform, cBridge, a standalone, fixed-price liquidity bridge for all platforms and cAntifraud, an AI-powered fraud detection solution. Spotware’s expertise is consistently recognised with multiple international industry awards, including Best Trading Platform, Best Services for Partners and Best Mobile Trading App.