Image Generation MCP Server

Image Generation MCP

[CI] [codecov] [PyPI] [Python] [License] [Docker] [Docs] [llms.txt] [Template]

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_providers includes a top-level warnings array 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/.rpm with hardened systemd, OIDC + bearer auth, persistent EventStore for HTTP session resumability.

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-1.5 for typography-aware photorealism.
• "Create three concept-art variations of a cyberpunk alley at dusk." Composes generate_image with provider="sd_webui" and a stylised checkpoint like dreamshaperXL.
• "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://list resource 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_image with the gallery image_id as a reference (image-to-image via Gemini).

Installation

From PyPI

pip install image-generation-mcp

If you add optional extras via the PROJECT-EXTRAS-START / PROJECT-EXTRAS-END sentinels in pyproject.toml, document them below:

Example: pip install image-generation-mcp[all].

From source

git clone https://github.com/pvliesdonk/image-generation-mcp.gitcd image-generation-mcpuv sync --all-extras --all-groups

Docker

docker pull ghcr.io/pvliesdonk/image-generation-mcp:latest

To 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:edge

A 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>.mcpb

Claude 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.

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 transportimage-generation-mcp serve --transport http --port 8000   # streamable HTTP

For 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:

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:

1. Fill in the DOMAIN blocks (every section marked with a DOMAIN sentinel comment) in this README and in CLAUDE.md. The GENERATED-ENV-TABLE-* regions are not DOMAIN blocks; the config generator owns them and rewrites them on every run.
2. Configure GitHub secrets (see below).
3. Install dev + docs tooling: uv sync --all-extras --all-groups.
4. Install pre-commit hooks: uv run pre-commit install.
5. Run the gate locally: uv run pytest -x -q && uv run ruff check --fix . && uv run ruff format . && uv run mypy src/ tests/.
6. 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:

gh secret set RELEASE_TOKENgh secret set CODECOV_TOKENgh secret set CLAUDE_CODE_OAUTH_TOKEN

Dependency updates are handled by Renovate (renovate.yml), which reuses RELEASE_TOKEN. It maintains uv.lock and auto-merges patch/minor bumps once the CI Success check is green; bootstrap.yml enables 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 via copier update, not per-repo.

GITHUB_TOKEN is auto-provided; no action needed.

Local development

The PR gate (matches CI):

uv run pytest -x -q                                  # testsuv run ruff check --fix . && uv run ruff format .    # lint + formatuv run mypy src/ tests/                              # type-check

Pre-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 .venvuv sync --all-extras --all-groups

uv 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

• Documentation
• llms.txt
• FastMCP
• fastmcp-pvl-core

Domain configuration

Domain environment variables use the IMAGE_GENERATION_MCP_ prefix:

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. (See docs/decisions/0001-…, 0002-…, 0007-….)
• Per-model style_profile metadata, surfaced via list_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-level warnings array. (See docs/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_status polling; clients pick the mode via task=True. (See docs/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. (See docs/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_profile describes the model. (See docs/decisions/0008-… and 0009-… for disambiguation.)
• Composes fastmcp_pvl_core.ServerConfig, never inherits. Domain config goes between CONFIG-FIELDS-START / CONFIG-FIELDS-END sentinels; env reads route through fastmcp_pvl_core.env(...) to keep prefix naming consistent.