Skip to main content
Glama
heroku

Heroku MCP server

Official
by heroku

create_app

Create a new Heroku application with customizable settings, including name, region, private space, or team association. Automatically generate app names if not specified and receive detailed app information upon creation.

Instructions

Create a new Heroku application with customizable settings. Use this tool when a user wants to: 1) Create a new app with a specific name, 2) Create an app in a particular region (US/EU), 3) Create an app within a team, or 4) Create an app in a private space. The tool handles name generation if not specified and returns the new app's details.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
appNoSpecifies the desired name for the new Heroku app. If omitted, Heroku will auto-generate a random name. Best practice: Provide a meaningful, unique name that reflects your application's purpose.
regionNoDetermines the geographical region where your app will run. Options: "us" (United States) or "eu" (Europe). Defaults to "us" if not specified. Note: Cannot be used with space parameter.
spaceNoPlaces the app in a specific private space, which provides enhanced security and networking features. Specify the private space name. Note: When used, the app inherits the region from the private space and the region parameter cannot be used.
teamNoAssociates the app with a specific team for collaborative development and management. Provide the team name to set ownership. The app will be created under the team's account rather than your personal account.

Implementation Reference

  • The core handler function that constructs a CommandBuilder for the 'apps:create' CLI command using provided options and executes it via the HerokuREPL, returning the processed output.
    async (options: CreateAppOptions): Promise<McpToolResponse> => {
      const command = new CommandBuilder(TOOL_COMMAND_MAP.CREATE_APP)
        .addPositionalArguments({ app: options.app })
        .addFlags({
          region: options.region,
          space: options.space,
          team: options.team
        })
        .build();
    
      const output = await herokuRepl.executeCommand(command);
      return handleCliOutput(output);
    }
  • Zod schema defining the input parameters for the create_app tool, including optional app name, region, space, and team.
    export const createAppOptionsSchema = z.object({
      app: z.string().optional().describe('App name. Auto-generated if omitted'),
      region: z.enum(['us', 'eu']).optional().describe('Region: us/eu. Default: us. Excludes space param'),
      space: z.string().optional().describe('Private space name. Inherits region. Excludes region param'),
      team: z.string().optional().describe('Team name for ownership')
    });
  • Module-level registration function that registers the 'create_app' tool on the MCP server with schema and handler.
    export const registerCreateAppTool = (server: McpServer, herokuRepl: HerokuREPL): void => {
      server.tool(
        'create_app',
        'Create app: custom name, region (US/EU), team, private space',
        createAppOptionsSchema.shape,
        async (options: CreateAppOptions): Promise<McpToolResponse> => {
          const command = new CommandBuilder(TOOL_COMMAND_MAP.CREATE_APP)
            .addPositionalArguments({ app: options.app })
            .addFlags({
              region: options.region,
              space: options.space,
              team: options.team
            })
            .build();
    
          const output = await herokuRepl.executeCommand(command);
          return handleCliOutput(output);
        }
      );
    };
  • src/index.ts:52-52 (registration)
    Top-level application registration call for the create_app tool.
    apps.registerCreateAppTool(server, herokuRepl);
  • Helper constant mapping the CREATE_APP tool to the Heroku CLI command 'apps:create'.
    CREATE_APP: 'apps:create',
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses that the tool handles name generation if not specified and returns the new app's details, which adds behavioral context. However, it doesn't mention authentication requirements, rate limits, or potential side effects like billing implications, leaving gaps for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized with two sentences: the first states the purpose and customizable settings, and the second covers usage scenarios and behavioral details. It's front-loaded with the core function, though the second sentence is a bit dense with four bullet-like points.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations and no output schema, the description is moderately complete. It covers purpose, usage, and some behavior (auto-naming, returns details), but lacks information on error handling, permissions, or response format. Given the complexity, it should do more to compensate for missing structured data.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value by listing the four customizable settings (name, region, team, private space) but doesn't provide additional semantics beyond what's in the schema descriptions. Baseline 3 is appropriate when schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Create') and resource ('new Heroku application'), specifies customizable settings, and distinguishes from siblings like 'rename_app' or 'transfer_app' by focusing on initial creation. It's specific about what the tool does without being tautological.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly lists four scenarios when to use this tool: creating with a specific name, in a particular region, within a team, or in a private space. It provides clear context for usage without needing to mention alternatives, as the use cases are well-defined.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/heroku/heroku-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server