Image Generation MCP Setup & Guide
io.github.pvliesdonk/image-generation-mcp · v1.12.1
MCP server for AI image generation via OpenAI, Stable Diffusion (SD WebUI), or placeholders.
Copy the install config on this page first, then verify docs and permissions upstream.
Overview
MCP server for AI image generation via OpenAI, Stable Diffusion (SD WebUI), or placeholders. Image Generation MCP Server is a MCP Server listed from MCP Registry. Transports: stdio, streamable-http. This page includes an overview, setup tutorial, install commands, and use cases for Trae, Tongyi Lingma, Cursor, Claude Code, and VS Code.
Use cases
AgentHub Verified AvailabilityTested & Ready
Automated pipeline validated install commands, protocol & client compatibility
Copy by platform
Choose your platform
- Open or create .cursor/mcp.json in your project root
- Click Copy config and paste; merge only this mcpServers entry if others exist
- Replace <placeholders> in env with real secrets (see Environment variables below)
- Save, then Cmd+Shift+P → Reload Window
Pre-fill Environment Variables (Optional)
{
"mcpServers": {
"image-generation-mcp": {
"command": "uvx",
"args": [
"image-generation-mcp"
]
}
}
}Setup tutorial
- Open the Image Generation MCP Server page and confirm this MCP Server (source: MCP Registry).
- Copy the Cursor, Claude Code, or VS Code snippet.
- Merge it into mcpServers and replace env placeholders with real secrets.
- Reload the window, then call the MCP tools from your agent chat.
Install commands
Install commands and setup steps are in the HTML so search engines and no-JS browsers can read them without running client JavaScript.
Claude Code (local)
- Install Claude Code CLI
- Copy the command below, replace <placeholders> with real env values, then run in terminal
- See Environment variables below if listed
claude mcp add image-generation-mcp -- uvx image-generation-mcpCursor — .cursor/mcp.json (local)
- Open or create .cursor/mcp.json in your project root
- Click Copy config and paste; merge only this mcpServers entry if others exist
- Replace <placeholders> in env with real secrets (see Environment variables below)
- Save, then Cmd+Shift+P → Reload Window
{
"mcpServers": {
"image-generation-mcp": {
"command": "uvx",
"args": [
"image-generation-mcp"
]
}
}
}VS Code — .vscode/mcp.json (local)
- Install GitHub Copilot in VS Code with MCP support
- Open or create .vscode/mcp.json in your project root
- Click Copy config and paste; merge only this mcpServers entry if others exist
- Replace <placeholders> in env with real secrets
- Save and Developer: Reload Window
{
"mcpServers": {
"image-generation-mcp": {
"command": "uvx",
"args": [
"image-generation-mcp"
]
}
}
}Claude Desktop — claude_desktop_config.json (local)
- Open Claude Desktop claude_desktop_config.json (see remote guide for paths)
- Click Copy config and merge under mcpServers
- Replace <placeholders> in env with real secrets
- Fully quit and restart Claude Desktop
{
"mcpServers": {
"image-generation-mcp": {
"command": "uvx",
"args": [
"image-generation-mcp"
]
}
}
}Trae — .trae/mcp.json (local)
- Trae → Settings → MCP, or edit .trae/mcp.json / global mcp.json
- Click Copy config and merge mcpServers
- Replace <placeholders> in env with real secrets
- Save and reload Trae
{
"mcpServers": {
"image-generation-mcp": {
"command": "uvx",
"args": [
"image-generation-mcp"
]
}
}
}Cherry Studio — MCP settings (local)
- Cherry Studio → Settings → MCP Servers → Add (STDIO)
- Or import JSON: click Copy config and merge mcpServers
- Replace <placeholders> in env; ensure Node.js / uv (npx, uvx) are installed
- Enable the server and check tools load
{
"mcpServers": {
"image-generation-mcp": {
"command": "uvx",
"args": [
"image-generation-mcp"
]
}
}
}Tongyi Lingma — MCP config (local)
- Lingma Settings → MCP → + → STDIO or config file
- Click Copy config and merge mcpServers
- Replace <placeholders> in env; need Node.js 18+ (npx) or uv (uvx)
- Confirm connected before using tools in agent chat
{
"mcpServers": {
"image-generation-mcp": {
"command": "uvx",
"args": [
"image-generation-mcp"
]
}
}
}Windsurf — mcp_config.json (local)
- Edit ~/.codeium/windsurf/mcp_config.json
- Click Copy config and merge mcpServers (stdio same as Cursor)
- Replace <placeholders> in env, save, refresh Cascade
{
"mcpServers": {
"image-generation-mcp": {
"command": "uvx",
"args": [
"image-generation-mcp"
]
}
}
}Cline — MCP Servers (local)
- Cline panel → Settings → MCP Servers
- Click Copy config and merge
- Replace <placeholders> in env, then save
{
"mcpServers": {
"image-generation-mcp": {
"command": "uvx",
"args": [
"image-generation-mcp"
]
}
}
}WorkBuddy — .workbuddy/mcp.json (local)
- Edit ~/.workbuddy/mcp.json (user) or project .workbuddy/mcp.json
- Or Plugins → MCP Servers → Configure MCP and paste the JSON below
- Replace <placeholders> in env; on Windows prefer absolute paths for command/scripts
- Save, restart WorkBuddy, confirm connector status is green
{
"mcpServers": {
"image-generation-mcp": {
"command": "uvx",
"args": [
"image-generation-mcp"
]
}
}
}Troubleshooting & Common ErrorsFAQ
Common connection errors and verified fixes for Image Generation MCP Server
Getting 'connection closed' or exit code 1 in Cursor / Claude Code for Image Generation MCP Server?
Usually caused by missing runtime paths or IDE environment inheritance. Fix steps: 1. Verify Node.js 18+ (npx) or Python 3.10+ (uvx) is installed; 2. Run 'which npx' or 'which uvx' in terminal, and replace 'command' with absolute path; 3. Reload or restart the client window after modifying config.
# Check binary path in terminal: which npx node -v
Getting 'spawn npx ENOENT' or 'command not found'?
The editor background process does not inherit your full terminal PATH. Solution: Globally install the package, or set the absolute binary path (e.g. C:\Program Files\nodejs\npx.cmd on Windows, or /usr/local/bin/npx on macOS).
Missing required environment variable or authentication failure?
Image Generation MCP Server requires environment variables (IMAGE_GENERATION_MCP_KV_STORE_URL、IMAGE_GENERATION_MCP_TOOLS_ALLOW、IMAGE_GENERATION_MCP_TOOLS_DENY、IMAGE_GENERATION_MCP_SERVER_NAME、IMAGE_GENERATION_MCP_INSTRUCTIONS、FASTMCP_LOG_LEVEL、FASTMCP_ENABLE_RICH_LOGGING、IMAGE_GENERATION_MCP_A1111_HOST、IMAGE_GENERATION_MCP_A1111_MODEL、IMAGE_GENERATION_MCP_READ_ONLY、IMAGE_GENERATION_MCP_SCRATCH_DIR、IMAGE_GENERATION_MCP_OPENAI_API_KEY、IMAGE_GENERATION_MCP_GOOGLE_API_KEY、IMAGE_GENERATION_MCP_SD_WEBUI_HOST、IMAGE_GENERATION_MCP_SD_WEBUI_MODEL、IMAGE_GENERATION_MCP_DEFAULT_PROVIDER、IMAGE_GENERATION_MCP_TRANSFORM_CACHE_SIZE、IMAGE_GENERATION_MCP_PAID_PROVIDERS、IMAGE_GENERATION_MCP_STYLES_DIR、IMAGE_GENERATION_MCP_ALLOW_LOCAL_FILE_INPUT、IMAGE_GENERATION_MCP_MAX_INPUT_IMAGE_BYTES、IMAGE_GENERATION_MCP_FETCH_TIMEOUT_S、IMAGE_GENERATION_MCP_TRANSFER_TTL_DEFAULT_S、IMAGE_GENERATION_MCP_TRANSFER_TTL_MAX_S、IMAGE_GENERATION_MCP_TRANSFER_GRACE_TTL_S、IMAGE_GENERATION_MCP_TRANSFER_LEASE_S、IMAGE_GENERATION_MCP_TRANSFER_MAX_UPLOAD_BYTES、IMAGE_GENERATION_MCP_BASE_URL、IMAGE_GENERATION_MCP_BEARER_TOKEN、IMAGE_GENERATION_MCP_OIDC_CONFIG_URL、IMAGE_GENERATION_MCP_OIDC_CLIENT_ID、IMAGE_GENERATION_MCP_OIDC_CLIENT_SECRET、IMAGE_GENERATION_MCP_OIDC_AUDIENCE、IMAGE_GENERATION_MCP_OIDC_REQUIRED_SCOPES、IMAGE_GENERATION_MCP_OIDC_ADVERTISED_SCOPES、IMAGE_GENERATION_MCP_OIDC_JWT_SIGNING_KEY、IMAGE_GENERATION_MCP_OIDC_VERIFY_ACCESS_TOKEN、IMAGE_GENERATION_MCP_KV_STORE_URL、IMAGE_GENERATION_MCP_APP_DOMAIN、IMAGE_GENERATION_MCP_TOOLS_ALLOW、IMAGE_GENERATION_MCP_TOOLS_DENY、IMAGE_GENERATION_MCP_AUTH_MODE、IMAGE_GENERATION_MCP_BEARER_TOKENS_FILE、IMAGE_GENERATION_MCP_BEARER_DEFAULT_SUBJECT、IMAGE_GENERATION_MCP_SERVER_NAME、IMAGE_GENERATION_MCP_INSTRUCTIONS、IMAGE_GENERATION_MCP_HTTP_PATH、PUID、PGID、FASTMCP_LOG_LEVEL、FASTMCP_ENABLE_RICH_LOGGING、IMAGE_GENERATION_MCP_A1111_HOST、IMAGE_GENERATION_MCP_A1111_MODEL、IMAGE_GENERATION_MCP_READ_ONLY、IMAGE_GENERATION_MCP_SCRATCH_DIR、IMAGE_GENERATION_MCP_OPENAI_API_KEY、IMAGE_GENERATION_MCP_GOOGLE_API_KEY、IMAGE_GENERATION_MCP_SD_WEBUI_HOST、IMAGE_GENERATION_MCP_SD_WEBUI_MODEL、IMAGE_GENERATION_MCP_DEFAULT_PROVIDER、IMAGE_GENERATION_MCP_TRANSFORM_CACHE_SIZE、IMAGE_GENERATION_MCP_PAID_PROVIDERS、IMAGE_GENERATION_MCP_STYLES_DIR、IMAGE_GENERATION_MCP_ALLOW_LOCAL_FILE_INPUT、IMAGE_GENERATION_MCP_MAX_INPUT_IMAGE_BYTES、IMAGE_GENERATION_MCP_FETCH_TIMEOUT_S、IMAGE_GENERATION_MCP_TRANSFER_TTL_DEFAULT_S、IMAGE_GENERATION_MCP_TRANSFER_TTL_MAX_S、IMAGE_GENERATION_MCP_TRANSFER_GRACE_TTL_S、IMAGE_GENERATION_MCP_TRANSFER_LEASE_S、IMAGE_GENERATION_MCP_TRANSFER_MAX_UPLOAD_BYTES). Ensure you have added valid keys under the 'env' object in your config file without trailing whitespace.
// .cursor/mcp.json 或 claude_desktop_config.json
{
"env": {
"API_KEY": "your_actual_key_here"
}
}Tool Mock Playground
SandboxImage Generation MCP Server Tool Interface Simulation · Preview tool schema & outputs without local runtime
{
"target": "Image Generation MCP Server",
"action": "execute",
"options": {
"mode": "standard",
"timeoutMs": 5000
}
}Click 'Run Mock' above
to preview the raw response returned to the LLM
Decision Guide: Why & When to Use
Assess suitability before installing to save trial-and-error time
- PR review
- Changelog generation
- Cross-repo issue search
- Replacing human security audit
- Unauthorized repo access
Image Generation MCP Server + Scenario Prompt → Complete Agent Automation
MCP hands-on: install to visible results
Follow the full lab (expected UI/output + contrast checks). After installing this item, verify with the tutorial prompts.
Related resources
ssh-mcp-pro
v1.17.0
io.github.oaslananka/ssh-mcp-pro
Secure MCP SSH automation server with policy controls, resources, prompts, stdio, and HTTP.
flint
v1.19.6
io.github.synuns/flint
Agent long-term memory with search, recording, and hot injection for AI coding agents
Agent Data Tools: Web, documents and search
v1.331.0
io.github.Nutshell2000/agent-data-tools-web
30 tools: web pages, JS apps and PDFs as text, feeds, sitemaps, search. 10 free calls.
Agent Data Tools: Speech to text and text to speech
v1.331.0
io.github.Nutshell2000/agent-data-tools-voice
Transcribe audio and video (SRT/VTT subtitles, an hour for $0.05) and text to speech as MP3.
Agent Data Tools: Utilities
v1.331.0
io.github.Nutshell2000/agent-data-tools-utilities
109 tools: JSON repair, CSV, hashes, cron, dates, units, validators. 10 free calls.
Agent Data Tools: Prices and DeFi
v1.331.0
io.github.Nutshell2000/agent-data-tools-prices
53 tools: token prices, wallet and contract risk, liquidity pools, FX. 10 free calls.
Often paired with
insurance-advisor-china
v2.4.21
io.clawhub.mnetfairy/insurance-advisor-china
中国大陆AI保险顾问。为个人和家庭提供全方位的保险咨询、产品对比、方案设计、投保指导。当用户询问保险配置、保险方案、产品对比、重疾险/医疗险/寿险/意外险/储蓄险推荐、保费计算、保障缺口分析、需求分析、核保合规、理赔等问题时使用。发布产物仅含 SKILL.md + 3 个只读参考文件(references/products.json、insurance-knowledge.md、compliance.md)+ 3 个运行时脚本(needs_analyzer / premium_calculator / plan_designer);数据清洗脚本与回归测试脚本是本地维护工具,不随发布产物分发。
ai-insurance-advisor
v2.4.21
io.clawhub.mnetfairy/ai-insurance-advisor
中国大陆保险顾问。本 skill 覆盖 8 项能力:保险需求分析(needs_analyzer.py)、产品对比(premium_calculator.py + 本地 products.json)、保费计算(premium_calculator.py)、方案设计(plan_designer.py)、保险知识问答(insurance-knowledge.md)、合规要点提示(compliance.md)、朋友圈/社交营销文案生成(agent LLM 生成,无专属脚本)、培训话术支持(agent LLM 生成,无专属脚本)。不提供核保预审、理赔代办、代理人展业工具等能力——这些场景请转人工或调用专业服务。发布产物仅含 SKILL.md + 3 个只读参考文件 + 3 个运行时脚本(needs_analyzer / premium_calculator / plan_designer);数据清洗与回归测试脚本为本地维护工具,不随发布产物分发。
中文公文写作
v2.0.63
io.clawhub.gongyu0918-debug/chinese-official-writing
用于中文公文、事务性材料和新闻稿件的起草、改写、压缩、润色、审校、文种核对、去口语化、降 AI 味及 Word 格式处理,适用于机关、企事业单位、学校和新闻机构。涵盖申请、请示、报告、通知、通告、意见、决定、决议、议案、公报、命令、函、复函、批复、说明、方案、纪要、公告、公示、通报、制度、规定、办法、细则、操作规程、工作要点、总结、调研、讲话、致辞、主持词、述职、可研、审查材料、技术需求、新闻消息、编者按、新闻评论,以及采购、整改、反馈和 AI 算力等场景。
Free Ride - Unlimited free AI
v1.1.0
io.clawhub.shaivpidadi/free-ride
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Optional Groq, Gemini and Cerebras free tiers are opt-in. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
Keep exploring AgentHub
Most people compare similar tools or check scenario guides before installing—start here.
Listing badge: put AgentHub on your site
Copy either snippet into your project homepage, docs, or GitHub README. The badge is a hotlinked SVG — nothing to host — and it links back to this page so visitors can find the install steps.
<a href="https://myagenthub.cn/p/io.github.pvliesdonk/image-generation-mcp" title="Listed on AgentHub: Image Generation MCP Server" target="_blank" rel="noopener">
<img src="https://myagenthub.cn/badge/io.github.pvliesdonk/image-generation-mcp?lang=en" alt="Listed on AgentHub: Image Generation MCP Server" height="20" style="border:0"/>
</a>[](https://myagenthub.cn/p/io.github.pvliesdonk/image-generation-mcp)Badges are generated on the fly from /badge/<package-id>, so name and listing changes propagate automatically. Keep the link target unchanged — it is what counts as the referral.
Unified Manifest
{
"id": "io.github.pvliesdonk/image-generation-mcp",
"type": "mcp-server",
"version": "1.12.1",
"displayName": "Image Generation MCP Server",
"description": "MCP server for AI image generation via OpenAI, Stable Diffusion (SD WebUI), or placeholders.",
"repository": {
"url": "https://github.com/pvliesdonk/image-generation-mcp",
"source": "github"
},
"homepage": "https://pvliesdonk.github.io/image-generation-mcp/",
"distribution": {
"packages": [
{
"registryType": "pypi",
"identifier": "image-generation-mcp",
"version": "1.12.1",
"runtimeHint": "uvx",
"transport": "stdio",
"environmentVariables": [
{
"name": "IMAGE_GENERATION_MCP_KV_STORE_URL",
"description": "Persistent-state backend URL shared by every pvl-core subsystem that needs state. `memory://` is in-process and lost on restart; `file:///path` persists on one server; `redis://`, `dynamodb://` and `mongodb://` each need their matching extra. When unset, defaults to `file:///data/state` (the volume family Docker images mount), or to `memory://` — with a warning — on a host where that directory is not usable."
},
{
"name": "IMAGE_GENERATION_MCP_TOOLS_ALLOW",
"description": "Comma-separated explicit tool names this instance exposes; every other tool is hidden from listings and cannot be invoked. Names matching no registered tool are inert. Mutually exclusive with `tools_deny`. Takes effect through `apply_tool_visibility`."
},
{
"name": "IMAGE_GENERATION_MCP_TOOLS_DENY",
"description": "Comma-separated explicit tool names hidden from this instance (absent from listings, cannot be invoked). Names matching no registered tool are inert. Mutually exclusive with `tools_allow`. Takes effect through `apply_tool_visibility`."
},
{
"name": "IMAGE_GENERATION_MCP_SERVER_NAME",
"description": "Rename this server instance; defaults to the project name."
},
{
"name": "IMAGE_GENERATION_MCP_INSTRUCTIONS",
"description": "Replaces the default MCP instructions text sent to clients."
},
{
"name": "FASTMCP_LOG_LEVEL",
"description": "Log level for FastMCP internals and app loggers (DEBUG / INFO / WARNING / ERROR / CRITICAL). The -v CLI flag overrides to DEBUG."
},
{
"name": "FASTMCP_ENABLE_RICH_LOGGING",
"description": "Set false for plain or structured JSON log output."
},
{
"name": "IMAGE_GENERATION_MCP_A1111_HOST",
"description": "Deprecated alias for IMAGE_GENERATION_MCP_SD_WEBUI_HOST; logs a warning when used."
},
{
"name": "IMAGE_GENERATION_MCP_A1111_MODEL",
"description": "Deprecated alias for IMAGE_GENERATION_MCP_SD_WEBUI_MODEL; logs a warning when used."
},
{
"name": "IMAGE_GENERATION_MCP_READ_ONLY",
"description": "When true, write-tagged tools (image generation, transforms, uploads) are hidden from clients. Set false to enable them."
},
{
"name": "IMAGE_GENERATION_MCP_SCRATCH_DIR",
"description": "Directory where generated images are saved. Created automatically on first use."
},
{
"name": "IMAGE_GENERATION_MCP_OPENAI_API_KEY",
"description": "OpenAI API key. Enables the OpenAI provider (gpt-image-2, gpt-image-1.5, dall-e-3) when set.",
"isSecret": true
},
{
"name": "IMAGE_GENERATION_MCP_GOOGLE_API_KEY",
"description": "Google API key. Enables the Gemini provider (gemini-3.1-flash-image and others) when set. Get a key at https://aistudio.google.com/apikey.",
"isSecret": true
},
{
"name": "IMAGE_GENERATION_MCP_SD_WEBUI_HOST",
"description": "SD WebUI base URL (such as http://localhost:7860). Enables the SD WebUI provider when set. Compatible with AUTOMATIC1111, Forge, reForge, and Forge-neo."
},
{
"name": "IMAGE_GENERATION_MCP_SD_WEBUI_MODEL",
"description": "SD WebUI checkpoint name, used for model-aware preset detection (SD 1.5 / SDXL / Lightning) and checkpoint override. Unset uses the instance's current model."
},
{
"name": "IMAGE_GENERATION_MCP_DEFAULT_PROVIDER",
"description": "Provider used when no keyword triggers auto-selection: auto, openai, gemini, sd_webui, or placeholder. auto picks the first configured provider."
},
{
"name": "IMAGE_GENERATION_MCP_TRANSFORM_CACHE_SIZE",
"description": "Maximum number of transformed image results (resize, crop, convert) kept in memory. Set 0 to disable caching."
},
{
"name": "IMAGE_GENERATION_MCP_PAID_PROVIDERS",
"description": "Comma-separated provider names that cost money; generate_image asks for confirmation (client elicitation) before using them. An empty value falls back to this default; to disable confirmation, set a value that names no provider (such as none)."
},
{
"name": "IMAGE_GENERATION_MCP_STYLES_DIR",
"description": "Directory for style preset files (Markdown with YAML front matter). Created automatically if it does not exist."
},
{
"name": "IMAGE_GENERATION_MCP_ALLOW_LOCAL_FILE_INPUT",
"description": "Allow reading input images from local filesystem paths. Off by default: only URLs and uploads are accepted."
},
{
"name": "IMAGE_GENERATION_MCP_MAX_INPUT_IMAGE_BYTES",
"description": "Maximum accepted input image size in bytes."
},
{
"name": "IMAGE_GENERATION_MCP_FETCH_TIMEOUT_S",
"description": "HTTP timeout in seconds when fetching remote image URLs (fetch_image and URL inputs)."
},
{
"name": "IMAGE_GENERATION_MCP_TRANSFER_TTL_DEFAULT_S",
"description": "Link lifetime in seconds when the caller requests no explicit TTL."
},
{
"name": "IMAGE_GENERATION_MCP_TRANSFER_TTL_MAX_S",
"description": "Ceiling in seconds a caller-requested link TTL is clamped to."
},
{
"name": "IMAGE_GENERATION_MCP_TRANSFER_GRACE_TTL_S",
"description": "Post-success grace window in seconds: a served token's TTL shrinks to this so a stalled transfer can retry within it."
},
{
"name": "IMAGE_GENERATION_MCP_TRANSFER_LEASE_S",
"description": "Crashed-handler reclaim window in seconds for an in-flight reservation."
},
{
"name": "IMAGE_GENERATION_MCP_TRANSFER_MAX_UPLOAD_BYTES",
"description": "Maximum size in bytes of a single upload."
}
]
},
{
"registryType": "oci",
"identifier": "ghcr.io/pvliesdonk/image-generation-mcp:v1.12.1",
"transport": "streamable-http",
"environmentVariables": [
{
"name": "IMAGE_GENERATION_MCP_BASE_URL",
"description": "Public base URL of the deployed server, e.g. `https://mcp.example.com`. Required for OIDC. Also the fallback source of the MCP Apps domain when `app_domain` is unset."
},
{
"name": "IMAGE_GENERATION_MCP_BEARER_TOKEN",
"description": "Single shared bearer token; enables bearer auth unless `bearer_tokens_file` is set, which takes precedence.",
"isSecret": true
},
{
"name": "IMAGE_GENERATION_MCP_OIDC_CONFIG_URL",
"description": "OIDC discovery document URL, e.g. `https://auth.example.com/.well-known/openid-configuration`."
},
{
"name": "IMAGE_GENERATION_MCP_OIDC_CLIENT_ID",
"description": "OIDC client identifier registered with the provider."
},
{
"name": "IMAGE_GENERATION_MCP_OIDC_CLIENT_SECRET",
"description": "OIDC client secret registered with the provider.",
"isSecret": true
},
{
"name": "IMAGE_GENERATION_MCP_OIDC_AUDIENCE",
"description": "Expected `aud` claim; tokens issued for another audience are rejected."
},
{
"name": "IMAGE_GENERATION_MCP_OIDC_REQUIRED_SCOPES",
"description": "Scopes a caller must present, space- or comma-separated. Defaults to `openid` in oidc-proxy mode."
},
{
"name": "IMAGE_GENERATION_MCP_OIDC_ADVERTISED_SCOPES",
"description": "Scopes advertised to MCP clients in protected-resource metadata, space- or comma-separated. Overrides the default `openid offline_access`; `oidc_required_scopes` is always added on top. Set this when the registered client is not permitted `offline_access`, or to have clients request extra claim scopes (e.g. `groups`) without also requiring them in every token."
},
{
"name": "IMAGE_GENERATION_MCP_OIDC_JWT_SIGNING_KEY",
"description": "Signing key for issued JWTs; used in oidc-proxy mode only. When unset, the key is derived deterministically from `oidc_client_secret`, so tokens survive a restart — but rotating that secret invalidates every issued token. Set this explicitly to decouple token validity from secret rotation. Generate with `openssl rand -hex 32`.",
"isSecret": true
},
{
"name": "IMAGE_GENERATION_MCP_OIDC_VERIFY_ACCESS_TOKEN",
"description": "Validate the access token instead of the id token."
},
{
"name": "IMAGE_GENERATION_MCP_KV_STORE_URL",
"description": "Persistent-state backend URL shared by every pvl-core subsystem that needs state. `memory://` is in-process and lost on restart; `file:///path` persists on one server; `redis://`, `dynamodb://` and `mongodb://` each need their matching extra. When unset, defaults to `file:///data/state` (the volume family Docker images mount), or to `memory://` — with a warning — on a host where that directory is not usable."
},
{
"name": "IMAGE_GENERATION_MCP_APP_DOMAIN",
"description": "MCP Apps iframe domain, used for CSP sandboxing. Overrides the host derived from `base_url`."
},
{
"name": "IMAGE_GENERATION_MCP_TOOLS_ALLOW",
"description": "Comma-separated explicit tool names this instance exposes; every other tool is hidden from listings and cannot be invoked. Names matching no registered tool are inert. Mutually exclusive with `tools_deny`. Takes effect through `apply_tool_visibility`."
},
{
"name": "IMAGE_GENERATION_MCP_TOOLS_DENY",
"description": "Comma-separated explicit tool names hidden from this instance (absent from listings, cannot be invoked). Names matching no registered tool are inert. Mutually exclusive with `tools_allow`. Takes effect through `apply_tool_visibility`."
},
{
"name": "IMAGE_GENERATION_MCP_AUTH_MODE",
"description": "Explicit auth-mode override, accepting `remote` or `oidc-proxy` (case- and whitespace-insensitive). When unset the mode is auto-detected from which auth variables are set; the override exists because having all four OIDC variables set is ambiguous between those two modes. Other values are ignored with a warning."
},
{
"name": "IMAGE_GENERATION_MCP_BEARER_TOKENS_FILE",
"description": "Path to a TOML file mapping bearer tokens to subjects; overrides the single-token `bearer_token` mode."
},
{
"name": "IMAGE_GENERATION_MCP_BEARER_DEFAULT_SUBJECT",
"description": "Subject assigned to the single-token bearer mode; ignored when `bearer_tokens_file` is set, since mapped mode carries per-token subjects."
},
{
"name": "IMAGE_GENERATION_MCP_SERVER_NAME",
"description": "Rename this server instance; defaults to the project name."
},
{
"name": "IMAGE_GENERATION_MCP_INSTRUCTIONS",
"description": "Replaces the default MCP instructions text sent to clients."
},
{
"name": "IMAGE_GENERATION_MCP_HTTP_PATH",
"description": "Mount path for the MCP endpoint."
},
{
"name": "PUID",
"description": "Run the server process as this UID; the container entrypoint chowns writable paths to match."
},
{
"name": "PGID",
"description": "Run the server process as this GID; pair with PUID to match the owner of a mounted volume."
},
{
"name": "FASTMCP_LOG_LEVEL",
"description": "Log level for FastMCP internals and app loggers (DEBUG / INFO / WARNING / ERROR / CRITICAL). The -v CLI flag overrides to DEBUG."
},
{
"name": "FASTMCP_ENABLE_RICH_LOGGING",
"description": "Set false for plain or structured JSON log output."
},
{
"name": "IMAGE_GENERATION_MCP_A1111_HOST",
"description": "Deprecated alias for IMAGE_GENERATION_MCP_SD_WEBUI_HOST; logs a warning when used."
},
{
"name": "IMAGE_GENERATION_MCP_A1111_MODEL",
"description": "Deprecated alias for IMAGE_GENERATION_MCP_SD_WEBUI_MODEL; logs a warning when used."
},
{
"name": "IMAGE_GENERATION_MCP_READ_ONLY",
"description": "When true, write-tagged tools (image generation, transforms, uploads) are hidden from clients. Set false to enable them."
},
{
"name": "IMAGE_GENERATION_MCP_SCRATCH_DIR",
"description": "Directory where generated images are saved. Created automatically on first use."
},
{
"name": "IMAGE_GENERATION_MCP_OPENAI_API_KEY",
"description": "OpenAI API key. Enables the OpenAI provider (gpt-image-2, gpt-image-1.5, dall-e-3) when set.",
"isSecret": true
},
{
"name": "IMAGE_GENERATION_MCP_GOOGLE_API_KEY",
"description": "Google API key. Enables the Gemini provider (gemini-3.1-flash-image and others) when set. Get a key at https://aistudio.google.com/apikey.",
"isSecret": true
},
{
"name": "IMAGE_GENERATION_MCP_SD_WEBUI_HOST",
"description": "SD WebUI base URL (such as http://localhost:7860). Enables the SD WebUI provider when set. Compatible with AUTOMATIC1111, Forge, reForge, and Forge-neo."
},
{
"name": "IMAGE_GENERATION_MCP_SD_WEBUI_MODEL",
"description": "SD WebUI checkpoint name, used for model-aware preset detection (SD 1.5 / SDXL / Lightning) and checkpoint override. Unset uses the instance's current model."
},
{
"name": "IMAGE_GENERATION_MCP_DEFAULT_PROVIDER",
"description": "Provider used when no keyword triggers auto-selection: auto, openai, gemini, sd_webui, or placeholder. auto picks the first configured provider."
},
{
"name": "IMAGE_GENERATION_MCP_TRANSFORM_CACHE_SIZE",
"description": "Maximum number of transformed image results (resize, crop, convert) kept in memory. Set 0 to disable caching."
},
{
"name": "IMAGE_GENERATION_MCP_PAID_PROVIDERS",
"description": "Comma-separated provider names that cost money; generate_image asks for confirmation (client elicitation) before using them. An empty value falls back to this default; to disable confirmation, set a value that names no provider (such as none)."
},
{
"name": "IMAGE_GENERATION_MCP_STYLES_DIR",
"description": "Directory for style preset files (Markdown with YAML front matter). Created automatically if it does not exist."
},
{
"name": "IMAGE_GENERATION_MCP_ALLOW_LOCAL_FILE_INPUT",
"description": "Allow reading input images from local filesystem paths. Off by default: only URLs and uploads are accepted."
},
{
"name": "IMAGE_GENERATION_MCP_MAX_INPUT_IMAGE_BYTES",
"description": "Maximum accepted input image size in bytes."
},
{
"name": "IMAGE_GENERATION_MCP_FETCH_TIMEOUT_S",
"description": "HTTP timeout in seconds when fetching remote image URLs (fetch_image and URL inputs)."
},
{
"name": "IMAGE_GENERATION_MCP_TRANSFER_TTL_DEFAULT_S",
"description": "Link lifetime in seconds when the caller requests no explicit TTL."
},
{
"name": "IMAGE_GENERATION_MCP_TRANSFER_TTL_MAX_S",
"description": "Ceiling in seconds a caller-requested link TTL is clamped to."
},
{
"name": "IMAGE_GENERATION_MCP_TRANSFER_GRACE_TTL_S",
"description": "Post-success grace window in seconds: a served token's TTL shrinks to this so a stalled transfer can retry within it."
},
{
"name": "IMAGE_GENERATION_MCP_TRANSFER_LEASE_S",
"description": "Crashed-handler reclaim window in seconds for an in-flight reservation."
},
{
"name": "IMAGE_GENERATION_MCP_TRANSFER_MAX_UPLOAD_BYTES",
"description": "Maximum size in bytes of a single upload."
}
]
}
],
"remotes": []
},
"dependencies": [],
"installTargets": [
"claude-code",
"claude-desktop",
"cursor",
"vscode",
"trae",
"cherry-studio",
"lingma",
"windsurf",
"cline",
"workbuddy"
],
"keywords": [],
"provenance": {
"origin": "official-mcp-registry",
"originalId": "io.github.pvliesdonk/image-generation-mcp",
"originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.pvliesdonk%2Fimage-generation-mcp/versions/latest",
"isOfficial": true,
"status": "active"
}
}