io.github.pvliesdonk/image-generation-mcp
This server offers image generation and management across multiple AI providers: OpenAI (DALL-E), Google Gemini, Stable Diffusion WebUI, and a test placeholder. Key capabilities include:
Generate: create images from prompts, with automatic provider routing (
auto) based on content type.Monitor: poll
check_generation_statusfor long-running tasks.View & Transform: display images with on-demand resize, crop, format conversion via
image://URIs.Browse: explore gallery with pagination, thumbnails, and filtering by origin.
Edit: interactive crop, rotate, flip, saving as new images.
Input Images: upload or fetch images for image-to-image generation (e.g., background replacement).
Discovery: list providers, models, supported aspects, styles, and deprecation warnings.
Style Library: save/apply style presets.
Resources: list and read MCP resources.
Server Info: check version details.
Cost Confirm: require user approval for paid providers.
Generates images using Google Gemini models like gemini-2.5-flash-image and gemini-3.x previews.
Generates images using OpenAI models such as gpt-image-1.5, gpt-image-1, and dall-e-3.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@io.github.pvliesdonk/image-generation-mcp Generate a sci-fi cityscape at night, 16:9."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Image Generation MCP
Multi-provider image generation MCP server built on FastMCP. Generate images from Claude Desktop, Claude Code, or any MCP client using OpenAI, Google Gemini, Stable Diffusion (SD WebUI), or a zero-cost placeholder provider.
Documentation | Config wizard | PyPI | Docker
Features
Multi-provider: OpenAI (
gpt-image-2,gpt-image-1.5,dall-e-3), Google Gemini (gemini-3.1-flash-image,gemini-3-pro-image,gemini-3.1-flash-lite-image), SD WebUI (Stable Diffusion / Forge / reForge), and a zero-cost placeholder for testing.Per-model style metadata: every model carries a
style_profile(strengths, prompt grammar, lifecycle);list_providersincludes a top-levelwarningsarray for deprecated models. See Model Catalog.Keyword-based auto-selection:
provider="auto"routes by prompt content (text/logo → OpenAI, photoreal/anime → SD WebUI, draft → placeholder).CDN-style image transforms:
image://{id}/view?format=webp&width=512&crop_x=...resizes / re-encodes / crops on demand without re-generating.Hybrid background tasks: long-running SD generations run with
task=True(poll for status); short OpenAI calls stream progress in the foreground.MCP Apps gallery + viewer: interactive UI surfaces (browse generated images, edit / crop / rotate) for clients that support
app:resources.Production deployment: Docker (multi-arch),
.deb/.rpmwith hardened systemd, OIDC + bearer auth, persistent EventStore for HTTP session resumability.
Related MCP server: gemini-nano-banana-mcp
What you can do with it
With this server mounted in an MCP client, you can ask:
"Generate a coffee mug product photo on a worn oak table, 16:9, no text." Routes to
gpt-image-1.5for typography-aware photorealism."Create three concept-art variations of a cyberpunk alley at dusk." Composes
generate_imagewithprovider="sd_webui"and a stylised checkpoint likedreamshaperXL."Crop this image to a 1:1 square centred on the subject and resize to 512px." Uses
image://{id}/view?width=512&height=512&crop_x=...resource transforms."Show me my recent generations." Browses the gallery via the
image://listresource and the MCP Apps gallery viewer."Save this style as 'cyberpunk-night' so I can apply it to future requests." Uses the style library, whose markdown briefs the LLM interprets per-provider.
"Replace the background of my last photo with a sunset sky." Uses
transform_imagewith the galleryimage_idas a reference (image-to-image via Gemini).
Installation
From PyPI
pip install image-generation-mcpIf you add optional extras via the PROJECT-EXTRAS-START / PROJECT-EXTRAS-END sentinels in pyproject.toml, document them below:
Extra | Includes | Use when |
|
| Background-task support ( |
|
| Enables the OpenAI provider. |
|
| Enables the Gemini provider. |
|
| Everything except SD WebUI (which is HTTP-only, no extra needed). |
Example: pip install image-generation-mcp[all].
From source
git clone https://github.com/pvliesdonk/image-generation-mcp.git
cd image-generation-mcp
uv sync --all-extras --all-groupsDocker
docker pull ghcr.io/pvliesdonk/image-generation-mcp:latestTo run the newest merged code instead of the newest release, use the rolling edge tag. It is rebuilt on every merge to main and carries no version identity. See Image tags for the full tag list.
docker pull ghcr.io/pvliesdonk/image-generation-mcp:edgeA compose.yml ships at the repo root as a starting point. Copy .env.example to .env, edit, and docker compose up -d.
To attach a remote Python debugger (development only; the protocol is unauthenticated), see Remote debugging.
Linux packages (.deb / .rpm)
Download .deb or .rpm packages from the GitHub Releases page. Both install a hardened systemd unit; env configuration is sourced from /etc/image-generation-mcp/env (copy from the shipped /etc/image-generation-mcp/env.example).
Claude Desktop (.mcpb bundle)
Download the .mcpb bundle from the GitHub Releases page and double-click to install, or run:
mcpb install image-generation-mcp-<version>.mcpbClaude Desktop prompts for required env vars via a GUI wizard, with no manual JSON editing needed.
For manual Claude Desktop configuration and setup options, see Claude Desktop deployment.
Release channels
Artifacts ship on three channels. Each row lists exactly what that channel publishes.
Channel | Version identity | Artifacts |
| None; the commit is the identity | Docker image |
Pre-release |
| PyPI (as the pre-release |
Stable |
| Everything: PyPI, Docker (version tag plus ordering-aware |
Pre-releases reach PyPI so that a candidate's .mcpb bundle installs: the bundle points at PyPI rather than carrying the code. Ordinary installers never see them, because a PEP 440 resolver skips pre-releases unless the requirement pins one or you pass --pre. Ask for a candidate by name with pip install image-generation-mcp==X.Y.ZrcN. PyPI spells it in the PEP 440 canonical form, while tags use SemVer. Rolling pointers are ordering-aware, so a patch release cut from an old release/X.Y branch never moves latest-style tags back to older content, and a candidate for an already-released version never moves rc. See Release process for the full model.
Quick start
image-generation-mcp serve # stdio transport
image-generation-mcp serve --transport http --port 8000 # streamable HTTPFor library usage (embedding the domain logic without the MCP transport), import from the image_generation_mcp package directly. See the project's domain modules under src/image_generation_mcp/ for entry points.
Server info
The server registers a built-in get_server_info tool (via fastmcp_pvl_core.register_server_info_tool) so operators can confirm the deployed version with a single MCP call. The default response carries server_name, server_version, and core_version. Servers that talk to a remote upstream wire upstream version reporting inside the DOMAIN-UPSTREAM-START / DOMAIN-UPSTREAM-END sentinel in src/image_generation_mcp/server.py; see CLAUDE.md for the wiring pattern.
Configuration
Core environment variables shared across all fastmcp-pvl-core-based services:
Variable | Default | Description |
|
| Persistent-state backend URL shared by every pvl-core subsystem that needs state. |
|
| Log level for FastMCP internals and app loggers (DEBUG / INFO / WARNING / ERROR / CRITICAL). The -v CLI flag overrides to DEBUG. |
|
| Set false for plain or structured JSON log output. |
Domain-specific variables go below under Domain configuration.
Authentication
Callers authenticate via a bearer token or OIDC (mutually exclusive). See the Authentication guide for setup, mapped multi-subject tokens, OIDC, and troubleshooting.
Post-scaffold checklist
After copier copy and gh repo create --push:
Fill in the DOMAIN blocks (every section marked with a
DOMAINsentinel comment) in this README and inCLAUDE.md. TheGENERATED-ENV-TABLE-*regions are not DOMAIN blocks; the config generator owns them and rewrites them on every run.Configure GitHub secrets (see below).
Install dev + docs tooling:
uv sync --all-extras --all-groups.Install pre-commit hooks:
uv run pre-commit install.Run the gate locally:
uv run pytest -x -q && uv run ruff check --fix . && uv run ruff format . && uv run mypy src/ tests/.Push the first commit. CI should be green.
GitHub secrets
CI workflows reference three repository secrets. Configure them via Settings → Secrets and variables → Actions or with gh secret set:
Secret | Used by | How to generate |
|
| Fine-grained PAT at https://github.com/settings/personal-access-tokens/new with |
|
| https://codecov.io: sign in with GitHub and add the repo. The upload token is on its settings page. |
|
| Run |
gh secret set RELEASE_TOKEN
gh secret set CODECOV_TOKEN
gh secret set CLAUDE_CODE_OAUTH_TOKENDependency updates are handled by Renovate (
renovate.yml), which reusesRELEASE_TOKEN. It maintainsuv.lockand auto-merges patch/minor bumps once theCI Successcheck is green;bootstrap.ymlenables auto-merge and applies the repository rulesets (.github/rulesets/) on first push. See Repository Protection for the per-branch posture and bypass model. GitHub Actions are updated in the copier template and arrive viacopier update, not per-repo.
GITHUB_TOKEN is auto-provided; no action needed.
Local development
The PR gate (matches CI):
uv run pytest -x -q # tests
uv run ruff check --fix . && uv run ruff format . # lint + format
uv run mypy src/ tests/ # type-checkPre-commit runs a subset of the gate on each commit; see .pre-commit-config.yaml for details, or CLAUDE.md for the full Hard PR Acceptance Gates.
Troubleshooting
Moving a scaffolded project
uv sync creates .venv/bin/* scripts with absolute shebangs pointing at the venv Python. If you move the repo after scaffolding (mv /old/path /new/path), uv run pytest fails with ModuleNotFoundError: No module named 'fastmcp' because the stale shebang resolves to a different interpreter than the venv's site-packages.
Fix:
rm -rf .venv
uv sync --all-extras --all-groupsuv run python -m pytest also works as a one-shot workaround (bypasses the stale entry-script shim).
uv.lock refresh after copier update
When copier update introduces new dependencies (such as a new extra added to pyproject.toml.jinja), the CI install step runs uv sync --locked, which fails against a stale lockfile. Run uv lock locally and commit the refreshed uv.lock alongside accepting the copier-update PR.
CI installs with --locked (and the review workflow with --frozen) so no job ever rewrites uv.lock in its own workspace: a job that re-locks hides the drift it just repaired, and a dirty workspace breaks any later git checkout in the same job. Lockfile drift then shows up as a red install step with a clear message, not as a silent mutation.
Links
Domain configuration
Domain environment variables use the IMAGE_GENERATION_MCP_ prefix:
Variable | Default | Required | Description |
| (none) | No | Deprecated alias for IMAGE_GENERATION_MCP_SD_WEBUI_HOST; logs a warning when used. |
| (none) | No | Deprecated alias for IMAGE_GENERATION_MCP_SD_WEBUI_MODEL; logs a warning when used. |
|
| No | When true, write-tagged tools (image generation, transforms, uploads) are hidden from clients. Set false to enable them. |
|
| No | Directory where generated images are saved. Created automatically on first use. |
| (none) | No | OpenAI API key. Enables the OpenAI provider (gpt-image-2, gpt-image-1.5, dall-e-3) when set. |
| (none) | No | 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. |
| (none) | No | SD WebUI base URL (such as http://localhost:7860). Enables the SD WebUI provider when set. Compatible with AUTOMATIC1111, Forge, reForge, and Forge-neo. |
| (none) | No | 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. |
|
| No | Provider used when no keyword triggers auto-selection: auto, openai, gemini, sd_webui, or placeholder. auto picks the first configured provider. |
|
| No | Maximum number of transformed image results (resize, crop, convert) kept in memory. Set 0 to disable caching. |
|
| No | 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). |
|
| No | Directory for style preset files (Markdown with YAML front matter). Created automatically if it does not exist. |
|
| No | Allow reading input images from local filesystem paths. Off by default: only URLs and uploads are accepted. |
|
| No | Maximum accepted input image size in bytes. |
|
| No | HTTP timeout in seconds when fetching remote image URLs (fetch_image and URL inputs). |
|
| No | Link lifetime in seconds when the caller requests no explicit TTL. |
|
| No | Ceiling in seconds a caller-requested link TTL is clamped to. |
|
| No | Post-success grace window in seconds: a served token's TTL shrinks to this so a stalled transfer can retry within it. |
|
| No | Crashed-handler reclaim window in seconds for an in-flight reservation. |
|
| No | Maximum size in bytes of a single upload. |
The create_download_link / create_upload_link tools and the /transfer/{token} route register only on an HTTP or SSE transport with BASE_URL set, and store link tokens in IMAGE_GENERATION_MCP_KV_STORE_URL; the IMAGE_GENERATION_MCP_TRANSFER_* knobs above tune link lifetime and upload limits. Security: IMAGE_GENERATION_MCP_ALLOW_LOCAL_FILE_INPUT grants callers server-filesystem read access via reference-image paths; enable it only for trusted callers or local single-user deployments.
Domain-config fields are composed inside src/image_generation_mcp/config.py between the CONFIG-FIELDS-START / CONFIG-FIELDS-END sentinels; env reads go through fastmcp_pvl_core.env(_ENV_PREFIX, "SUFFIX", default) so naming stays consistent, and field invariants go in __post_init__ between the CONFIG-VALIDATE-START / CONFIG-VALIDATE-END sentinels. Each field's metadata help and tags generate the table above directly, so keep them accurate and complete.
Key design decisions
Multi-provider with capability discovery, not feature flags. Each provider's
discover_capabilities()reports its actual supported aspect ratios / qualities / formats / negative-prompt support at startup; routing logic asks the capability surface, not a hard-coded enum. New providers slot in by satisfying the protocol, with no router edits needed. (Seedocs/decisions/0001-…,0002-…,0007-….)Per-model
style_profilemetadata, surfaced vialist_providers. Closed-list providers (OpenAI, Gemini, placeholder) use exact-key lookup; SD WebUI uses a regex-ordered pattern table. Profiles include lifecycle flags (current/legacy/deprecated) and feed an auto-built top-levelwarningsarray. (Seedocs/decisions/0009-….)Hybrid background tasks. Short calls (OpenAI ~5 s) stream progress in-line; long calls (SD WebUI 30-180 s) run as background tasks with
check_generation_statuspolling; clients pick the mode viatask=True. (Seedocs/decisions/0005-….)Image asset model: content-addressed registry + sidecar JSON metadata + on-demand transforms. Generated images keep their full-resolution original;
image://{id}/view?format=webp&width=512&crop_x=…resources do format conversion / resize / crop on demand without re-generating. Transforms are cached. (Seedocs/decisions/0006-….)Style library. User-saved markdown briefs (with YAML frontmatter for tags / aspect ratio / quality) that the LLM interprets per-provider, not copy-pasted verbatim. Distinct from per-model
style_profile: style library is the brief;style_profiledescribes the model. (Seedocs/decisions/0008-…and0009-…for disambiguation.)Composes
fastmcp_pvl_core.ServerConfig, never inherits. Domain config goes betweenCONFIG-FIELDS-START/CONFIG-FIELDS-ENDsentinels; env reads route throughfastmcp_pvl_core.env(...)to keep prefix naming consistent.
Available Tools
10 toolsbrowse_galleryBrowse GalleryARead-only
Browse all generated images in an interactive visual gallery.
Opens a gallery view showing thumbnail previews of images in the
scratch directory, filtered by origin (generated images by default).
For non-UI clients the response is a JSON object with total,
page, page_size, origin, and items. Each completed item includes
image_id, prompt, provider, dimensions,
created_at, thumbnail_b64 (128 px WebP, base64-encoded),
content_type, and origin. Pending/generating items include
status, progress, and progress_message instead of a
thumbnail.
Use browse_gallery to see all images; use
show_image(uri="image://{image_id}/view") to view one
image at full resolution.
Inputs: origin.
check_generation_statusCheck Generation StatusARead-onlyIdempotent
Check whether a background image generation has finished.
Call this after generate_image to wait for completion.
Returns a short JSON status — no image data, no heavy UI.
"completed"→ callshow_image(uri=original_uri)to display the finished image."generating"→ wait and check again."failed"→ report the error to the user.
Inputs: image_id (required). Returns: result
edit_imageEdit ImageARead-only
Open an image for interactive editing (crop, rotate, flip).
The user edits in the viewer UI and saves as a new image. Always edits the original image — resource template transforms are ephemeral and LLM-facing; editor transforms are persistent and user-facing.
Inputs: image_id (required).
gallery_full_imageGallery Full ImageARead-only
Return full-resolution image data for the gallery lightbox.
App-only helper called by the gallery lightbox to load a single image at full (or near-full) resolution. Images larger than 1 MB are downscaled to 1024 px wide WebP before encoding.
Inputs: image_id (required). Returns: result
gallery_pageGallery PageARead-only
Return a page of image thumbnails for the gallery UI.
App-only helper called by the gallery UI to load additional pages when the user paginates. Not intended for direct model invocation.
Inputs: page, origin, page_size. Returns: result
get_server_infoServer InfoARead-only
Report wrapper and upstream version info for image-generation-mcp. Returns server_name, server_version, core_version (fastmcp-pvl-core), and (when configured) an upstream version block. Useful for verifying a deployment matches the expected build.
Inputs: no named parameters. Returns: object
list_providersList ProvidersARead-only
List available image generation providers, models, and capabilities.
Returns provider names, available models, and capability details.
Each model includes a prompt_style field: use "clip" for
comma-separated CLIP tags (SD 1.5/SDXL) or "natural_language"
for descriptive sentences (Flux, OpenAI). Each call includes a
refreshed_at timestamp. Pass force_refresh=true if
providers may have changed since the last check.
Also available as the info://providers resource for clients
that support MCP resources.
Inputs: force_refresh. Returns: result
list_resourcesList ResourcesARead-only
List all available resources and resource templates.
Returns JSON with resource metadata. Static resources have a 'uri' field, while templates have a 'uri_template' field with placeholders like {name}.
Inputs: no named parameters. Returns: result
read_resourceRead ResourceARead-only
Read a resource by its URI.
For static resources, provide the exact URI. For templated resources, provide the URI with template parameters filled in.
Returns the resource content as a string. Binary content is base64-encoded.
Inputs: uri (required). Returns: result
show_imageShow ImageARead-only
Display a completed image with optional on-demand transforms.
Only call this for completed images — use
check_generation_status to poll, then call this once when
status is "completed".
Accepts a full image:// resource URI (e.g.
image://abc123/view or
image://abc123/view?format=webp&width=512). Transforms are
encoded in the URI query string — no separate parameters needed.
Read the image://list resource to browse available image IDs.
Inputs: uri (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Most tools have clearly distinct purposes (polling, displaying, browsing, editing, listing providers). However, gallery_page and gallery_full_image are app-only helpers that overlap conceptually with browse_gallery and show_image, creating mild ambiguity for an agent.
The majority follow a verb_noun pattern (check_generation_status, show_image, browse_gallery, edit_image, list_providers, get_server_info, list_resources, read_resource), but gallery_page and gallery_full_image break the pattern by starting with a noun. This makes the naming convention somewhat inconsistent.
With 10 tools, the count falls within the ideal 3–15 range and feels well-scoped for an image generation server, assuming the missing generate_image tool existed. The number itself is appropriate.
The server is named image-generation-mcp, yet there is no generate_image tool among the listed functions; check_generation_status references it but it is absent. This is a severe gap—the core generation capability is missing, leaving only supporting utilities and viewing/browsing tools.
Maintenance
Related MCP Connectors
MCP server for Qwen Image 3 AI image generation
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models. Up to 4 images per call, SVG vectorization, background removal, upscaling and image-to-video. Remote MCP with OAuth, no API keys.
Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceMCP server for generating, editing, and processing images via multiple providers including Kilo, OpenRouter, OpenAI, and Gemini, with local tools for background removal, resizing, and cropping.16 npm3MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that enables Claude Code to generate images using Google's Gemini image generation models.MIT
- AlicenseAqualityDmaintenanceA security-first MCP server that generates images via OpenAI's image model (gpt-image-2) and returns them as MCP image content, usable from Claude Code, Claude Desktop, and other stdio MCP clients.1MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for generating and editing images using OpenRouter API, with support for multiple models and dynamic model discovery. Runs in Docker and integrates with Claude Desktop via stdio transport.MIT