kraken-mcp-integration
Connect MCP clients to kraken-cli for native tool calling without subprocess wrappers.
Best use case
kraken-mcp-integration is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Connect MCP clients to kraken-cli for native tool calling without subprocess wrappers.
Teams using kraken-mcp-integration should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/kraken-official-mcp-integration/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How kraken-mcp-integration Compares
| Feature / Agent | kraken-mcp-integration | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Connect MCP clients to kraken-cli for native tool calling without subprocess wrappers.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# 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,trade,paper"]
}
}
}
```
### 2. Set credentials
The MCP server reads credentials from environment variables:
```bash
export KRAKEN_API_KEY="your-key"
export KRAKEN_API_SECRET="your-secret"
```
Public market data and paper trading require no credentials.
### 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 # market data + paper trading
kraken mcp -s market,trade,paper # add live trading
kraken mcp -s market,account,trade # add account queries
kraken mcp -s all # everything (many tools)
```
Keep the service list to what you need. MCP clients typically handle 50-100 tools well.
| Service | Auth | Tools | Risk |
|---------|------|-------|------|
| market | No | ~10 | None |
| account | Yes | ~18 | Read-only |
| trade | Yes | ~9 | Orders (dangerous) |
| funding | Yes | ~10 | Withdrawals (dangerous) |
| earn | Yes | ~6 | Staking (dangerous) |
| subaccount | Yes | ~2 | Transfers (dangerous) |
| futures | Mixed | ~39 | Orders (dangerous) |
| paper | No | ~10 | None (simulation) |
| auth | No | ~3 | Read-only (auth set/auth reset excluded) |
## 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.Related Skills
Kraken Crypto Skill
Use the kraken_cli.py wrapper to query your Kraken account.
openclaw_kraken
Use a Bash CLI to query Kraken Spot and Futures APIs, inspect account state, run guarded trading and funding actions, and work with Kraken websocket payloads using OpenClaw-managed secrets.
kraken-ws-streaming
Real-time data streaming via WebSocket for spot and futures.
kraken-twap-execution
Execute large orders as time-weighted slices to reduce market impact.
kraken-tax-export
Export trade history, ledgers, and cost basis data for tax reporting.
kraken-subaccount-ops
Create and manage subaccounts with inter-account transfers.
kraken-stop-take-profit
Manage stop-loss and take-profit orders for risk-bounded positions.
kraken-spot-execution
Execute spot orders with validation, confirmation gates, and post-trade checks.
kraken-shared
Shared runtime contract for kraken-cli: auth, invocation, parsing, and safety.
kraken-risk-operations
Operational risk controls for live agent trading sessions.
kraken-rebalancing
Portfolio rebalancing to maintain target allocations across assets.
kraken-rate-limits
Understand Kraken API rate limits and adapt agent behavior when limits are hit.