Ark Seed Multimodal MCP Server
by byteplus-sa
README.md
# Ark Seed Multimodal MCP Server
A Python [Model Context Protocol](https://modelcontextprotocol.io) server
built on [FastMCP](https://gofastmcp.com) that exposes BytePlus multimodal
generation through a typed, safe tool surface.
## Documentation
Read the [Ark MCP documentation](https://byteplus-sa.github.io/ark-mcp/) for
installation, client integrations, worked examples, and generated input/output
schemas for every catalog tool.
The source guides cover [installation](docs/setup/install.md),
[client integrations](docs/integrations/index.md),
[your first tool call](docs/setup/first-run.md), and
[choosing a tool](docs/capabilities.md). See
[site maintenance](docs/site-maintenance.md) for local development and deployment.
> **Upgrading from 0.1.x?** 0.2.0 consolidates the tool surface and removes
> the old per-model, per-variation and per-operation tools with no
> compatibility layer. See the [migration guide](docs/migration-0.2.md).
## Releases
Version bumps and changelogs are reviewed in automated release PRs. Merging
one publishes a tested GitHub Release with Python distributions and versioned
GHCR images. `latest` follows releases; `edge` follows passing main builds.
See [release policy and installation](docs/releases.md) and the
[changelog](docs/changelog.md). PyPI publication is not configured.
## What It Does
The server provides a conditional MCP tool surface across several BytePlus
products plus artifact access and an optional media upload helper:
| Product | Tools | Description |
|---|---|---|
| **Seed Audio** | `seed_audio_generate` | Background-task full-scene audio generation through Seed Speech; one clip or 1-5 parallel variations |
| **Seedream** | `seedream_generate_image` | One background-task image tool through ModelArk: [Seedream 5.5](https://byteplus-sa.github.io/ark-mcp/tool-reference/seedream-generate-image/#seedream-5-5) by default, generation/reference and point/box editing, native transparent PNGs, auto backgrounds, standard-only optimization, validated 1K/1.5K/2K or custom sizes, hashed safety IDs, provider image metadata, 1-10 variations and dry runs. Pro retains transparency-preserving edits; batches are Lite/4.x only. Layer decomposition/OCR are not exposed |
| **Seedance** | `seedance_create_task` | One background-task video tool for every configured Seedance model (regular 2.5 and Flash bound by default, 2.0 configurable): regular 2.5 supports `resolution="4k"`; Flash supports 480p/720p and no Draft. Pick the model from `ark_list_models(kind='video')`, create 1-5 variations, or use `dry_run` for a free request and static cost preview; poll with the shared generation task tools |
| **Hyper3D / Hitem3d** | `hyper3d_create_task`, `hitem3d_create_task` | Background-task 3D submission through ModelArk; poll with the shared generation task tools (gated by `BYTEPLUS_MODELARK_3D_ENABLED`, disabled by default) |
| **Generation tasks** | `gen_task_get`, `gen_task_list`, `gen_task_cancel_or_delete` | One lifecycle for every ModelArk generation task (Seedance video and 3D): batched status checks (1-50 IDs) with derived queue timing and optionally background output persistence, cursor-paged listing of your own tasks, and guarded cancel/delete |
| **OmniHuman 2.0** | `omnihuman_create_task`, `omnihuman_get_task`, `omnihuman_cancel_task` | Image + audio to talking-avatar video through BytePlus Vision AI; background-task submission, polling with durable video persistence, and queue cancel (gated by `BYTEPLUS_OMNIHUMAN_ENABLED` and `BYTEPLUS_CV_API_KEY`, disabled by default) |
| **Seed 2.1 Understanding** | `seed_understand` | Background-task video/image understanding and reasoning through ModelArk Chat Completions; always thinks, returns only the final answer, enforces JSON Schemas, and can save the answer to a local file |
| **Seed Audio Understanding** | `seed_audio_understand` | Background-task audio understanding (transcription, translation, speaker/emotion analysis, summaries, Q&A) through ModelArk Chat Completions `input_audio`; model set by `SEED_AUDIO_UNDERSTANDING_MODEL` (default `seed-2-0-lite-260428`), same thinking, JSON Schema, and `save_to` controls as `seed_understand` |
| **Speech-to-Text** | `speech_to_text` | Background-task audio transcription through Seed Speech ASR (HTTP) |
| **VOD AI MediaKit** | `vod_enhance_video` | Submit asynchronous AI video upscaling/enhancement with fast, standard, or professional tiers and target resolutions from 240p to 8K |
| **VOD AI MediaKit Transcode** | `vod_transcode_video` | Submit async video transcoding (codec, container, resolution, bitrate, frame rate) |
| **VOD AI MediaKit Subtitles** | `vod_add_subtitles`, `vod_remove_subtitles` | Burn SRT/VTT/ASS or inline cues into video, or remove hardcoded subtitles and recognized on-screen text |
| **VOD Audio Separation** | `vod_separate_audio` | Submit voice + background (or voice + music + sfx) audio separation via the VOD AI MediaKit (`separate-voice`) |
| **VOD task polling** | `vod_get_task` | One poller for every `vod_*` task: pass the `task_id` and `operation` the create tool returned; normalized status and outputs with optionally background durable persistence |
| **Private Asset Library** | `ark_asset_group_ensure`, `ark_asset_group_list`, `ark_asset_create`, `ark_asset_list`, `ark_asset_update`, `ark_asset_verification_start`, `ark_asset_verification_result`, `ark_asset_delete` | Manage Seedance Advanced Creation Rights assets (virtual portraits, verified real people) with BytePlus AK/SK; reference them as `asset://<id>` in Seedance |
| **Artifacts** | `seed_media_get_artifact`, `seed_media_export_artifact`, `seed_media_persist_url` | Retrieve persisted media inline by artifact ID, locate/copy it to a local path without Base64 round-trips, or durably persist a provider URL whose storage failed |
| **Object storage** (optional) | `media_upload`, `media_presign` | Background-task upload of 1-50 Base64 or local-file media items to TOS or S3 with per-item results; foreground URL renewal for 1-100 object keys without re-uploading |
| **Background jobs** | `ark_job_capabilities`, `ark_job_submit`, `ark_job_get`, `ark_job_cancel` | Ordinary MCP tools and the default way to submit and manage long-running work; no task-augmented execution required |
Key features:
- **Model discovery** - `ark_list_models` reports configured models and the
tools serving them. Understanding modalities describe the named tool:
`seed_understand` takes images/videos; `seed_audio_understand` takes audio
only, with a server-configured model.
- **Cached account pricing** - with AK/SK configured, discovery includes fresh
catalog prices without making a provider call. Image and understanding cost
estimates use recognized catalog rates, with built-in fallbacks.
- **Large audio inputs** - audio understanding supports Files API delivery for
oversized URLs and video soundtracks, with temporary-upload cleanup.
- **Organization self-hosting** - the [Compose kit](docs/self-hosting.md)
packages TLS ingress, [shared MCP key authentication](docs/self-hosting.md#shared-mcp-key),
internal Redis, and spending controls.
The [BytePlus Terraform starter](docs/byteplus-terraform.md) provisions one ECS
host with retained storage. Its [guided deployment CLI](docs/byteplus-terraform.md#guided-deployment-cli)
adds preflight, reviewed approvals, encrypted configuration, resumable
activation, nonbillable verification and application-only updates.
[Secret Manager integration](docs/secret-manager.md) adds pinned-version
provider-key reads and approved, resumable MCP-only configuration sync.
- **Durable artifacts** — generated media is persisted locally so MCP
resources remain usable after known provider URL lifetimes (2h audio, 24h
ModelArk image/video); VOD MediaKit persistence is best-effort and capped at
200 MiB, and completed enhancement URLs have a confirmed 24-hour lifetime
- **Billed outputs are never dropped** — downloads are retried; if storage
still fails, the result returns the provider URL (or inline bytes) with a
`persistence_error` instead of an error, recoverable with
`seed_media_persist_url`
- **Local output paths** — on stdio, `output_path` / `output_dir` / `save_to`
write results straight into the client's MCP roots (or `OUTPUT_ROOTS`) with
symlink-safe, no-silent-overwrite writes
- **Parallel variations** — generate N independent variations in a single
call, partial failures captured per variation with the failure phase
- **Seedream provenance and byte checks** — single calls and variations record
request IDs, submitted seeds, final-prompt hashes and allowlisted options.
Advisory PNG/JPEG inspection measures dimensions, format and actual alpha
separately from provider reports; it preserves billed output without rerolls.
Base64 delivery requires persistence. See the bounded
[review/edit workflow](docs/integration-guide.md#seedream-review-and-edit)
- **Per-variation seeds** — with `variations > 1`, Seedream `seed` is the base
seed and variation *i* uses `seed + i` (wrapped); identical pixels are not guaranteed
- **Typed inputs** — Pydantic models validate all inputs before spending
quota; unsupported combinations are rejected at the MCP layer
- **Timeout-safe long operations** — generation, transcription, large upload,
and provider task-submission tools run in the background through the ordinary
`ark_job_*` tools by default, or native MCP task augmentation on clients that
support it; completed-output retrieval also supports background execution
when persistence may require a large download
- **Model capability registry** — logical model families map to
operator-configured model IDs; validates resolutions, formats, and
batch support per model
- **Security** — DNS-pinned SSRF-safe downloads, tenant/principal ownership,
shared-team API key auth for network HTTP, Host/Origin protection, and body limits
- **Runtime controls** — shared provider/principal concurrency, daily budget
reservations, safe retries, task ownership, readiness with optional provider
health checks, per-IP HTTP rate limiting, metrics, and tracing
- **Offline regression coverage** — unit, contract, integration, HTTP security,
E2E, and MCP conformance tests, plus documentation build/link checks
## Supported Input Modalities
All input media is validated through an SSRF-safe URL policy and size-checked
Base64 before reaching the provider. The table below shows what each tool
accepts as reference input:
| Tool | Modality | URL | Base64 | Speaker ID | Roles | Max | Constraints |
|---|---|:---:|:---:|:---:|---|:---:|---|
| `seedream_generate_image` | Image | ✓ | ✓ | — | reference | 10 5.5·PRO / 14 LITE·4X | — |
| `seedance_create_task` (2.0 models) | Image | ✓ | ✓ | — | `first_frame` · `last_frame` · `reference_image` | 9 | — |
| `seedance_create_task` (2.0 models) | Video | ✓ | — | — | `reference_video` | 3 | URL only |
| `seedance_create_task` (2.0 models) | Audio | ✓ | ✓ | — | `reference_audio` | 3 | Not sole input |
| `seedance_create_task` (2.5 models) | Image | ✓ | ✓ | — | `first_frame` · `last_frame` · `reference_image` | 30 | — |
| `seedance_create_task` (2.5 models) | Video | ✓ | — | — | `reference_video` | 10 | URL only |
| `seedance_create_task` (2.5 models) | Audio | ✓ | ✓ | — | `reference_audio` | 10 | May be the sole input |
| `seed_audio_generate` | Audio | ✓ | ✓ | ✓ | — | 3 | Exclusive w/ image |
| `seed_audio_generate` | Image | ✓ | ✓ | — | — | 1 | Exclusive w/ audio |
> Variations are a field on the base tools (`variations` on
> `seedream_generate_image`, `seed_audio_generate`, and
> `seedance_create_task`), so they accept the same input modalities and limits
> as a single call.
> [!NOTE]
> **Video references must be pre-hosted.** `seedance_create_task` accepts
> video references as a **public HTTPS URL only** — there is no inline Base64
> option. Run `media_upload` in the background through `ark_job_submit` (or MCP
> task metadata on a task-capable client) to upload Base64 or a local file path
> (stdio only) to object storage (TOS or S3). Retrieve its presigned HTTPS GET
> URL from the terminal `ark_job_get.result` (or `tasks/get` response), then run
> `seedance_create_task` through the same supported background path.
> Alternatively, host the video on
> your own accessible HTTPS endpoint. The URL must resolve to
> a public IP (private/loopback/link-local addresses are rejected by the SSRF
> policy). `media_upload` requires TOS or S3 credentials; see [Configuration](docs/configuration.md).
## Architecture
The server uses dedicated provider gateways behind one normalized domain layer, a
lifespan-owned runtime for concurrency/budget/ownership, and a durable
artifact store. See [docs/architecture.md](docs/architecture.md) for the full
overview.
**Components**
```mermaid
flowchart TB
subgraph Client["MCP clients"]
CD[Claude Desktop]
CX[Codex CLI]
OC[OpenCode]
TR[TRAE IDE]
end
subgraph Server["Ark MCP Server (FastMCP)"]
Tools["Tools<br/>Seedream · Seedance · Seed Audio · VOD AI MediaKit · Artifacts · Object storage"]
Domain["Domain layer<br/>models · capability registry · errors"]
Runtime["Runtime services<br/>concurrency · budget · ownership · retry"]
Store["Artifact store<br/>filesystem + .meta.json"]
Sec["Security: shared-key auth, SSRF-safe downloads, body limits"]
Obs["Observability<br/>structured logs · metrics · traces"]
end
subgraph Providers["BytePlus"]
MA["ModelArk gateway<br/>Bearer auth"]
SS["Seed Speech gateway<br/>X-Api-Key"]
VOD["VOD AI MediaKit gateway<br/>Bearer auth"]
end
Client <-->|"stdio / HTTP"| Tools
Tools --> Domain
Tools --> Runtime
Tools --> Store
Domain --> Providers
Sec -. guards .-> Tools
Obs -. observes .-> Tools
```
**Layered view**
```mermaid
flowchart LR
L1["Transport<br/>stdio · Streamable HTTP"] --> L2["Server<br/>FastMCP tools · resources · routes"]
L2 --> L3["Domain<br/>typed models · capability registry"]
L3 --> L4["Provider gateways<br/>ModelArk · Seed Speech"]
L4 --> L5["BytePlus<br/>Seedream · Seedance · Seed Audio"]
L2 -.-> X["Cross-cutting<br/>security · runtime · observability · artifacts"]
```
**Request sequence (a billable generate call)**
```mermaid
sequenceDiagram
participant C as MCP Client
participant T as Tool handler
participant R as Runtime services
participant P as Provider gateway
participant B as BytePlus
participant A as Artifact store
C->>T: call tool (Pydantic inputs)
T->>T: validate inputs + capability registry
T->>R: reserve budget + acquire provider/principal semaphores
R-->>T: budget reservation
T->>P: call_with_retry(provider request)
P->>B: HTTPS (Bearer / X-Api-Key)
B-->>P: media URL (2h audio / 24h image·video)
P-->>T: provider result
T->>A: persist artifact (durable copy)
A-->>T: seed-media://artifacts/{id}
T->>R: commit budget
T-->>C: ArtifactRef (stable resource URI)
```
## Quick Start
For agent-guided installation or updates, use the
[`ark-mcp-setup` skill](.agents/skills/ark-mcp-setup/SKILL.md). It detects the
target client (including TRAE, Claude, and Codex), defaults to global MCP
registration, prefers the latest stable release, and opens a private local
credential file for user entry. If no stable release exists, it asks before
using a default-branch commit.
1. Open [guided setup](docs/setup/install.md). A coding agent with terminal
and file access can prepare the reviewed installation and client entry.
2. Enter the provider keys you need in the private local editor, not in chat.
3. Enable `ark-seed` in your client and ask:
```text
Check Ark with ark_list_models and ark_job_capabilities.
Tell me which services and tools are available. Do not generate,
understand, transcribe, upload, or submit jobs.
```
The client starts the local server automatically; do not run a separate
terminal server after setup. If your team already runs Ark,
[connect to its endpoint](docs/setup/shared-server.md) without installing
anything locally. [Manual installation](docs/setup/manual-install.md) remains
available for users without a setup-capable agent.
## Agent Skill
Install the optional [ark-mcp usage skill](docs/setup/agent-skill.md) to teach
your agent model discovery, background jobs, progress checks and artifact
handling. Ask your agent to use the Skills CLI, or run:
```bash
npx skills add byteplus-sa/ark-mcp --skill ark-mcp -g
```
Requires Node.js 22.20+, npm/npx and Git. Select your agents and review the
installation summary; omit `-g` for a project-only install. The CLI handles
the skill directories. The [guide](docs/setup/agent-skill.md) covers existing
skills, telemetry, verification and manual fallback. This installs instructions,
not the MCP server or its connection.
## Configuration
Only configure the products you use. [Provider Keys](docs/api-keys.md) explains
which key each product needs. Store keys in a private file outside the
repository; the client receives only its `ARK_MCP_ENV_FILE` path. Guided setup
prepares the blank file and configuration; optional flags remain off unless
requested.
> [!IMPORTANT]
> **Upgrading:** `SEEDANCE_DEFAULT_MODEL` now defaults to Seedance 2.5. If
> `SEEDANCE_MODEL_BINDINGS` lists only a Seedance 2.0 model, set
> `SEEDANCE_DEFAULT_MODEL` to that ID (or add a 2.5 binding), or the server
> fails at startup. See [Configuration](docs/configuration.md#seedance-default-model-upgrade-note).
If a credential is absent, the server skips registering that product's
tools. `seed_media_get_artifact`, `seed_media_export_artifact`, and
`seed_media_persist_url` are always available, provider tools appear only
when their credentials are configured, `media_upload` and
`media_presign` appear
only when object storage credentials (TOS or S3) are configured, and
`speech_to_text` appears only when `BYTEPLUS_SEED_SPEECH_API_KEY` is set.
`vod_enhance_video`, `vod_transcode_video`, `vod_add_subtitles`,
`vod_remove_subtitles`, `vod_separate_audio`, and `vod_get_task` appear only when
`BYTEPLUS_VOD_MEDIAKIT_API_KEY` is set. `omnihuman_create_task`,
`omnihuman_get_task`, and `omnihuman_cancel_task` appear only when
`BYTEPLUS_OMNIHUMAN_ENABLED=true` and `BYTEPLUS_CV_API_KEY` is set.
See [Configuration](docs/configuration.md) for the full environment
variable reference.
## Using with MCP Clients
Long operations always run in the background. By default, submit them with
ordinary calls to `ark_job_capabilities`, `ark_job_submit`, `ark_job_get`, and
`ark_job_cancel` — MCP task support is still rare, and any client that reports
task augmentation as unsupported rejects `execution.taskSupport="required"`
outright. A client with MCP task support can instead call the original tools as
task-augmented requests and retrieve output through `tasks/get`. Both paths
enqueue the same FastMCP Docket worker and preserve the same typed tool result,
ownership, scope, concurrency, and replay safeguards.
Both paths are tested in-process, over subprocess stdio, and over authenticated
Streamable HTTP with the locked FastMCP 4.1.8 runtime. The ordinary path uses
standard MCP tool calls and does not require a client-specific task transport.
The named desktop/IDE snippets below remain connection templates because exact
client releases and tool-selection behavior can change. See the
[background execution workflows](docs/integration-guide.md#background-execution).
Use the client-specific guides below. Each starts with guided setup and keeps
manual configuration as an optional fallback.
### Claude Desktop
Follow [Claude Desktop setup](docs/integrations/claude-desktop.md).
A separate coding agent can configure Desktop; Desktop chat alone is not
assumed to have local installation tools.
### Codex CLI
Follow [Codex setup](docs/integrations/codex.md), or
[Claude Code setup](docs/integrations/claude-code.md) for that coding client.
### OpenCode
Follow [OpenCode setup](docs/integrations/opencode.md). Its configuration
format depends on the installed edition.
For multiple clients sharing jobs, see the operator's
[shared-server transport guide](docs/transports.md). Separate local stdio
processes do not share their in-memory jobs.
### TRAE IDE
Follow [TRAE setup](docs/integrations/trae.md). Let the agent resolve paths
and prepare the entry, then complete any required settings-screen confirmation.
### TRAE Work
Use the Work notes in the [TRAE guide](docs/integrations/trae.md), checking
edition and local/cloud runtime. A cloud host cannot use local paths or
credentials without a separate setup decision.
### Cursor, VS Code, MCP Inspector
See [Cursor](docs/integrations/cursor.md) and [VS Code](docs/integrations/vscode.md).
The [MCP Inspector](docs/integration-guide.md#mcp-inspector) is an optional
developer tool, not an onboarding requirement.
## Available Make Targets
```bash
make help # Show all targets
make install # Install dependencies from uv.lock
make start # Run the server over stdio
make start-http # Run the server over Streamable HTTP (localhost:3000)
make dev # Run in dev mode with auto-reload
make test # Run the test suite
make lint # Lint with ruff
make typecheck # Type-check with mypy
make inspect # Launch FastMCP inspector
make check-env # Validate environment configuration
```
## Documentation
| Document | Description |
|---|---|
| [Getting Started](docs/getting-started.md) | Installation, configuration, and first run |
| [Migrating to 0.2.0](docs/migration-0.2.md) | Removed 0.1.x tools and their replacements |
| [Architecture](docs/architecture.md) | System structure, two-gateway domain layer, request flow |
| [Configuration](docs/configuration.md) | Full environment variable reference |
| [Integration Guide](docs/integration-guide.md) | MCP client setup (Claude, Cursor, VS Code, Inspector) |
| [API Reference](docs/api-reference.md) | Complete tool schemas, inputs, outputs, and examples |
| [Use Cases](docs/use-cases.md) | Common scenarios with example tool calls |
| [Tools](docs/tools.md) | Tool reference with input/output tables |
| [Private Asset Library](docs/assets.md) | Real-person, virtual portrait and copyright assets for Seedance (AK/SK) |
| [Security](docs/security.md) | Consolidated security model (auth, SSRF, body limits) |
| [Runtime](docs/runtime.md) | Concurrency, budget, ownership, retry |
| [Observability](docs/observability.md) | Structured logging, metrics, tracing |
| [Models](docs/models.md) | Model capability registry and validation |
| [Artifacts](docs/artifacts.md) | Durable artifact lifecycle and store |
| [Transports](docs/transports.md) | stdio vs HTTP deployment |
| [Deployment](docs/deployment.md) | Container, Kubernetes, and remote HTTP deployment |
| [BytePlus Terraform](docs/byteplus-terraform.md) | ECS starter, retained disk, private activation, backups, and recovery |
| [Secret Manager](docs/secret-manager.md) | Pinned BytePlus provider-key versions, redacted planning, sync, and rollback |
| [Troubleshooting](docs/troubleshooting.md) | Common errors and fixes |
## Project Layout
```text
ark-mcp/
├── src/ark_mcp/
│ ├── server.py # Deterministic FastMCP factory and registration
│ ├── __main__.py # Entry point (truststore injection)
│ ├── runtime.py # Lifespan-owned stores, limits, budgets, ownership
│ ├── config/ # Pydantic Settings, model capability registry
│ ├── domain/ # ArtifactRef, errors, media, models
│ ├── providers/ # ModelArk + Seed Speech gateways and adapters
│ ├── tools/ # 9 tool handlers + parallel helpers + cost estimation
│ ├── artifacts/ # Tenant-aware filesystem artifact store
│ ├── observability/ # Structured logging and Prometheus metrics
│ └── security/ # Shared-key auth, URL/media policy, safe downloader, HTTP limits
├── tests/
│ ├── unit/ # Model validators, URL policy, media policy, helpers
│ ├── contract/ # Provider gateway + adapter contract tests
│ ├── integration/ # Tool handler, HTTP security, MCP conformance
│ └── e2e/ # In-process FastMCP client tests
├── docs/ # User and contributor documentation
├── plans/ # Implementation plans
├── scripts/ # Verification and smoke test scripts
├── fastmcp.json # Declarative server configuration
├── Makefile # Task runner
└── pyproject.toml # Project metadata and dependencies
```
## Tech Stack
- [Python 3.12+](https://www.python.org/) on [uv](https://docs.astral.sh/uv/)
- [FastMCP v4](https://gofastmcp.com/) — MCP server framework
- [httpx](https://www.python-httpx.org/) — async HTTP client
- [Pydantic v2](https://docs.pydantic.dev/) — typed models and validation
- [Pillow](https://pillow.readthedocs.io/) — bounded PNG/JPEG artifact inspection
- [pydantic-settings](https://pydantic.dev/docs/validation/latest/concepts/pydantic_settings/) — environment configuration
- [Starlette](https://www.starlette.io/) — HTTP middleware, body limits, and responses
- [prometheus-client](https://github.com/prometheus/client_python) — `/metrics` and Prometheus exposition
- [cachetools](https://github.com/tkem/cachetools) — TTL caching for provider responses and principal limits
- [truststore](https://truststore.readthedocs.io/) — macOS system certificate injection
- [respx](https://github.com/lundberg/respx) — HTTP mocking for contract tests
## License
See the project configuration for license details.
## Status
The provider surfaces and both transports are implemented. CI enforces offline
regression tests and coverage, formatting/lint, strict typing, security scans,
package builds, dependency auditing, and container health. Remote HTTP requires
a shared MCP key hash (`MCP_API_KEY_SHA256`) and is intentionally fail-closed.
All key holders use the fixed `shared-team` tenant/principal, shared data and
budget, and ordinary scopes excluding asset and moderation administration.
Python defaults to `MCP_AUTH_MODE=local` for stdio/loopback; Docker, Compose and
Terraform default to `api_key`.
**Breaking authentication change:** the former `jwt` mode is rejected and
retired `MCP_JWT_*`, `MCP_TENANT_CLAIM` and `MCP_PUBLIC_BASE_URL` settings are
not used. Ownership is not transferred automatically. Preserve SQLite, Redis,
artifacts and the encryption key; follow the
[migration guide](docs/self-hosting.md#breaking-change-migration).
Seedream's [live smoke matrix](docs/integration-guide.md#opt-in-seedream-smoke-matrix)
is opt-in; editing/alpha and visual acceptance still require authorized checks.
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessNo recent community issues