MCP Tools Reference
Complete reference for all Ink MCP tools — deploy, observe, and manage production applications through AI agents
Model Context Protocol (MCP) is an open standard for connecting AI agents to external tools and data sources. Instead of building custom integrations for each AI client, a service exposes MCP tools once and every compatible client can use them.
Ink exposes 30+ MCP tools through a single endpoint that give AI agents full control over infrastructure — deploy services, deploy database templates, manage DNS records, read logs, and more.
Endpoint
https://mcp.ml.ink/Ink uses Streamable HTTP transport. The agent sends JSON-RPC requests over HTTP and receives responses back. Most MCP clients handle this automatically — you just provide the endpoint URL.
Authentication
All requests require authentication. Two methods are supported:
- OAuth — the agent authenticates through a browser flow, handled automatically by the MCP client. This is the default for Claude Code, Cursor, and most desktop clients.
- API Key — pass a
dk_live_token viaAuthorization: Bearer YOUR_API_KEYheader. Designed for headless agents and programmatic access.
Tool discovery
On connection, the agent calls tools/list and receives every available tool with:
- Name — the tool identifier (e.g.,
create_service) - Description — what the tool does, written for AI agents to understand
- Input schema — typed parameters with descriptions and defaults
- Required fields — which parameters are mandatory
The agent uses these descriptions to decide when and how to call each tool.
Tool categories
| Category | Tools | Description |
|---|---|---|
| Services | create_service, list_services, get_service, update_service, delete_service | Deploy, monitor, and manage applications |
| Git | create_repo, get_git_token | Create repositories and get push credentials |
| Domains | add_custom_domain, remove_custom_domain, list_delegations, list_dns_records, add_dns_record, delete_dns_record | Custom domains and full DNS management |
| Identity | whoami, list_projects, list_workspaces | Authentication and project management |
Common patterns
Deploy a service
create_service(
"name": "my-app",
"repo": "ink/my-app"
)Check deployment status and logs
get_service(
"name": "my-app",
"deploy_log_lines": "100",
"runtime_log_lines": "100"
)Provision a database
template_deploy(
"slug": "postgresql",
"name": "my-db"
)Assign a custom domain
add_custom_domain(
"name": "my-app",
"domain": "app.example.com"
)MCP vs REST APIs
| MCP | REST API | |
|---|---|---|
| Consumer | AI agents | Human developers writing code |
| Discovery | Automatic — agent reads tool list | Manual — developer reads docs |
| Invocation | Agent decides based on context | Developer writes explicit calls |
| Auth | OAuth or token, handled by client | Developer manages tokens |
| Error handling | Agent reads error, adapts approach | Developer writes error handling code |
MCP doesn't replace REST APIs — it's a layer designed for AI agent interaction. Ink's MCP tools call the same underlying API, but the interface is optimized for how agents think and operate.