@runapi.ai/gpt-image-mcp 0.1.0 → 0.1.2

package/README.md

@@ -1,37 +1,56 @@
-# @runapi.ai/gpt-image-mcp
+<h1 align="center">RunAPI GPT Image MCP Server</h1>
 
-RunAPI MCP server for the **GPT Image** model line. Create tasks,
-poll their status, and check pricing through a single RunAPI API key.
+<p align="center">
+  <strong>GPT Image API access for AI agents: create image generation tasks, poll results, and check pricing through one focused MCP server.</strong>
+</p>
 
-## Tools
+<p align="center">
+  <sub>Works with Claude Code, Codex, Cursor, Windsurf, VS Code, Roo Code, and any MCP-compatible host.</sub>
+</p>
 
-- `edit_image` — create a GPT Image task (edit image) and (optionally) poll until it reaches a terminal status. Returns the task id, status, output URLs, and a price snapshot. Models: `gpt-image-1.5`.
-- `text_to_image` — create a GPT Image task (text to image) and (optionally) poll until it reaches a terminal status. Returns the task id, status, output URLs, and a price snapshot. Models: `gpt-image-1.5`.
-- `get_task` — fetch the current status and latest payload for a task.
-- `check_pricing` — look up pricing for a model in this line.
+<p align="center">
+  <a href="https://www.npmjs.com/package/@runapi.ai/gpt-image-mcp"><img src="https://img.shields.io/npm/v/%40runapi.ai/gpt-image-mcp?style=flat-square&color=blue" alt="npm version"></a>
+  <a href="https://github.com/runapi-ai/gpt-image-mcp"><img src="https://img.shields.io/badge/GitHub-runapi--ai%2Fgpt-image-mcp-24292f?style=flat-square" alt="GitHub repository"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-blue?style=flat-square" alt="Apache-2.0 license"></a>
+  <img src="https://img.shields.io/badge/Type-MCP_Server-blue?style=flat-square" alt="MCP Server">
+  <img src="https://img.shields.io/badge/Models-1-16a34a?style=flat-square" alt="1 models">
+</p>
 
-## Configuration
+<p align="center">
+  <a href="#install">Install</a> |
+  <a href="#tools">Tools</a> |
+  <a href="#models">Models</a> |
+  <a href="#agent-prompts">Agent Prompts</a> |
+  <a href="#configuration">Configuration</a> |
+  <a href="#links">Links</a>
+</p>
 
-Set a RunAPI API key via the `RUNAPI_API_KEY` environment variable, or write
-it to `~/.config/runapi/config.json`:
+---
 
-```bash
-mkdir -p ~/.config/runapi
-echo '{"api_key":"YOUR_KEY"}' > ~/.config/runapi/config.json
-```
+## Why This Package?
 
-Get an API key at https://runapi.ai. Pricing is listed at
-https://runapi.ai/pricing.
+`@runapi.ai/gpt-image-mcp` is a focused Model Context Protocol server for the **GPT Image** model line on RunAPI.
+It gives MCP-compatible assistants direct access to 2 endpoints and 1 model variant without loading the full RunAPI catalog.
 
-## Usage
+Use this per-model server when an agent should stay scoped to GPT Image. Use [`@runapi.ai/mcp`](https://github.com/runapi-ai/mcp) when one assistant should discover every RunAPI model line.
 
-Run the server over stdio:
+---
+
+## Install
+
+Add it to Claude Code:
 
 ```bash
-npx -y @runapi.ai/gpt-image-mcp
+claude mcp add gpt-image -s user -- npx -y @runapi.ai/gpt-image-mcp
 ```
 
-Add it to an MCP client (see `examples/` for per-client configs):
+Use project scope when the server should be shared with a repository:
+
+```bash
+claude mcp add gpt-image -s project -- npx -y @runapi.ai/gpt-image-mcp
+```
+
+Codex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:
 
 ```json
 {
@@ -45,6 +64,97 @@ Add it to an MCP client (see `examples/` for per-client configs):
 }
 ```
 
+Create an API key at [runapi.ai](https://runapi.ai) and expose it as `RUNAPI_API_KEY`. `check_pricing` can run without a key; task creation and status polling require one.
+
+Ready-made examples are in [`examples/`](examples/) for Claude, Cursor, Windsurf, VS Code, and Roo Code.
+
+---
+
+## Tools
+
+| Tool | Auth | Purpose |
+|---|---|---|
+| `edit_image` | Yes | Create a GPT Image edit image task and optionally wait for a terminal status. Returns the task id, status, output URLs, and pricing snapshot. |
+| `text_to_image` | Yes | Create a GPT Image text to image task and optionally wait for a terminal status. Returns the task id, status, output URLs, and pricing snapshot. |
+| `get_task` | Yes | Fetch the current status and latest payload for an existing task. |
+| `check_pricing` | No | Look up the current pricing snapshot for a GPT Image model and endpoint. |
+
+---
+
+## Models
+
+GPT Image covers 1 model variant across 2 endpoints. Each tool accepts the models listed for it:
+
+| Tool | Models |
+|---|---|
+| `edit_image` | `gpt-image-1.5` |
+| `text_to_image` | `gpt-image-1.5` |
+
+Model availability can change between releases. Use `check_pricing` or the [GPT Image model page](https://runapi.ai/models/gpt-image) for the current catalog view.
+
+---
+
+## Agent Prompts
+
+Ask your assistant in natural language; it can inspect pricing, create the task, and return the task id plus output URLs.
+
+### Create a task
+
+```text
+Run a GPT Image edit image task with RunAPI.
+```
+
+The assistant can call `check_pricing`, then `edit_image`, and return the task id, status, and output URLs.
+
+### Submit without waiting
+
+```text
+Create the task but don't wait for it to finish.
+```
+
+The assistant calls the create tool with `wait: false` and returns the task id. Check on it later with `get_task`.
+
+### Check pricing before creating
+
+```text
+Check current GPT Image pricing, then create the task if it matches my request.
+```
+
+The assistant calls `check_pricing` and can link to the [GPT Image model page](https://runapi.ai/models/gpt-image) for the canonical catalog entry.
+
+---
+
+## Configuration
+
+The server reads the API key in this order:
+
+1. `RUNAPI_API_KEY` environment variable
+2. `~/.config/runapi/config.json`
+
+Example config file:
+
+```json
+{
+  "apiKey": "your_runapi_key"
+}
+```
+
+Do not commit real API keys. Get one at [runapi.ai](https://runapi.ai).
+
+---
+
+## Links
+
+| Resource | URL |
+|---|---|
+| GPT Image model page | [https://runapi.ai/models/gpt-image](https://runapi.ai/models/gpt-image) |
+| npm package | [@runapi.ai/gpt-image-mcp](https://www.npmjs.com/package/@runapi.ai/gpt-image-mcp) |
+| GitHub repository | [runapi-ai/gpt-image-mcp](https://github.com/runapi-ai/gpt-image-mcp) |
+| RunAPI MCP overview | [runapi.ai/mcp](https://runapi.ai/mcp) |
+| RunAPI docs | [runapi.ai/docs](https://runapi.ai/docs) |
+
+---
+
 ## License
 
-Apache-2.0
+Licensed under the [Apache License, Version 2.0](LICENSE).

package/dist/src/meta.d.ts

@@ -1,5 +1,5 @@
 export declare const META: {
     readonly name: "@runapi.ai/gpt-image-mcp";
-    readonly version: "0.1.0";
+    readonly version: "0.1.1";
     readonly lineSlug: "gpt-image";
 };

package/dist/src/meta.js

@@ -1,6 +1,6 @@
 export const META = {
     name: "@runapi.ai/gpt-image-mcp",
-    version: "0.1.0",
+    version: "0.1.1",
     lineSlug: "gpt-image"
 };
 //# sourceMappingURL=meta.js.map

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@runapi.ai/gpt-image-mcp",
-  "version": "0.1.0",
-  "description": "RunAPI MCP server for one model line: create tasks, poll status, and check pricing with one API key.",
+  "version": "0.1.2",
+  "description": "RunAPI GPT Image MCP server for image generation: create tasks, poll results, and check pricing across 1 model from Claude Code, Codex, Cursor, and VS Code.",
   "type": "module",
   "main": "dist/src/index.js",
   "bin": {
@@ -25,13 +25,25 @@
   },
   "keywords": [
     "runapi",
+    "runapi-ai",
     "mcp",
+    "mcp-server",
     "model-context-protocol",
-    "ai"
+    "ai-agents",
+    "claude-code",
+    "cursor",
+    "vscode",
+    "gpt-image",
+    "gpt-image-mcp",
+    "gpt-image-api",
+    "image-generation",
+    "ai-image",
+    "edit-image",
+    "text-to-image"
   ],
   "author": "RunAPI",
   "license": "Apache-2.0",
-  "homepage": "https://runapi.ai",
+  "homepage": "https://runapi.ai/models/gpt-image",
   "repository": {
     "type": "git",
     "url": "git+https://github.com/runapi-ai/gpt-image-mcp.git"

package/server.json

@@ -1,23 +1,23 @@
 {
   "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
   "name": "io.github.runapi-builder/gpt-image-mcp",
-  "description": "RunAPI MCP server for GPT Image: create tasks, poll status, and check pricing.",
+  "description": "RunAPI MCP server for GPT Image: create tasks, poll status, check pricing.",
   "repository": {
     "url": "https://github.com/runapi-ai/gpt-image-mcp",
     "source": "github"
   },
-  "version": "0.1.0",
+  "version": "0.1.2",
   "packages": [
     {
       "registryType": "npm",
       "identifier": "@runapi.ai/gpt-image-mcp",
-      "version": "0.1.0",
+      "version": "0.1.2",
       "transport": {
         "type": "stdio"
       },
       "environmentVariables": [
         {
-          "description": "RunAPI API key. Get one at https://runapi.ai",
+          "description": "RunAPI API key. Create one at https://runapi.ai",
           "isRequired": true,
           "format": "string",
           "isSecret": true,