图像生成 MCP配置与使用教程

{
  "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"
  }
}