Leverate Opens a Back-Office MCP Server, Pointing AI at Broker Data Instead of Trades

Wednesday, 01/07/2026 | 07:57 GMT by Damian Chmiel
  • The broker technology vendor is connecting AI assistants like Claude to a firm's CRM, funnels and risk data rather than to trade execution.
  • The release lands in a crowded MCP wave, though most rivals have aimed the same protocol at traders placing orders.
Leverate

Leverate has released a Model Context Protocol (MCP) server that lets brokers connect AI assistants such as Claude and ChatGPT to their own operational data. The tool points the technology at a firm's CRM, marketing funnels and risk activity rather than at trade execution, the company said.

That framing sets it apart from most of the recent MCP wave, which has wired AI agents into live trading accounts so clients can place orders by prompt.

A recent FM Intelligence study counted at least 10 brokers and platform vendors that connected agents to client accounts in the first half of 2026, with Anthropic's Claude named in nine of them.

Leverate is aiming lower down the stack, at the broker's business rather than the trader's account.

What the Server Actually Does

The Model Context Protocol is an open standard, backed by Anthropic, for connecting AI models to the systems where a company's data already sits.

Leverate said its server exposes a broker's permissioned data across the CRM, Broker Portal and trading platform through a single connection, so staff can question it in plain language instead of building a report or waiting on a developer.

According to the company, brokers can ask an assistant to trace how leads move from registration through KYC to a first deposit, group traders into segments by behavior, or flag patterns across exposure and flow for a risk team to review.

The firm said each answer is meant as a starting point, with the broker deciding what to act on.

The CRM piece is not new ground for Leverate, which has spent years wiring client-management tools into its stack, including an AltimaCRM integration with Intivion.

Leverate did not disclose pricing, and described the release as a step toward becoming what it calls the "AI operating system for brokers."

A Crowded Field, Aimed Mostly at the Trader

Broker technology firms have spent much of 2026 racing to attach the same protocol to their platforms, though most have pointed it at execution .

Spotware opened its cTrader platform to AI agents in May through two MCP servers under the name AI Agent Connect, letting outside tools place trades and manage positions by prompt.

ThinkMarkets followed in June with ChelseaAI, a server that lets an AI place orders without the trader ever logging in.

Around the same time, Capital.com shipped an MCP plugin for its MENA clients that runs trades behind a two-step confirmation. All three put the AI next to the order book.

Leverate's server does not touch execution at all.

The nearest peer is MahiMarkets, which extended an automated pricing and risk engine to Dubai brokers in June, though that system makes its own calls rather than opening a broker's data to an assistant the staff choose.

Leverate's Second AI Move in a Month

Ran Strauss, the CEO of Leverate
Ran Strauss, the CEO of Leverate

The MCP server is not the firm's first AI release of the summer. In June, Leverate bundled an AI chat assistant into its trading platform that answered trader questions while giving brokers a record of what clients searched for.

Ran Strauss, Leverate's chief executive and co-founder, said brokers "have been sitting on rich data without an easy way to ask it questions." He said the open standard lets firms connect tools they already use while keeping the broker in control of any action taken.

Leverate cited Anthropic figures of more than 10,000 active public MCP servers and over 97 million monthly SDK downloads by December 2025, alongside a 2024 Bank of England and FCA survey showing roughly three-quarters of UK financial firms already use AI in some form.

The company, which has operated for more than 19 years, said the server will connect to whichever assistant a broker's team prefers.

Leverate has released a Model Context Protocol (MCP) server that lets brokers connect AI assistants such as Claude and ChatGPT to their own operational data. The tool points the technology at a firm's CRM, marketing funnels and risk activity rather than at trade execution, the company said.

That framing sets it apart from most of the recent MCP wave, which has wired AI agents into live trading accounts so clients can place orders by prompt.

A recent FM Intelligence study counted at least 10 brokers and platform vendors that connected agents to client accounts in the first half of 2026, with Anthropic's Claude named in nine of them.

Leverate is aiming lower down the stack, at the broker's business rather than the trader's account.

What the Server Actually Does

The Model Context Protocol is an open standard, backed by Anthropic, for connecting AI models to the systems where a company's data already sits.

Leverate said its server exposes a broker's permissioned data across the CRM, Broker Portal and trading platform through a single connection, so staff can question it in plain language instead of building a report or waiting on a developer.

According to the company, brokers can ask an assistant to trace how leads move from registration through KYC to a first deposit, group traders into segments by behavior, or flag patterns across exposure and flow for a risk team to review.

The firm said each answer is meant as a starting point, with the broker deciding what to act on.

The CRM piece is not new ground for Leverate, which has spent years wiring client-management tools into its stack, including an AltimaCRM integration with Intivion.

Leverate did not disclose pricing, and described the release as a step toward becoming what it calls the "AI operating system for brokers."

A Crowded Field, Aimed Mostly at the Trader

Broker technology firms have spent much of 2026 racing to attach the same protocol to their platforms, though most have pointed it at execution .

Spotware opened its cTrader platform to AI agents in May through two MCP servers under the name AI Agent Connect, letting outside tools place trades and manage positions by prompt.

ThinkMarkets followed in June with ChelseaAI, a server that lets an AI place orders without the trader ever logging in.

Around the same time, Capital.com shipped an MCP plugin for its MENA clients that runs trades behind a two-step confirmation. All three put the AI next to the order book.

Leverate's server does not touch execution at all.

The nearest peer is MahiMarkets, which extended an automated pricing and risk engine to Dubai brokers in June, though that system makes its own calls rather than opening a broker's data to an assistant the staff choose.

Leverate's Second AI Move in a Month

Ran Strauss, the CEO of Leverate
Ran Strauss, the CEO of Leverate

The MCP server is not the firm's first AI release of the summer. In June, Leverate bundled an AI chat assistant into its trading platform that answered trader questions while giving brokers a record of what clients searched for.

Ran Strauss, Leverate's chief executive and co-founder, said brokers "have been sitting on rich data without an easy way to ask it questions." He said the open standard lets firms connect tools they already use while keeping the broker in control of any action taken.

Leverate cited Anthropic figures of more than 10,000 active public MCP servers and over 97 million monthly SDK downloads by December 2025, alongside a 2024 Bank of England and FCA survey showing roughly three-quarters of UK financial firms already use AI in some form.

The company, which has operated for more than 19 years, said the server will connect to whichever assistant a broker's team prefers.

About the Author: Damian Chmiel
Damian Chmiel
  • 3696 Articles
  • 114 Followers
About the Author: Damian Chmiel
Damian Chmiel is a Senior Analyst & Editor at Finance Magnates with more than 15 years of experience in the CFD and online trading industry. Active as both a trader and journalist since 2010, he focuses on broker coverage, fintech innovation, and regulatory developments across Europe, the Middle East, and Asia. His work includes interviews with C-level leaders at major brokerages and fintech platforms, as well as co-authoring Finance Magnates’ quarterly industry benchmarking reports. Damian’s reporting is data-driven, market-aware, and grounded in direct industry engagement. His analysis and commentary have also been cited by external media outlets, including Investing.com, Binance, The Asset, Stockhead, and Dispatch. Education: MA in Finance and Accounting, Cracow University of Economics
  • 3696 Articles
  • 114 Followers

More from the Author

Retail FX

!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|} !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}