Image Generation MCP Server

Image Generation MCP Server is an MCP integration. MCP server for AI image generation via OpenAI, Stable Diffusion (SD WebUI), or placeholders.

Packages and local setup

The published pypi package is image-generation-mcp, version 1.12.1. Its declared MCP transport is stdio.

The package declares IMAGE_GENERATION_MCP_KV_STORE_URL: 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.; IMAGE_GENERATION_MCP_TOOLS_ALLOW: 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.; IMAGE_GENERATION_MCP_TOOLS_DENY: 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.; IMAGE_GENERATION_MCP_SERVER_NAME: Rename this server instance; defaults to the project name.; IMAGE_GENERATION_MCP_INSTRUCTIONS: Replaces the default MCP instructions text sent to clients.; FASTMCP_LOG_LEVEL: Log level for FastMCP internals and app loggers (DEBUG / INFO / WARNING / ERROR / CRITICAL). The -v CLI flag overrides to DEBUG.; FASTMCP_ENABLE_RICH_LOGGING: Set false for plain or structured JSON log output.; IMAGE_GENERATION_MCP_A1111_HOST: Deprecated alias for IMAGE_GENERATION_MCP_SD_WEBUI_HOST; logs a warning when used.; IMAGE_GENERATION_MCP_A1111_MODEL: Deprecated alias for IMAGE_GENERATION_MCP_SD_WEBUI_MODEL; logs a warning when used.; IMAGE_GENERATION_MCP_READ_ONLY: When true, write-tagged tools (image generation, transforms, uploads) are hidden from clients. Set false to enable them.; IMAGE_GENERATION_MCP_SCRATCH_DIR: Directory where generated images are saved. Created automatically on first use.; IMAGE_GENERATION_MCP_OPENAI_API_KEY: OpenAI API key. Enables the OpenAI provider (gpt-image-2, gpt-image-1.5, dall-e-3) when set.; IMAGE_GENERATION_MCP_GOOGLE_API_KEY: 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.; IMAGE_GENERATION_MCP_SD_WEBUI_HOST: SD WebUI base URL (such as http://localhost:7860). Enables the SD WebUI provider when set. Compatible with AUTOMATIC1111, Forge, reForge, and Forge-neo.; IMAGE_GENERATION_MCP_SD_WEBUI_MODEL: 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.; IMAGE_GENERATION_MCP_DEFAULT_PROVIDER: Provider used when no keyword triggers auto-selection: auto, openai, gemini, sd_webui, or placeholder. auto picks the first configured provider.; IMAGE_GENERATION_MCP_TRANSFORM_CACHE_SIZE: Maximum number of transformed image results (resize, crop, convert) kept in memory. Set 0 to disable caching.; IMAGE_GENERATION_MCP_PAID_PROVIDERS: 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).; IMAGE_GENERATION_MCP_STYLES_DIR: Directory for style preset files (Markdown with YAML front matter). Created automatically if it does not exist.; IMAGE_GENERATION_MCP_ALLOW_LOCAL_FILE_INPUT: Allow reading input images from local filesystem paths. Off by default: only URLs and uploads are accepted.; IMAGE_GENERATION_MCP_MAX_INPUT_IMAGE_BYTES: Maximum accepted input image size in bytes.; IMAGE_GENERATION_MCP_FETCH_TIMEOUT_S: HTTP timeout in seconds when fetching remote image URLs (fetch_image and URL inputs).; IMAGE_GENERATION_MCP_TRANSFER_TTL_DEFAULT_S: Link lifetime in seconds when the caller requests no explicit TTL.; IMAGE_GENERATION_MCP_TRANSFER_TTL_MAX_S: Ceiling in seconds a caller-requested link TTL is clamped to.; IMAGE_GENERATION_MCP_TRANSFER_GRACE_TTL_S: Post-success grace window in seconds: a served token's TTL shrinks to this so a stalled transfer can retry within it.; IMAGE_GENERATION_MCP_TRANSFER_LEASE_S: Crashed-handler reclaim window in seconds for an in-flight reservation.; IMAGE_GENERATION_MCP_TRANSFER_MAX_UPLOAD_BYTES: Maximum size in bytes of a single upload..

The published oci package is ghcr.io/pvliesdonk/image-generation-mcp:v1.12.1. Its declared MCP transport is streamable-http.

The package declares IMAGE_GENERATION_MCP_BASE_URL: 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.; IMAGE_GENERATION_MCP_BEARER_TOKEN: Single shared bearer token; enables bearer auth unless bearer_tokens_file is set, which takes precedence.; IMAGE_GENERATION_MCP_OIDC_CONFIG_URL: OIDC discovery document URL, e.g. https://auth.example.com/.well-known/openid-configuration.; IMAGE_GENERATION_MCP_OIDC_CLIENT_ID: OIDC client identifier registered with the provider.; IMAGE_GENERATION_MCP_OIDC_CLIENT_SECRET: OIDC client secret registered with the provider.; IMAGE_GENERATION_MCP_OIDC_AUDIENCE: Expected aud claim; tokens issued for another audience are rejected.; IMAGE_GENERATION_MCP_OIDC_REQUIRED_SCOPES: Scopes a caller must present, space- or comma-separated. Defaults to openid in oidc-proxy mode.; IMAGE_GENERATION_MCP_OIDC_ADVERTISED_SCOPES: 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.; IMAGE_GENERATION_MCP_OIDC_JWT_SIGNING_KEY: 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.; IMAGE_GENERATION_MCP_OIDC_VERIFY_ACCESS_TOKEN: Validate the access token instead of the id token.; IMAGE_GENERATION_MCP_KV_STORE_URL: 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.; IMAGE_GENERATION_MCP_APP_DOMAIN: MCP Apps iframe domain, used for CSP sandboxing. Overrides the host derived from base_url.; IMAGE_GENERATION_MCP_TOOLS_ALLOW: 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.; IMAGE_GENERATION_MCP_TOOLS_DENY: 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.; IMAGE_GENERATION_MCP_AUTH_MODE: 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.; IMAGE_GENERATION_MCP_BEARER_TOKENS_FILE: Path to a TOML file mapping bearer tokens to subjects; overrides the single-token bearer_token mode.; IMAGE_GENERATION_MCP_BEARER_DEFAULT_SUBJECT: Subject assigned to the single-token bearer mode; ignored when bearer_tokens_file is set, since mapped mode carries per-token subjects.; IMAGE_GENERATION_MCP_SERVER_NAME: Rename this server instance; defaults to the project name.; IMAGE_GENERATION_MCP_INSTRUCTIONS: Replaces the default MCP instructions text sent to clients.; IMAGE_GENERATION_MCP_HTTP_PATH: Mount path for the MCP endpoint.; PUID: Run the server process as this UID; the container entrypoint chowns writable paths to match.; PGID: Run the server process as this GID; pair with PUID to match the owner of a mounted volume.; FASTMCP_LOG_LEVEL: Log level for FastMCP internals and app loggers (DEBUG / INFO / WARNING / ERROR / CRITICAL). The -v CLI flag overrides to DEBUG.; FASTMCP_ENABLE_RICH_LOGGING: Set false for plain or structured JSON log output.; IMAGE_GENERATION_MCP_A1111_HOST: Deprecated alias for IMAGE_GENERATION_MCP_SD_WEBUI_HOST; logs a warning when used.; IMAGE_GENERATION_MCP_A1111_MODEL: Deprecated alias for IMAGE_GENERATION_MCP_SD_WEBUI_MODEL; logs a warning when used.; IMAGE_GENERATION_MCP_READ_ONLY: When true, write-tagged tools (image generation, transforms, uploads) are hidden from clients. Set false to enable them.; IMAGE_GENERATION_MCP_SCRATCH_DIR: Directory where generated images are saved. Created automatically on first use.; IMAGE_GENERATION_MCP_OPENAI_API_KEY: OpenAI API key. Enables the OpenAI provider (gpt-image-2, gpt-image-1.5, dall-e-3) when set.; IMAGE_GENERATION_MCP_GOOGLE_API_KEY: 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.; IMAGE_GENERATION_MCP_SD_WEBUI_HOST: SD WebUI base URL (such as http://localhost:7860). Enables the SD WebUI provider when set. Compatible with AUTOMATIC1111, Forge, reForge, and Forge-neo.; IMAGE_GENERATION_MCP_SD_WEBUI_MODEL: 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.; IMAGE_GENERATION_MCP_DEFAULT_PROVIDER: Provider used when no keyword triggers auto-selection: auto, openai, gemini, sd_webui, or placeholder. auto picks the first configured provider.; IMAGE_GENERATION_MCP_TRANSFORM_CACHE_SIZE: Maximum number of transformed image results (resize, crop, convert) kept in memory. Set 0 to disable caching.; IMAGE_GENERATION_MCP_PAID_PROVIDERS: 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).; IMAGE_GENERATION_MCP_STYLES_DIR: Directory for style preset files (Markdown with YAML front matter). Created automatically if it does not exist.; IMAGE_GENERATION_MCP_ALLOW_LOCAL_FILE_INPUT: Allow reading input images from local filesystem paths. Off by default: only URLs and uploads are accepted.; IMAGE_GENERATION_MCP_MAX_INPUT_IMAGE_BYTES: Maximum accepted input image size in bytes.; IMAGE_GENERATION_MCP_FETCH_TIMEOUT_S: HTTP timeout in seconds when fetching remote image URLs (fetch_image and URL inputs).; IMAGE_GENERATION_MCP_TRANSFER_TTL_DEFAULT_S: Link lifetime in seconds when the caller requests no explicit TTL.; IMAGE_GENERATION_MCP_TRANSFER_TTL_MAX_S: Ceiling in seconds a caller-requested link TTL is clamped to.; IMAGE_GENERATION_MCP_TRANSFER_GRACE_TTL_S: Post-success grace window in seconds: a served token's TTL shrinks to this so a stalled transfer can retry within it.; IMAGE_GENERATION_MCP_TRANSFER_LEASE_S: Crashed-handler reclaim window in seconds for an in-flight reservation.; IMAGE_GENERATION_MCP_TRANSFER_MAX_UPLOAD_BYTES: Maximum size in bytes of a single upload..

This package has launch arguments in its registry record. Use the maintainer’s configuration for those arguments rather than launching it with only the package name.

Before connecting

Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.

Project and source

View the publisher’s registry entry · Project repository · Project website. This profile uses version 1.12.1 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.

Browse related ai & ml services MCP servers for tools that cover the same kind of work.