{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_9dj5hjfg29kv","handle":"mcp-image-gen","url":"https://wellknown.network/agents/mcp-image-gen","links":{"self":"https://wellknown.network/agents/mcp-image-gen/record.json","html":"https://wellknown.network/agents/mcp-image-gen","markdown":"https://wellknown.network/agents/mcp-image-gen/record.md","api":"https://wellknown.network/api/v1/agents/mcp-image-gen","status":"https://wellknown.network/api/v1/agents/mcp-image-gen/status","claim":"https://wellknown.network/agents/mcp-image-gen/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-image-gen/claim.json","badge":"https://wellknown.network/agents/mcp-image-gen/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-image-gen/history","tools":"https://wellknown.network/api/v1/agents/mcp-image-gen/tools"},"ard":{"identifier":"urn:air::server:mcp-image-gen","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-image-gen","summary":"一个基于MCP协议的OpenAI图像生成服务器，生成后上传图床","description":"# OpenAI图像生成MCP服务 (v0.1.3) \n \n这是一个基于MCP协议的OpenAI图像生成服务器，允许大语言模型通过MCP协议调用OpenAI的图像生成API，生成图像后自动上传到图床并返回图片链接。 \n \n## 安装 \n \n```bash \npip install mcp-image-gen \n``` \n \n## 功能 \n \n### 工具 (Tools) \n \n- `generate_image`: 根据文本提示生成图像，自动上传到图床，返回图片URL。 \n  - 参数: \n    - `prompt`: 描述想要生成的图像的文本提示 \n    - `size`: 图像尺寸，可选 `1024x1024`(默认), `1024x1536`, `1536x1024` \n    - `quality`: 图像质量，可选 `low`, `medium`(默认), `high`, `auto` \n    - `model`: 使用的模型，默认为 `gpt-image-1` \n    - `save_locally`: 是否同时保存图像到本地文件，默认为`False` \n    - `api_key`: 可选，自定义API密钥，不提供则使用默认值 \n    - `base_url`: 可选，自定义API基础URL，不提供则使用默认值 \n    - `image_hosting_token`: 可选，自定义图床API令牌，不提供则使用默认值 \n    - `image_hosting_url`: 可选，自定义图床API URL，不提供则使用默认值 \n \n- `save_image_base64`: 将Base64编码的图像数据保存为文件。 \n  - 参数: \n    - `base64_data`: Base64编码的图像数据 \n    - `filename`: 要保存的文件名，默认为 `generated_image.png` \n \n- `upload_to_image_hosting`: 将Base64编码的图像数据上传到图床。 \n  - 参数: \n    - `base64_data`: Base64编码的图像数据 \n    - `filename`: 上传的文件名，默认为 `generated_image.png` \n    - `permission`: 图片权限，1=公开，0=私有，默认为1 \n    - `image_hosting_token`: 可选，自定义图床API令牌，不提供则使用默认值 \n    - `image_hosting_url`: 可选，自定义图床API URL，不提供则使用默认值 \n \n### 资源 (Resources) \n \n- `openai://api/status`: 检查OpenAI API的可用性状态。 \n \n## 在阿里云百炼中使用 \n \n在阿里云百炼平台的MCP服务配置中，使用以下JSON： \n \n```json \n{ \n  \"mcpServers\": { \n    \"openai-image-gen\": {  // 服务名称，可自定义 \n      \"command\": \"uvx\", \n      \"args\": [\"mcp-image-gen\"] \n    } \n  } \n} \n``` \n \n## 本地运行 \n \n安装后，您可以在本地通过以下方式运行： \n \n```bash \n# 使用uvx \nuvx mcp-image-gen \n \n# 使用包提供的命令 \nmcp-image-gen \n \n# 使用Python -m \npython -m mcp_image_gen \n``` \n \n按 `Ctrl+C` 停止服务器。 \n \n## 配置 \n \n默认情况下，服务器使用内置的API密钥、代理URL和图床配置，但您可以在调用工具时通过参数覆盖它们。这使得大语言模型可以灵活地传入自定义凭证和配置。 \n \n### 错误处理 \n \n服务器会将所有错误信息返回给调用方，格式为 `\"Error: 具体错误信息\"`，方便大语言模型理解错误原因并做出相应处理。 \n \n## 图床功能 \n \n本服务使用 `tu.my` 图床服务来托管生成的图像，确保图像生成后能够立即获得可访问的URL。 \n \n## 许可证 \n \nMIT License","publisher":{"name":"MCP服务开发者","url":null},"homepage":"https://github.com/yourusername/mcp-image-gen","repository":"https://github.com/yourusername/mcp-image-gen","version":"0.1.3","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:mcp-image-gen","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"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":"derived"}],"categories":["media"],"language":"zh"},"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-image-gen","registry":"pypi","observedAt":"2026-11-03T13:26:51.716Z","publishedAt":"2025-04-30T07:40:27.016501Z","latestVersion":"0.1.3"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-image-gen","url":"https://pypi.org/project/mcp-image-gen/","firstSeenAt":"2026-09-10T02:22:50.561Z","fetchedAt":"2026-11-03T13:26:20.990Z","normalizedAt":"2026-11-03T13:26:20.990Z"}]},"firstSeenAt":"2026-09-10T02:22:50.561Z","updatedAt":"2026-11-03T13:26:51.716Z"}