Skip to main content
Glama

PixVerse MCP Server by useapi.net (third-party)

Generate images

pixverse_create_image

Generate 1-4 images with Qwen Image (the default), Nano Banana, Seedream, GPT Image or Kling image models, from a prompt and up to 16 reference images (by model). Each model has its own qualities, ratios and reference count (pixverse_get_features lists the image models the plan allows). Uses PixVerse credits per image, free in Relax Mode where the plan includes the model. Waits up to ~50 s and returns each image's image_id and image_url, the first as an image; else the ids for pixverse_get_image. POST /images/create.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "pixverse_create_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNoSeed for a repeatable result.
waitNoWait up to ~50 s for the job to finish (default true); false returns the id at once.
emailNoThe PixVerse account email (pixverse_list_accounts). Optional: by default a random account with a free slot.
modelNoDefault qwen-image.
promptYesWhat the image shows; the limit depends on the model.
maxJobsNoOverride the account's maxJobs (jobs at once) for this request, 1-8.
qualityNoDefault: the model's first quality. Each model takes only some (400 otherwise).
relax_modeNoLeft out, the image is free where the plan includes the model (Relax Mode) and costs credits otherwise; true insists on Relax Mode (412 when the plan does not include the model); false pays credits at full speed.
image_pathsNoReference images in order: paths from pixverse_upload_file (the model sets how many).
aspect_ratioNoDefault: the model's first ratio (auto where offered). 1:4, 4:1, 1:8 and 8:1 on nano-banana-2.1 only.
create_countNoImages to make, 1-4 (default 1). Each image is charged.
detail_levelNogpt-image-2.0 (low, medium, high), gpt-image-2.5-flare / -sunburst (also xhigh, max) and nano-banana-2.1 (minimal, medium, high) only; default low, medium on nano-banana-2.1.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With annotations supplied (readOnly=false, openWorld=true, idempotent=false, destructive=false), the description adds real behavioral context: credit consumption per image, free Relax Mode condition, a ~50 s wait cap, non-waiting polling behavior, and the 412/400 failure modes. That is substantially more than the annotations convey for a paid, non-idempotent generation call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, front-loaded with the core action and inputs, then cost/latency, then return values and the endpoint. The first sentence is long and packs model enumeration that could be trimmed, but no sentence is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter, credit-consuming generation tool with no output schema, the description covers the missing pieces an agent needs: return shape (image_id/image_url, first image inline), the async fallback path, latency ceiling, and cost behavior. Nothing essential to invoking it correctly is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents every parameter and the baseline is 3. The description adds cross-parameter meaning by noting that qualities, ratios, and reference counts are model-dependent and that each returned image is charged, which helps an agent reason about model/quality/aspect_ratio coupling rather than reading each field in isolation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a precise verb+resource ('Generate 1-4 images') and names the concrete model family and inputs (prompt plus up to 16 reference images). It also names the sibling tools that support the workflow (pixverse_get_features for model availability, pixverse_get_image for polling), so an agent can separate this from the video/music creation tools at a glance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is strong: it explains calling pixverse_get_features to see which models the plan allows, and states that when not waiting the agent should poll with pixverse_get_image. The relax_mode sentence gives a clear decision rule (free vs. credits, 412 when unsupported). It never explicitly says when NOT to use this tool (e.g., video instead of stills), which keeps it from a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources