Coinrule MCP

Coinrule MCP: Build AI Trading Agents Through Natural Language

*Last updated July 22, 2026*

AI is changing the way traders interact with financial markets. Instead of relying exclusively on dashboards, configuration panels, charts, and manually constructed automation, traders can increasingly use AI assistants as an intelligent interface between a trading idea and the infrastructure required to analyse, test, automate, and monitor it.

Coinrule MCP https://coinrule.com/mcp/ brings this conversational approach to automated trading.

By connecting a compatible AI assistant such as ChatGPT, Claude, Gemini, Grok, or another MCP-compatible client to a Coinrule account, traders can use natural-language instructions to inspect portfolios, analyse running strategies, explore trading ideas, perform historical backtests, create automated strategies, monitor signals, and manage trading agents.

The objective is not simply to add a chatbot to a trading platform. It is to create a more intelligent layer for interacting with algorithmic trading infrastructure.

Instead of navigating through multiple interfaces to answer questions such as:

Which of my strategies generated the latest signal?

or:

How is my portfolio currently allocated across connected venues?

a trader can ask an AI assistant directly.

More advanced workflows can go further:

Design a momentum strategy for BTC that only enters when the broader trend is positive, include defined risk controls, explain the logic, and backtest the configuration before I consider running it.

The AI assistant interprets the intention behind the request and uses the authorised Coinrule MCP tools required to perform the relevant operations. Coinrule continues to provide the strategy, execution, validation, portfolio, and market-connectivity infrastructure underneath the conversation.

This creates a new model for AI trading: the trader defines the objective, the AI helps translate that objective into structured actions, and Coinrule provides the controlled automation layer through which those actions are executed.

[!WARNING]

A Read + Write connection can launch strategies that trade real funds. Start with Read-only access or paper trading, review every request, and make the venue and capital amount explicit.

Connect in under a minute

1. Choose a compatible client such as Claude, ChatGPT, Grok, Cursor, or VS Code.
2. Add this remote MCP server:

   https://cloud.coinrule.com/mcp

1. Sign in to Coinrule when your client opens the OAuth window.
2. Choose Read-only or Read + Write, then try:

   Show my Coinrule bots and how each one is doing.

You need a Coinrule Cloud account and an AI client that supports remote MCP connectors with OAuth. Connect an exchange or broker to trade live, or use paper trading without one.

Agent Plugin

This repository is packaged as an Agent Plugins 1.0.0 plugin for compatible clients and directories, including Cursor:

• plugin.json contains portable plugin metadata.
• mcp.json declares the hosted Coinrule MCP server using the Streamable HTTP transport.
• server.json contains the official MCP Registry metadata.

Agent Plugins 1.0.0 intentionally leaves OAuth to the client. When the plugin connects to https://cloud.coinrule.com/mcp, the client discovers Coinrule's OAuth 2.1 endpoints and asks the user to authorize Read-only or Read + Write access.

---

From Trading Bots to AI Trading Agents

Traditional trading automation usually begins with configuration.

A trader chooses an asset, selects an indicator, defines an entry condition, configures an exit, chooses a position size, and decides where the strategy should run.

This approach can be effective, but it requires the trader to translate an investment or trading thesis into the structure expected by the software.

AI trading introduces a different interaction model.

Instead of beginning with a configuration screen, the process can begin with intent.

For example:

I want to investigate whether short-term weakness in Ethereum creates attractive entries when the longer-term trend remains bullish.

An AI assistant can help break this idea into questions:

• How should short-term weakness be measured?
• How should the broader trend be defined?
• Which timeframe should be used?
• What conditions invalidate the setup?
• How much capital should be allocated?
• How frequently should the strategy be allowed to trade?
• What stop-loss or exit logic should apply?
• How would the strategy have behaved historically?

The conversation can then move from an abstract idea toward a structured trading strategy.

With Coinrule MCP, the AI assistant can interact with authorised Coinrule functionality during this process. Depending on the permissions granted, that may include reviewing portfolio information, examining existing strategies, creating strategies, running backtests, launching baskets, or managing trading automation.

The important distinction is that the language model is not replacing the trading infrastructure.

The AI assistant acts as the conversational and reasoning interface. Coinrule remains the underlying system responsible for connecting strategies with supported exchanges, brokers, assets, portfolio data, and automation functionality.

---

What Is Coinrule MCP?

MCP stands for Model Context Protocol.

It is an open protocol designed to allow compatible AI applications to interact with external tools and services.

Coinrule operates an official remote MCP server that allows supported AI assistants to connect to Coinrule Cloud. Once the connection has been authorised, the assistant can use the Coinrule tools available within the permission scope selected by the user.

From the trader's perspective, the interaction remains conversational.

You might ask:

Show me my active Coinrule strategies and summarise their recent activity.

The AI assistant determines which authorised tools are required, requests the information through Coinrule MCP, and then presents the results in a conversational format.

You do not necessarily need to know the names of the underlying tools or understand Coinrule's internal API structure.

This abstraction is one of the most significant aspects of AI-assisted trading.

The trader can concentrate on what they want to understand or accomplish, while the AI assistant handles much of the translation between natural language and structured software operations.

Coinrule MCP is therefore not a separate exchange, broker, trading account, or custody solution. It is another interface through which authorised Coinrule functionality can be accessed.

Strategies created or managed through an AI assistant remain part of the broader Coinrule trading environment rather than existing in a disconnected AI-only system.

---

How AI Trading Through Coinrule MCP Works

A typical MCP interaction can be understood as a four-layer process.

1. The Trader Defines an Intention

You begin by describing a task in natural language.

For example:

Analyse my current strategies and identify which ones have produced signals during the last 24 hours.

Or:

Help me design a trend-following strategy for BTC using a moving-average filter and a volatility-based risk condition.

The prompt can be simple or highly detailed.

2. The AI Assistant Interprets the Request

The language model analyses the instruction and determines what information or actions may be necessary.

For an account-analysis request, it may need portfolio or strategy information.

For strategy development, it may need to construct and validate a configuration.

For historical analysis, it may need to run or retrieve a backtest.

3. Coinrule MCP Provides Authorised Tools

The assistant can call only the Coinrule functionality permitted by the user's connection.

A Read-only connection is intended for information retrieval and analysis.

A Read + Write connection provides additional capabilities for supported strategy creation and management actions.

4. Coinrule Handles the Underlying Trading Infrastructure

Coinrule remains the operational layer responsible for the relevant strategy, account, portfolio, backtesting, and market-connectivity functionality.

The AI assistant becomes an interface to that infrastructure rather than receiving unrestricted access to the trading environment.

This separation matters.

An AI model may be effective at interpreting objectives and helping users reason about strategies, but trading actions still need structured infrastructure, authentication, permissions, validation, and execution controls.

Coinrule MCP is designed to connect these two layers: AI reasoning and trading automation.

---

The AI Trading Lifecycle

One of the most useful ways to understand Coinrule MCP is to look at the complete lifecycle of an AI-assisted trading strategy.

Instead of viewing AI trading as a single prompt that immediately produces a trade, a more disciplined workflow can involve multiple stages.

1. Understand the Current Portfolio

Before creating another strategy, an AI assistant can help you understand what is already running.

With appropriate read permissions, you may be able to ask questions about balances, holdings, open positions, strategies, performance, and recent trading activity.

For example:

Summarise my current Coinrule portfolio and identify my largest asset exposures.

Or:

Show my active strategies, their current status, and the most recent signal generated by each one.

This turns the AI assistant into a conversational layer for portfolio intelligence.

Rather than manually moving between individual accounts and strategies, the trader can begin with a broader question and progressively investigate the areas that matter.

A conversation might evolve like this:

Which strategy currently has the largest open exposure?

Then:

What conditions caused that strategy to enter?

Then:

Show me its recent activity.

Then:

Compare its behaviour with my other momentum strategies.

This ability to move from a high-level portfolio question into increasingly detailed analysis is an important characteristic of conversational AI trading.

---

2. Express the Trading Thesis in Natural Language

Most trading strategies begin as ideas rather than software configurations.

Examples might include:

• Buy temporary weakness during a long-term uptrend.
• Reduce exposure when market volatility rises significantly.
• Accumulate an asset periodically rather than attempting to time every entry.
• Follow strong momentum but exit when the trend deteriorates.
• Rebalance a portfolio when allocations move outside predefined ranges.

An AI assistant can help convert these ideas into more precise specifications.

For example:

I want to buy significant dips in BTC, but only when the longer-term trend remains positive.

The assistant can help identify the missing variables.

What constitutes a significant dip?

What defines the long-term trend?

How frequently can the strategy enter?

Should the strategy scale into positions?

Where should risk be limited?

When should profits be taken?

The advantage of this approach is that strategy creation can become an iterative conversation rather than a one