Danube AI — Claude Code MCP server: what it does, how to install
A gateway connecting coding assistants to external services and workflows via a single HTTP endpoint. It handles tool execution, skill storage, and spending limits.
claude mcp add --transport http danube https://mcp.danubeai.com/mcpWhat Danube AI does
This MCP server runs over streamable HTTP at https://mcp.danubeai.com/mcp. It routes model calls into an ecosystem of 100+ services and 1400+ tools through unified authentication. Instead of configuring separate integrations for every external API, the assistant connects to a single remote bridge.
The server exposes over 30 tools. You can discover capabilities with search_tools, execute multiple calls at once using batch_execute_tools, or store multi-step routines with create_workflow. Financial controls are built directly into the schema: get_wallet_balance and update_spending_limits keep autonomous spending within defined bounds.
A valid Danube API key is mandatory. Without the danube-api-key header configured in your client, requests fail immediately. Developers can also interact with the platform directly using standalone Python and TypeScript SDKs.
What it helps with
- run external integrations through a single authenticated gateway
- bundle multiple tool calls into batch jobs using
batch_execute_tools - restrict agent budgets with
update_spending_limits - register and trigger reusable multi-step workflows
Example prompts for the agent
- Check my Danube wallet balance and list current spending caps.
- Search for available data enrichment tools using
search_tools. - Create a new automated pipeline to handle incoming support tickets.
How to install Danube AI
Platform CLI: remote server
claude mcp add --transport http danube https://mcp.danubeai.com/mcpPlatform CLI: remote server
codex mcp add danube-ai --url https://mcp.danubeai.com/mcpConfig file
{
"mcpServers": {
"danube-ai": {
"url": "https://mcp.danubeai.com/mcp"
}
}
}Config file
{
"servers": {
"danube-ai": {
"type": "http",
"url": "https://mcp.danubeai.com/mcp"
}
}
}Platform CLI: remote server
gemini mcp add -t http danube-ai https://mcp.danubeai.com/mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Danube AI
How to install Danube AI in Claude Code?
Run claude mcp add --transport http danube https://mcp.danubeai.com/mcp in your terminal. Make sure to configure the danube-api-key header with your key.
What does the Danube AI MCP server do?
It gives AI assistants access to 1400+ tools and 100+ services, handling discovery, workflow execution, and balance management through one connection.
What credentials does Danube AI require?
You need a Danube API key passed via the danube-api-key HTTP header. Unauthenticated requests are rejected by the server.
