Ein MCP-Server, mit dem Claude Code Bilder und kurze Videos über die Google Gemini API (Imagen 4 für Standbilder, Veo 3.1 für Videos) generieren kann.
Ich habe Websites mit Claude Code erstellt und bin immer wieder auf dieselbe Lücke gestoßen. Claude entwarf ein tolles Layout und sagte dann: „Fügen Sie hier Ihr Hero-Bild ein.“ Ich musste es woanders generieren, zurückkommen, es einbinden, iterieren, wiederholen. Der Kontextwechsel war der eigentliche Aufwand. Also habe ich diesen MCP-Server gebaut, um den Kreislauf zu schließen. Claude schreibt den Prompt, der Server kontaktiert Veo oder Imagen, die Datei landet im Projektverzeichnis und Claude referenziert sie in dem Code, den es bereits schreibt. Eine Sitzung, keine Übergaben.
Ich mache es als Open Source verfügbar, weil andere Leute dasselbe Problem lösen und niemand das zweimal bauen sollte.
Related MCP server: Gemini Image & Video Generation MCP
Claude Code generiert Visuals mit visualgen-mcp und bindet sie in die Seite ein.
https://github.com/user-attachments/assets/34d25755-cd4c-47b0-a0cb-056b9ed8b783
Sechs Tools, bereitgestellt über stdio:
submit_video(prompt, model, aspect_ratio, resolution, negative_prompt?, image_path?) — übermittelt einen Veo 3.1-Auftrag. Gibt sofort eine job_id zurück.
check_video(job_id) — fragt einen Auftrag ab. Wenn das Video fertig ist, lädt der Server es herunter und gibt den Pfad zurück.
list_videos() — listet MP4-Dateien im Ausgabeverzeichnis auf, die neuesten zuerst.
generate_image(prompt, model, aspect_ratio, negative_prompt?) — synchrone Bildgenerierung (normalerweise unter 10s). Gibt den PNG-Pfad zurück.
list_images() — listet PNG-Dateien im Ausgabeverzeichnis auf.
get_pricing() — gibt die aktuellen Gemini-Preise zurück, damit Claude Sie vor teuren Durchläufen warnen kann.
Gemini API-Preise Stand 22.04.2026. Überprüfen Sie diese auf der offiziellen Preisseite vor der produktiven Nutzung.
Modell | Kosten |
Veo 3.1 Standard (720p / 1080p) | $0.40 / Sekunde |
Veo 3.1 Standard (4k) | $0.60 / Sekunde |
Veo 3.1 Fast (720p) | $0.10 / Sekunde |
Veo 3.1 Fast (1080p) | $0.12 / Sekunde |
Veo 3.1 Fast (4k) | $0.30 / Sekunde |
Veo 3.1 Lite (720p) | $0.05 / Sekunde |
Veo 3.1 Lite (1080p) | $0.08 / Sekunde |
Imagen 4 Fast | $0.02 / Bild |
Imagen 4 Standard | $0.04 / Bild |
Imagen 4 Ultra | $0.06 / Bild |
Gemini 2.5 Flash Image (Nano Banana) | $0.039 / Bild |
Für Endbenutzer:
uvx visualgen-mcpFür Mitwirkende (aus dem Quellcode):
git clone https://github.com/1RaghavM/visualgen-mcp.git
cd visualgen-mcp
uv sync
uv run python -m visualgen_mcpFühren Sie die interaktive Einrichtung einmal aus. Sie speichert Ihr Profil unter ~/.config/visualgen-mcp/config.toml (chmod 600) und bindet optional .mcp.json im aktuellen Projektverzeichnis ein.
uvx visualgen-mcp initSie werden nach Folgendem gefragt:
Gemini API-Schlüssel — erhalten Sie unter aistudio.google.com/apikey. Veo erfordert einen kostenpflichtigen Plan; Imagen und Nano Banana funktionieren im kostenlosen Tarif, jedoch mit strengeren Ratenbegrenzungen.
Ausgabeverzeichnis — wo generierte PNGs und MP4s landen. Standard ist ~/visualgen-output. Der Server erstellt es, falls es nicht existiert, und Tool-Antworten geben absolute Pfade zurück, damit Claude die Dateien im Code, den es schreibt, referenzieren kann.
Standard-Video-Stufe, Bildmodell und Seitenverhältnisse — werden verwendet, wenn Claude ein Tool aufruft, ohne diese anzugeben.
Führen Sie visualgen-mcp init jederzeit erneut aus, um das Profil zu aktualisieren. Projektbezogene Überschreibungen funktionieren weiterhin: Ein GEMINI_API_KEY oder OUTPUT_DIR, das in einer lokalen .env-Datei oder im env-Block von .mcp.json festgelegt ist, hat Vorrang vor dem Profil.
Führen Sie entweder visualgen-mcp init in Ihrem Projekt aus (es bietet an, dies für Sie zu schreiben) oder fügen Sie dies zur .mcp.json im Stammverzeichnis Ihres Projekts hinzu:
{
"mcpServers": {
"visualgen": {
"command": "uvx",
"args": ["visualgen-mcp"]
}
}
}Der Server liest Ihren API-Schlüssel und die Standardeinstellungen aus ~/.config/visualgen-mcp/config.toml. Wenn Sie diese für ein bestimmtes Projekt überschreiben möchten, setzen Sie GEMINI_API_KEY oder OUTPUT_DIR im env-Block von .mcp.json — Umgebungsvariablen haben Vorrang vor dem Profil.
Führen Sie /mcp in Claude Code aus, um zu bestätigen, dass der Server verbunden ist. Sie sollten visualgen mit sechs Tools aufgelistet sehen.
/visualgen-FähigkeitDer Server wird mit einer Claude Code-Fähigkeit geliefert, die Claude beibringt, wann welches Tool zu verwenden ist, wie Prompts für gängige Webdesign-Anfragen strukturiert werden und wann Kosten mit Ihnen bestätigt werden müssen. Wenn Sie visualgen-mcp init ausgeführt haben, wurde die Installation bereits angeboten. Andernfalls:
cd your-project
cp -r /path/to/visualgen-mcp/.claude/skills/visualgen ./.claude/skills/visualgenNach der Installation startet /visualgen hero video, modern SaaS landing, calm mood den gesamten Prozess auf einen Schlag — Claude wählt die Vorlage, erstellt den Prompt, übermittelt den Auftrag und bindet die zurückgegebene Datei in Ihren Code ein. Sie können auch einfach in natürlicher Sprache nach Visuals fragen — die Fähigkeit lädt sich automatisch, wann immer Claude kurz davor steht, ein visualgen-mcp-Tool aufzurufen.
Die Fähigkeit ist bei Kosten strikt: Veo standard und jeder Bild-zu-Video-Aufruf erfordern immer eine Bestätigung, bevor Kosten anfallen. Alles andere — die gesamte Bildgenerierung sowie Veo lite/fast Text-zu-Video — läuft im Hintergrund ab.
Claude Desktop verwendet dasselbe Muster. Fügen Sie einen Eintrag unter mcpServers in ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) oder %APPDATA%\Claude\claude_desktop_config.json (Windows) hinzu. Jeder MCP-Client mit stdio-Transport, der Tool-Aufrufe unterstützt, funktioniert. Es gibt keine HTTP- oder Authentifizierungsebene — der Server ist für die lokale Verwendung gedacht.
Ein echter Durchlauf aus einem Landingpage-Projekt. Ausgelassene Zeilen sind mit ... markiert.
> Build me a hero video loop for the top of the page. Something that suggests "city at night, calm, slow."
I'll generate that with the visualgen server.
submit_video(
prompt="A slow drone shot over a city skyline at night, warm window lights,
occasional headlights tracing streets below, calm mood, cinematic",
model="fast",
aspect_ratio="16:9",
resolution="1080p"
)
→ { "job_id": "f3c1...", "status": "submitted", "model": "veo-3.1-fast-generate-preview",
"estimated_seconds": 60 }
I'll check back in a minute.
check_video("f3c1...")
→ { "status": "pending", "elapsed_seconds": 25 }
... wait ...
check_video("f3c1...")
→ { "status": "complete",
"path": "/Users/.../landing/generated/veo-fast-20260422T191203Z.mp4",
"duration_seconds": 8.0 }
Writing it into the hero section:
Edit: src/components/Hero.tsx
<video
autoPlay
muted
loop
playsInline
className="absolute inset-0 h-full w-full object-cover"
src="/generated/veo-fast-20260422T191203Z.mp4"
/>Ein Prompt, eine Generierung, Datei im Projekt, Code aktualisiert.
submit_videoParameter | Typ | Standard | Hinweise |
|
| (erforderlich) | Videobeschreibung. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Text, der beschreibt, was vermieden werden soll. |
|
|
| Absoluter Pfad zu einem PNG/JPEG/WebP-Startframe. |
Gibt {"job_id": str, "status": "submitted", "model": str, "estimated_seconds": int} zurück.
check_videoParameter | Typ | Standard |
|
| (erforderlich) |
Gibt eines der folgenden zurück:
{"status": "pending", "elapsed_seconds": int}
{"status": "complete", "path": str, "duration_seconds": float}
{"status": "failed", "error": str}
list_videosKeine Parameter. Gibt list[{"path": str, "size_bytes": int, "created_at": str}] zurück, die neuesten zuerst.
generate_imageParameter | Typ | Standard | Hinweise |
|
| (erforderlich) | Bildbeschreibung. |
|
|
|
|
|
|
|
|
|
|
| Wird von Nano Banana ignoriert. |
Gibt {"path": str, "model_used": str} zurück.
list_imagesKeine Parameter. Gibt list[{"path": str, "size_bytes": int, "created_at": str}] zurück, die neuesten zuerst.
get_pricingKeine Parameter. Gibt ein Wörterbuch der aktuellen Preise pro Modell, ein last_updated-Datum und einen Link zur Quelle zurück. Fest codiert — der Server ruft hierfür keine API auf.
Veo-Clips sind auf 8 Sekunden begrenzt. Dieser Server fordert immer 8 Sekunden an.
Es gibt keinen kostenlosen Tarif für Veo. Jede erfolgreiche Generierung wird in Rechnung gestellt.
Generierte Videos werden 48 Stunden nach der Generierung von den Google-Servern gelöscht. Laden Sie sie (über check_video) innerhalb dieses Zeitfensters herunter.
Der Auftragsspeicher ist im Arbeitsspeicher. Wenn Sie den Server neu starten, gehen ausstehende Aufträge verloren. Siehe das TODO in src/visualgen_mcp/jobs.py für den SQLite-Migrationspfad.
Einige Prompts werden von Googles Inhaltsfiltern abgelehnt. Sie erhalten {"status": "failed", ...} zurück, keinen Absturz.
Nano Banana (gemini-2.5-flash-image) ist schneller und günstiger als Imagen 4, akzeptiert aber keinen negative_prompt. Verwenden Sie Imagen 4, wenn Sie einen benötigen.
list_videos und list_images sehen nur Dateien im OUTPUT_DIR. Sie durchsuchen keine Unterverzeichnisse und wechseln nicht zwischen Verzeichnissen.
Siehe CONTRIBUTING.md.
MIT. Siehe LICENSE.
Check a video generation job. Downloads the file when ready.
Returns one of three shapes:
{"status": "pending", "elapsed_seconds": int}
{"status": "complete", "path": str, "duration_seconds": float}
{"status": "failed", "error": str}
Safe to call repeatedly. Once a job is complete or failed, subsequent calls return the cached terminal state without re-polling.
Args: job_id: The id returned by submit_video.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure and excels. It reveals key traits: polling behavior ('Downloads the file when ready'), idempotency ('Safe to call repeatedly'), caching ('returns the cached terminal state'), and the three possible return shapes with their semantics. This goes well beyond basic parameter documentation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly structured and concise. It front-loads the core purpose, then details return shapes, behavioral notes, and parameters in logical order. Every sentence earns its place with essential information, and there is no wasted verbiage.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (stateful job monitoring), lack of annotations, and presence of an output schema (which covers return values), the description is complete. It explains the tool's role in a workflow, behavioral guarantees, parameter semantics, and output interpretation, leaving no significant gaps for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, so the description must compensate. It adds crucial semantic context for the single parameter: 'job_id: The id returned by submit_video' clarifies the parameter's origin and relationship to another tool. However, it doesn't specify format constraints (e.g., UUID, string length) that might be in an unannotated schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('Check', 'Downloads') and resource ('video generation job'), distinguishing it from siblings like 'submit_video' (which creates jobs) and 'list_videos' (which lists existing videos). It explicitly describes the monitoring and file retrieval functionality.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool: 'Check a video generation job' implies it's for monitoring jobs created by 'submit_video'. It also specifies 'Safe to call repeatedly' and explains terminal state behavior, giving clear operational context without misleading exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate an image synchronously. Blocks until the file is on disk.
Typical latency is under 10 seconds. The PNG is written to the configured OUTPUT_DIR and the absolute path is returned.
Args: prompt: Text description of the image to generate. model: "nano-banana" (Gemini 2.5 Flash Image, the default — cheapest and fastest) or "imagen" (Imagen 4, higher quality, higher cost). aspect_ratio: "1:1", "16:9", "9:16", "4:3", or "3:4". negative_prompt: Optional text describing what to avoid. Ignored by Nano Banana; used by Imagen 4 when supplied.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | ||
| model | No | nano-banana | |
| aspect_ratio | No | 16:9 | |
| negative_prompt | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: synchronous operation ('Blocks until the file is on disk'), typical latency ('under 10 seconds'), file handling ('PNG is written to OUTPUT_DIR'), and return value ('absolute path is returned'). It also notes model-specific behavior differences (e.g., negative_prompt ignored by Nano Banana). However, it lacks details on error handling or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded: the first sentence states the core purpose and key behavioral trait (synchronous blocking). Subsequent sentences efficiently cover latency, output details, and parameter explanations in a structured format with bullet-like clarity. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (image generation with multiple parameters), no annotations, and the presence of an output schema (which handles return value documentation), the description is complete enough. It covers purpose, behavior, parameters, and output location, leaving the output schema to detail the return structure. No critical gaps remain for agent understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must fully compensate. It provides comprehensive parameter semantics: 'prompt' as the text description, 'model' with two options and cost/quality trade-offs, 'aspect_ratio' with five specific options, and 'negative_prompt' with optional usage and model-specific behavior. This adds significant meaning beyond the bare schema, fully documenting all four parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Generate an image synchronously' with specific details about the output format (PNG) and location (OUTPUT_DIR). It distinguishes from sibling tools like 'list_images' (which retrieves existing images) and 'submit_video' (which handles video generation), making the verb+resource combination specific and differentiated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool: for synchronous image generation with latency under 10 seconds. It distinguishes from alternatives by specifying the output format (PNG) and location (OUTPUT_DIR), but does not explicitly state when NOT to use it or compare it to other image-related tools beyond the sibling list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return current published Gemini API pricing for the models this server uses.
Rates are per-image for images and per-second for video. Pricing is
hardcoded from the official docs (see the source field) and may drift;
always verify before expensive operations.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key traits: it returns 'current published' pricing, notes that rates vary by media type (images vs. video), mentions the data source ('hardcoded from the official docs'), and warns about potential drift and the need for verification. This covers most behavioral aspects for a read-only pricing tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose in the first sentence, followed by supporting details. Every sentence earns its place by clarifying pricing units, data source, and reliability warnings. It is appropriately sized with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (0 parameters, no annotations, but with an output schema), the description is complete. It covers purpose, usage context, behavioral details like data source and limitations, and output semantics. The presence of an output schema means the description doesn't need to explain return values, so this is sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description adds value by explaining the semantics of the returned pricing data (e.g., 'per-image for images and per-second for video'), which goes beyond the schema. A baseline of 4 is appropriate for zero-parameter tools with high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Return current published Gemini API pricing for the models this server uses.' It specifies the verb ('Return'), resource ('Gemini API pricing'), and scope ('models this server uses'), distinguishing it from sibling tools like generate_image or submit_video that perform different operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool: to get pricing information for API operations. It implies usage before 'expensive operations' but does not explicitly state when not to use it or name alternatives among sibling tools, which would be needed for a score of 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List every PNG file in the configured OUTPUT_DIR, newest first.
Each entry has absolute path, size in bytes, and creation timestamp.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: it lists files from a specific directory (OUTPUT_DIR), sorts them (newest first), and describes the return format (absolute path, size, creation timestamp). It doesn't mention permissions, rate limits, or error conditions, but covers the core behavior adequately.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly concise with two sentences that each earn their place. The first sentence states the core action and scope, while the second provides essential output details. No wasted words, well-structured and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (0 parameters, no annotations, but has output schema), the description is complete enough. It explains what the tool does, how results are sorted, and what data each entry contains. The output schema will handle return value details, so the description doesn't need to explain return values further.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters with 100% schema description coverage, so the baseline is 4. The description doesn't need to add parameter information, and it appropriately focuses on the tool's behavior rather than parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('List every PNG file') and resources ('in the configured OUTPUT_DIR'), including sorting order ('newest first'). It distinguishes from sibling tools like 'list_videos' by specifying PNG files rather than videos.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool (listing PNG files in OUTPUT_DIR), but doesn't explicitly state when not to use it or name alternatives. It implies usage for PNG files specifically, which helps differentiate from 'list_videos' for video files.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List every MP4 file in the configured OUTPUT_DIR, newest first.
Each entry has absolute path, size in bytes, and creation timestamp.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: it lists files 'newest first', specifies the exact fields in each entry (path, size, timestamp), and mentions the configured OUTPUT_DIR as the source. It lacks details on permissions or error handling, but covers core behavior adequately.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly concise and front-loaded: the first sentence states the core purpose and key details (MP4 files, OUTPUT_DIR, ordering), and the second sentence adds essential output structure. Every sentence earns its place with zero waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (0 parameters, simple list operation), no annotations, and the presence of an output schema (which handles return values), the description is complete enough. It covers purpose, behavior, and output fields, leaving no significant gaps for this context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters with 100% schema description coverage, so the baseline is 4. The description adds no parameter information, which is appropriate since there are no parameters to document, maintaining clarity without redundancy.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('List every MP4 file') and resource ('in the configured OUTPUT_DIR'), with explicit scope details. It distinguishes from sibling tools like 'list_images' by specifying MP4 files only, not images.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context about when to use this tool (to list MP4 files in OUTPUT_DIR), but does not explicitly state when not to use it or name alternatives like 'list_images' for non-MP4 files or 'check_video' for individual video inspection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Submit a Veo 3.1 video generation job. Returns immediately with a job_id.
Videos typically take 30-120 seconds. Call check_video(job_id) to poll for completion. The final MP4 is written to the configured OUTPUT_DIR and its absolute path is returned by check_video once ready.
Args: prompt: Text description of the video to generate. model: "lite" (cheapest), "fast" (default, good balance), or "standard" (highest quality, most expensive). See get_pricing for rates. aspect_ratio: "16:9" (landscape) or "9:16" (portrait). resolution: "720p", "1080p", or "4k". "4k" is rejected for model="lite". negative_prompt: Optional text describing what to avoid. image_path: Optional absolute path to a PNG/JPEG/WebP file to use as the starting frame for image-to-video generation.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | ||
| model | No | fast | |
| aspect_ratio | No | 16:9 | |
| resolution | No | 720p | |
| negative_prompt | No | ||
| image_path | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: the asynchronous nature (returns immediately with job_id), typical processing time (30-120 seconds), polling mechanism (call check_video), output location (written to OUTPUT_DIR), and format (MP4). This covers execution flow, timing, and output handling beyond basic functionality.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and well-structured: it starts with the core purpose and immediate return, then explains the asynchronous workflow, and finally details each parameter in a clear Args section. Every sentence adds value without redundancy, making it efficient and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of an asynchronous video generation tool with 6 parameters, no annotations, and an output schema (implied by 'Returns immediately with a job_id'), the description is complete. It covers the tool's purpose, behavioral workflow, parameter semantics, and integration with sibling tools, providing all necessary context for an agent to use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must fully compensate. It provides detailed semantic explanations for all 6 parameters: purpose of prompt, model options with cost/quality trade-offs, aspect ratio meanings, resolution options with constraints (4k rejected for lite), optional negative_prompt usage, and image_path for image-to-video. This adds substantial meaning beyond the bare schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Submit a Veo 3.1 video generation job') and resource ('video'), distinguishing it from siblings like check_video (polling), generate_image (image creation), and list_videos (listing). It uses precise verbs and identifies the exact resource being created.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool (to start a video generation job) and explicitly mentions check_video as the follow-up for polling completion. However, it doesn't explicitly state when NOT to use it or compare it to alternatives like generate_image for image generation, leaving some sibling differentiation implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0check_videogenerate_imageget_pricinglist_imageslist_videossubmit_videoScored across 6 tools
Each tool has a clearly distinct purpose with no ambiguity. check_video monitors video jobs, generate_image creates images, get_pricing provides cost information, list_images and list_videos enumerate outputs, and submit_video initiates video generation. The separation between image and video operations is particularly clear.
All tools follow a consistent verb_noun pattern with snake_case throughout. The naming is predictable and readable: check_video, generate_image, get_pricing, list_images, list_videos, and submit_video. This consistency makes the tool set easy to understand at a glance.
Six tools is well-scoped for a visual generation server. This provides complete coverage for both image and video workflows without being overwhelming. Each tool earns its place by addressing a specific need in the generation, monitoring, listing, or pricing aspects of the service.
The tool set covers the core visual generation domain comprehensively with create, check, and list operations for both images and videos, plus pricing information. The only minor gap is the lack of a tool to delete or manage generated files, but agents can work around this using system file operations.
MCP server for Google Veo AI video generation
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
MCP server for Qwen Image 3 AI image generation
MCP server for Grok Imagine AI video generation
