![\"npm](\"https://img.shields.io/npm/v/%40runapi.ai/gpt-image-mcp?style=flat-square&color=blue\")
\n ![\"GitHub](\"https://img.shields.io/badge/GitHub-runapi--ai%2Fgpt--image--mcp-24292f?style=flat-square\"){kind=icon}
\n ![\"Apache-2.0](\"https://img.shields.io/badge/License-Apache_2.0-blue?style=flat-square\"){kind=icon}
\n ![\"MCP](\"https://img.shields.io/badge/Type-MCP_Server-blue?style=flat-square\"){kind=icon}
\n ![\"1](\"https://img.shields.io/badge/Models-1-16a34a?style=flat-square\"){kind=icon}
\n\n GPT Image API access for AI agents: run image generation operations, poll asynchronous results, and check pricing through one focused MCP server.\n
\n\n\n Works with Claude Code, Codex, Cursor, Windsurf, VS Code, Roo Code, and any MCP-compatible host.\n
\n\n\n
\n Install |\n Tools |\n Models |\n Agent Prompts |\n Configuration |\n Links\n
\n\n---\n\n## Why This Package?\n\n`@runapi.ai/gpt-image-mcp` is a focused Model Context Protocol server for the **GPT Image** model line on RunAPI.\nIt gives MCP-compatible assistants direct access to 2 endpoints and 1 model variant without loading the full RunAPI catalog.\n\nUse 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.\n\n---\n\n## Install\n\nAdd it to Claude Code:\n\n```bash\nclaude mcp add gpt-image -s user -- npx -y @runapi.ai/gpt-image-mcp\n```\n\nUse project scope when the server should be shared with a repository:\n\n```bash\nclaude mcp add gpt-image -s project -- npx -y @runapi.ai/gpt-image-mcp\n```\n\nCodex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:\n\n```json\n{\n \"mcpServers\": {\n \"gpt-image\": {\n \"command\": \"npx\",\n \"args\": [\"-y\", \"@runapi.ai/gpt-image-mcp\"]\n }\n }\n}\n```\n\n`check_pricing` works before sign-in. For task creation and status polling, ask your assistant to call the `login` tool. It opens a browser login and saves credentials to `~/.config/runapi/config.json`, the same file used by `runapi login`.\nHeadless and CI hosts can still set `RUNAPI_API_KEY` before starting the MCP host.\n\nReady-made examples are in [`examples/`](examples/) for Claude, Cursor, Windsurf, VS Code, and Roo Code.\n\n---\n\n## Tools\n\n| Tool | Auth | Purpose |\n|---|---|---|\n| `edit_image` | Yes | Create a GPT Image edit image task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |\n| `text_to_image` | Yes | Create a GPT Image text to image task and optionally wait for a terminal status. Returns the task id, status, and output URLs. |\n| `get_task` | Yes | Fetch the current status and latest payload for an existing task. |\n| `check_pricing` | No | Look up current pricing for a GPT Image model and endpoint. |\n\n---\n\n## Models\n\nGPT Image covers 1 model variant across 2 endpoints. Each tool accepts the models listed for it:\n\n| Tool | Models |\n|---|---|\n| `edit_image` | `gpt-image-1.5` |\n| `text_to_image` | `gpt-image-1.5` |\n\nModel 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.\n\n---\n\n## Agent Prompts\n\nAsk your assistant in natural language; it can inspect pricing, create the task, and return the task id plus output URLs.\n\n### Create a task\n\n```text\nRun a GPT Image edit image task with RunAPI.\n```\n\nThe assistant can call `check_pricing`, then `edit_image`, and return the task id, status, and output URLs.\n\n### Submit without waiting\n\n```text\nCreate the task but don't wait for it to finish.\n```\n\nThe assistant calls the create tool with `wait: false` and returns the task id. Check on it later with `get_task`.\n\n### Check pricing before creating\n\n```text\nCheck current GPT Image pricing, then create the task if it matches my request.\n```\n\nThe assistant calls `check_pricing` and can link to the [GPT Image model page](https://runapi.ai/models/gpt-image) for the canonical catalog entry.\n\n---\n\n## Configuration\n\nThe server resolves auth in this order:\n\n1. `RUNAPI_API_KEY` environment variable, useful for headless and CI hosts\n2. `~/.config/runapi/config.json`, created by the MCP `login` tool or `runapi login`\n3. No key, which still allows `check_pricing`\n\nThe config file is normally managed by login. A pre-provisioned headless config can use:\n\n```json\n{\n \"apiKey\": \"your_runapi_key\"\n}\n```\n\nDo not commit real API keys.\n\n---\n\n## Links\n\n| Resource | URL |\n|---|---|\n| GPT Image model page | [https://runapi.ai/models/gpt-image](https://runapi.ai/models/gpt-image) |\n| npm package | [@runapi.ai/gpt-image-mcp](https://www.npmjs.com/package/@runapi.ai/gpt-image-mcp) |\n| GitHub repository | [runapi-ai/gpt-image-mcp](https://github.com/runapi-ai/gpt-image-mcp) |\n| RunAPI MCP overview | [runapi.ai/mcp](https://runapi.ai/mcp) |\n| RunAPI docs | [runapi.ai/docs](https://runapi.ai/docs) |\n\n---\n\n## License\n\nLicensed under the [Apache License, Version 2.0](LICENSE).\n","readmeFilename":"README.md"}