---
name: developing-genkit-tooling
description: Best practices for authoring Genkit tooling, including CLI commands and MCP server tools. Covers naming conventions, architectural patterns, and consistency…
---

# developing-genkit-tooling

Best practices for authoring Genkit tooling, including CLI commands and MCP server tools. Covers naming conventions, architectural patterns, and consistency…

# developing-genkit-toolingby firebase
Best practices for authoring Genkit tooling, including CLI commands and MCP server tools. Covers naming conventions, architectural patterns, and consistency…

`npx skills add https://github.com/firebase/genkit --skill developing-genkit-tooling`Download ZIPGitHub

## Developing Genkit Tooling

## Naming Conventions

Consistency in naming helps users and agents navigate the tooling.

### CLI Commands

Use kebab-case with colon separators for subcommands.

* Format: `noun:verb` or `category:action`

* Examples: `flow:run`, `eval:run`, `init`

* Arguments: Use camelCase in code (`flowName`) but standard format in help text (`<flowName>`).

### MCP Tools

Use snake_case for tool names to align with MCP standards.

* Format: `verb_noun`

* Examples: `list_flows`, `run_flow`, `list_genkit_docs`, `read_genkit_docs`

## CLI Command Architecture

Commands are implemented in `cli/src/commands/` using `commander`.

### Runtime Interaction

Most commands require interacting with the user's project runtime. Use the `runWithManager` utility to handle the lifecycle of the runtime process.

```
`import { runWithManager } from '../utils/manager-utils';

// ... command definition ...
.action(async (arg, options) => {
await runWithManager(await findProjectRoot(), async (manager) => {
// Interact with manager here
const result = await manager.runAction({ key: arg });
});
});
`
```

### Output Formatting

* Logging: Use `logger` from `@genkit-ai/tools-common/utils`.

* Machine Readable: Provide options for JSON output or file writing when the command produces data.

* Streaming: If the operation supports streaming (like `flow:run`), provide a `--stream` flag and pipe output to stdout.

## MCP Tool Architecture

MCP tools in `cli/src/mcp/` follow two distinct patterns: Static and Runtime.

### Static Tools (e.g., Docs)

These tools do not require a running Genkit project context.

* Registration: `defineDocsTool(server: McpServer)`

* Dependencies: Only the `server` instance.

* Use Case: Documentation, usage guides, global configuration.

### Runtime Tools (e.g., Flows, Runtime Control)

These tools interact with a specific Genkit project's runtime.

* Registration: `defineRuntimeTools(server: McpServer, options: McpToolOptions)`

* Dependencies: Requires `options` containing `manager` (process manager) and `projectRoot`.

* Schema: MUST use `getCommonSchema(options.explicitProjectRoot, ...)` to ensure the tool can accept a `projectRoot` argument when required (e.g., in multi-project environments).

```
`// Runtime tool definition pattern
server.registerTool(
'my_runtime_tool',
{
inputSchema: getCommonSchema(options.explicitProjectRoot, {
myArg: z.string(),
}),
},
async (opts) => {
// Resolve project root before action
const rootOrError = resolveProjectRoot(
options.explicitProjectRoot,
opts,
options.projectRoot
);
if (typeof rootOrError !== 'string') return rootOrError;

// access manager via options.manager
}
);
`
```

### Error Handling

MCP tools should generally catch errors and return them as content blocks with `isError: true` rather than throwing exceptions, which ensures the client receives a structured error response.

```
`try {
// operation
} catch (err) {
const message = err instanceof Error ? err.message : String(err);
return {
isError: true,
content: [{ type: 'text', text: `Error: ${message}` }],
};
}
`
```

## More skills from firebase
developing-genkit-dartby firebaseUnified AI SDK for Dart enabling code generation, structured outputs, tools, flows, and agents. Provides core APIs for generation, tool definition, flow orchestration, embeddings, and streaming with a single interface Includes 8+ plugins for LLM providers (Google Gemini, Anthropic Claude, OpenAI GPT), Firebase AI, Model Context Protocol, Chrome browser integration, and HTTP server hosting via Shelf Built-in CLI with local development UI for flow execution, tracing, model experimentation, and...developing-genkit-goby firebaseDevelop AI-powered applications using Genkit in Go. Use when the user asks to build AI features, agents, flows, or tools in Go using Genkit, or when working…developing-genkit-jsby firebaseBuild AI-powered Node.js/TypeScript applications with Genkit flows, tools, and multi-model support. Genkit is provider-agnostic; supports Google AI, OpenAI, Anthropic, Ollama, and other LLM providers via plugins Define flows with type-safe schemas using Zod, execute generation requests, and compose multi-step AI workflows in TypeScript Requires Genkit CLI v1.29.0+; recent major API changes mean you must consult genkit docs:read and common-errors.md for current patterns, not prior knowledge...developing-genkit-pythonby firebaseDevelop AI-powered applications using Genkit in Python. Use when the user asks about Genkit, AI agents, flows, or tools in Python, or when encountering Genkit…firebase-ai-logicby firebaseClient-side Gemini integration for web apps with multimodal inference, streaming, and on-device hybrid execution. Supports text-only and multimodal inputs (images, audio, video, PDFs); files over 20 MB route through Cloud Storage Includes chat sessions with automatic history, streaming responses for real-time display, and structured JSON output enforcement Offers hybrid on-device inference via Gemini Nano in Chrome, with automatic fallback to cloud execution Requires App Check for production...firebase-ai-logic-basicsby firebaseOfficial skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.firebase-app-hosting-basicsby firebaseDeploy and manage full-stack web apps with Firebase App Hosting using Next.js, Angular, and other supported frameworks. Requires Firebase project on Blaze pricing plan; supports Server-Side Rendering (SSR) and Incremental Static Regeneration (ISR) workflows Deploy via firebase.json configuration with optional apphosting.yaml for backend setup, or enable automated "git push to deploy" through GitHub integration Includes secret management via CLI commands for secure access to sensitive keys...firebase-auth-basicsby firebaseSet up Firebase Authentication with multiple identity providers and secure data access rules. Supports email/password, phone number, anonymous, federated providers (Google, Facebook, Twitter, GitHub, Microsoft, Apple), and custom auth integration Each authenticated user receives a unique ID and JWT-based tokens (short-lived ID tokens and long-lived refresh tokens) for accessing Firebase services Enable providers via CLI for Google Sign In, anonymous, and email/password; use Firebase Console...

---

**Source**: https://github.com/firebase/genkit/tree/HEAD/skills/developing-genkit-tooling
**Author**: firebase
**Discovered via**: mcpservers.org