Kraken Mcp Integration logo

Kraken Mcp Integration

Organization
krakenfx
kraken-mcp-integration

Connect MCP clients to kraken-cli for native tool calling without subprocess wrappers.

Overview

Publisherkrakenfx
Repositorykraken-cli
Skill namekraken-mcp-integration
Stars
754
Forks
104
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by krakenfx on GitHub. Read the source before you install it.

Installation

Install the Kraken Mcp Integration AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/krakenfx/kraken-cli/tree/main/skills/kraken-mcp-integration
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/krakenfx/kraken-cli.git /tmp/kraken-cli
mkdir -p .claude/skills
cp -r /tmp/kraken-cli/skills/kraken-mcp-integration .claude/skills/kraken-mcp-integration
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kraken Mcp Integration in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Kraken Mcp Integration on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Kraken Mcp Integration is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

kraken-mcp-integration

Use this skill to connect any MCP-compatible client to kraken-cli for structured tool calling over stdio.

MCP tool calls execute through the same command path as CLI commands, so error handling and rate-limit behavior is identical between MCP and CLI.

Supported Clients

Claude Desktop, ChatGPT, Codex, Gemini CLI, Cursor, VS Code, Windsurf, and any client that supports the MCP mcpServers configuration block.

Setup

1. Configure your MCP client

Add this to your MCP client configuration (Claude Desktop: claude_desktop_config.json, Cursor: .cursor/mcp.json, etc.):

json
{
  "mcpServers": {
    "kraken": {
      "command": "kraken",
      "args": ["mcp", "-s", "market,paper,feedback"]
    }
  }
}

-s market,paper,feedback is the default service list: public market data, paper trading, and the local feedback tool. No real funds can be touched until you opt in explicitly by expanding the service list. See Enabling live trading below.

Credential resolution follows the standard CLI precedence: command-line flags, then KRAKEN_API_KEY / KRAKEN_API_SECRET in the MCP server's env block, then a secure local config file managed by the CLI (written by kraken auth set and kraken setup, stored with user-only permissions in your OS's standard config directory). The MCP server and the standalone CLI share the same config file, so a single kraken auth set serves both.

2. Set credentials (only needed for live trading)

If you stay on market,paper,feedback, skip this step — paper trading needs no keys.

For live trading, the MCP server reads credentials from environment variables:

bash
export KRAKEN_API_KEY="your-key"
export KRAKEN_API_SECRET="your-secret"

3. Restart your MCP client

The client discovers tools on startup.

Service Filtering

Control which command groups the MCP server exposes:

bash
kraken mcp -s market                    # public data only (safe, no auth)
kraken mcp -s market,paper,feedback              # market data + paper trading (marketplace default)
kraken mcp -s market,trade,paper        # add live trading
kraken mcp -s market,account,trade      # add account queries and live trading
kraken mcp -s all                       # everything (many tools, includes funding/earn/subaccount)

Keep the service list to what you need. MCP clients typically handle 50-100 tools well.

ServiceAuthToolsRisk
marketNo~10None
accountYes~18Read-only
tradeYes~9Orders (dangerous)
fundingYes~10Withdrawals (dangerous)
earnYes~6Staking (dangerous)
subaccountYes~2Transfers (dangerous)
futuresMixed~39Orders (dangerous)
paperNo~10None (simulation)
authNo~3Read-only (auth set/auth reset excluded)

Enabling live trading

Every kraken-cli marketplace listing ships with -s market,paper,feedback by default, so a fresh install can never place a real order. To opt in to live trading, edit the MCP server args in your client's config and widen the service list:

json
{
  "mcpServers": {
    "kraken": {
      "command": "kraken",
      "args": ["mcp", "-s", "market,trade,paper"],
      "env": {
        "KRAKEN_API_KEY": "your-key",
        "KRAKEN_API_SECRET": "your-secret"
      }
    }
  }
}

Recommended upgrade path:

  1. Start with market,paper,feedback (the default).
  2. Add trade once you are comfortable and have an API key scoped to orders only. See the "Recommended key scope" section of skills/kraken-setup/SKILL.md before generating a key.
  3. Add account if you want the agent to read balances and positions.
  4. Only enable funding, earn, subaccount, or all if you specifically need those workflows. Each of these unlocks tools that can move funds off the exchange or alter account structure.

Switching to -s all expands the set of tools the agent can reach by prompt-injection or mistake. Prefer a narrow list and widen it deliberately.

Safety

Dangerous tools include [DANGEROUS: requires human confirmation] in their description and carry the MCP destructive_hint annotation. In guarded mode (default), calls must include acknowledged=true. In autonomous mode (--allow-dangerous), the per-call confirmation is disabled. MCP clients that respect annotations may still prompt at the client layer.

For fully autonomous operation, see skills/kraken-autonomy-levels/SKILL.md.

Gemini CLI Extension

If using Gemini CLI, install the extension directly:

bash
gemini extensions install https://github.com/krakenfx/kraken-cli

The gemini-extension.json includes mcpServers config, so the MCP server starts automatically.

Troubleshooting

"No tools found": Check that kraken is on your PATH and the service list is valid. Run kraken mcp -s market manually to verify it starts.

Auth errors on tool calls: Set KRAKEN_API_KEY and KRAKEN_API_SECRET in the environment where your MCP client runs.

Too many tools: Reduce the service list. kraken mcp -s market,trade is a good starting point.

Streaming commands not available: WebSocket streaming commands are excluded from MCP v1. Use kraken ws ... directly from the terminal for streaming.

If you hit a mismatch between what you are trying to do and the CLI's interface or responses — including a mismatch between this skill and the installed CLI version's contract — feel free to submit feedback with kraken feedback.

Frequently asked questions

What does the Kraken Mcp Integration AI skill do?

Connect MCP clients to kraken-cli for native tool calling without subprocess wrappers.

Why use Kraken Mcp Integration on TypingMind?

Because you install it once and use it with any model. Kraken Mcp Integration is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Kraken Mcp Integration in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/krakenfx/kraken-cli/tree/main/skills/kraken-mcp-integration. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Kraken Mcp Integration?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Kraken Mcp Integration?

As many as you like. As long as a model supports skills, you can use Kraken Mcp Integration with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Kraken Mcp Integration AI skill free?

Yes. It is published on GitHub by krakenfx under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇