{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_ezn25k64w87u","handle":"mcp-openai-images-audio","url":"https://wellknown.network/agents/mcp-openai-images-audio","links":{"self":"https://wellknown.network/agents/mcp-openai-images-audio/record.json","html":"https://wellknown.network/agents/mcp-openai-images-audio","markdown":"https://wellknown.network/agents/mcp-openai-images-audio/record.md","api":"https://wellknown.network/api/v1/agents/mcp-openai-images-audio","status":"https://wellknown.network/api/v1/agents/mcp-openai-images-audio/status","claim":"https://wellknown.network/agents/mcp-openai-images-audio/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-openai-images-audio/claim.json","badge":"https://wellknown.network/agents/mcp-openai-images-audio/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-openai-images-audio/history","tools":"https://wellknown.network/api/v1/agents/mcp-openai-images-audio/tools"},"ard":{"identifier":"urn:air::server:mcp-openai-images-audio","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-openai-images-audio","summary":"MCP server exposing OpenAI gpt-image-2 image generation and editing as a single tool for Claude Code and other MCP clients.","description":"# mcp-openai-images-audio\n\n[`v0.1.0`](https://github.com/eduard256/mcp-openai-images-audio/releases/tag/v0.1.0)\n\nMCP server that exposes OpenAI's `gpt-image-2` and `gpt-image-1.5` to Claude Code as a single tool. Generate, edit, or compose images straight from a chat. Files are written to disk; the model never returns base64 to your context.\n\nThis isn't a wrapper for everything OpenAI does. It's one tool: `image`. That's intentional.\n\n![Example: GitHub re-imagined as if designed by the Instagram team](https://raw.githubusercontent.com/eduard256/mcp-openai-images-audio/main/docs/example-ui-mockup.webp)\n\nOne call, `size: 2048x1152`, `quality: high`, no references — produced this UI mockup. Real readable typography, real-looking code preview, accurate Instagram visual language. That's the level you should expect.\n\n## Install\n\n```bash\npip install mcp-openai-images-audio\n```\n\nOr run directly without installing:\n\n```bash\nuvx mcp-openai-images-audio\n```\n\n## Connect to Claude Code\n\n```bash\nclaude mcp add openai-images \\\n  --scope user \\\n  -e OPENAI_API_KEY=sk-... \\\n  -- uvx mcp-openai-images-audio\n```\n\n**Important:**\n\n1. **Organization verification is mandatory** for `gpt-image-2`. Verify at https://platform.openai.com/settings/organization/general. Takes a few minutes, propagates within 15 minutes.\n2. The API key needs billing credit. Without it you get a 400 with `billing_hard_limit_reached`.\n3. The server runs over stdio. No HTTP, no separate process to keep alive — Claude Code starts and stops it for you.\n\n## How the tool works\n\nOne tool, three modes selected by `references_paths`:\n\n- empty / not passed → `/v1/images/generations` (text → new image)\n- 1 path → `/v1/images/edits` (modify that image)\n- 2..16 paths → `/v1/images/edits` (compose with labeled references)\n\nThe server picks the model on its own:\n\n- `background='transparent'` → `gpt-image-1.5` (gpt-image-2 currently rejects alpha — confirmed regression in OpenAI's docs)\n- everything else → `gpt-image-2`\n\nThe ac…","publisher":{"name":"eduard256","url":null},"homepage":"https://github.com/eduard256/mcp-openai-images-audio","repository":"https://github.com/eduard256/mcp-openai-images-audio","version":"0.1.1","license":"MIT License  Copyright (c) 2026 eduard256  Permission is hereby…","protocols":["mcp"],"tags":["anthropic","claude","claude-code","gpt-image","image-generation","mcp","model-context-protocol","openai"],"pricing":null,"endpoints":[{"url":"pypi:mcp-openai-images-audio","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"media.image-generation","name":"Image Generation","confidence":1,"provenance":"declared"},{"slug":"dev.docs-lookup","name":"Documentation Lookup","confidence":0.791,"provenance":"derived"}],"categories":["dev","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-openai-images-audio","registry":"pypi","observedAt":"2026-11-03T14:24:04.697Z","publishedAt":"2026-05-03T19:13:16.030674Z","latestVersion":"0.1.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-openai-images-audio","url":"https://pypi.org/project/mcp-openai-images-audio/","firstSeenAt":"2026-09-10T02:24:27.815Z","fetchedAt":"2026-11-03T14:23:03.547Z","normalizedAt":"2026-11-03T14:23:03.547Z"}]},"firstSeenAt":"2026-09-10T02:24:27.815Z","updatedAt":"2026-11-03T14:24:04.697Z"}