Can I use Railway as a CLI?

Yes. KosmoKrator exposes a Railway CLI through kosmo integrations:call and the provider shortcut command. Commands can return JSON for scripts, CI, and coding agents.

Can I expose Railway through MCP?

Yes. The KosmoKrator MCP gateway can expose selected Railway tools to clients such as Claude Code, Cursor, Codex, and other MCP-compatible tools.

Where are Railway credentials stored?

Railway credentials are configured in KosmoKrator's local integration settings and reused by CLI, Lua, and MCP gateway surfaces.

Can I deny write access for Railway MCP tools?

Yes. Start the gateway with --write=deny for read-only clients, or use ask/allow only for trusted workspaces.

productivity

Railway MCP Integration for Vercel AI SDK

Connect Railway to Vercel AI SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.

7 functions 6 read 1 write Bearer token auth

Submit Railway feedback View package source

Connect Railway to Vercel AI SDK

Use KosmoKrator as a local integration gateway for Vercel AI SDK agents and scripts.

Create an MCP client that starts or connects to the KosmoKrator gateway for the selected integration. The gateway is local, scoped to this integration, and starts with --write=deny so Vercel AI SDK can inspect read-capable tools without receiving write access by default.

Railway MCP Config for Vercel AI SDK

Prefer CLI JSON calls when a workflow only needs one deterministic integration operation.

{
  "mcpServers": {
    "kosmokrator-railway": {
      "type": "stdio",
      "command": "kosmo",
      "args": [
        "mcp:serve",
        "--integration=railway",
        "--write=deny"
      ]
    }
  }
}

Run the Gateway Manually

kosmokrator mcp:serve --integration=railway --write=deny

Why Use KosmoKrator Here

Scoped tools

Expose only Railway instead of a broad multi-service tool list.

Local credentials

Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.

Write policy

Start read-only, then opt into ask or allow for trusted workspaces.

Railway Tools Visible to Vercel AI SDK

Vercel AI SDK sees stable MCP tool names generated from the Railway integration catalog.

MCP tool	Source function	Type	Description
`integration__railway__railway_list_projects`	`railway.railway_list_projects`	Read	List all Railway projects the authenticated user has access to. Returns project IDs, names, descriptions, and team info.
`integration__railway__railway_get_project`	`railway.railway_get_project`	Read	Get detailed information about a specific Railway project, including its environments and plugins.
`integration__railway__railway_create_project`	`railway.railway_create_project`	Write	Create a new Railway project with a name and optional description.
`integration__railway__railway_list_services`	`railway.railway_list_services`	Read	List all services in a Railway project. Returns service IDs, names, and repository info.
`integration__railway__railway_get_service`	`railway.railway_get_service`	Read	Get detailed information about a specific Railway service, including its source configuration and repository details.
`integration__railway__railway_list_deployments`	`railway.railway_list_deployments`	Read	List deployments for a Railway service. Returns deployment status, environment, and creator info.
`integration__railway__railway_get_current_user`	`railway.railway_get_current_user`	Read	Get information about the currently authenticated Railway user. Useful for verifying API credentials.

Related Railway Pages

Railway CLIUse direct JSON commands instead of MCP discovery. Railway MCPFull gateway reference and MCP tool names. KosmoKrator for Vercel AI SDKClient-level gateway setup.