Replicate Ideogram V3 MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REPLICATE_API_TOKEN | Yes | Your Replicate API token. You can get your API token from https://replicate.com/ |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageC | Generate an image using Ideogram V3 Balanced model via Replicate API. Supports text-to-image, inpainting, and style transfer. |
| get_image_statusC | Check the status of an image generation request |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: generate_image initiates an image generation request, while get_image_status checks the status of an existing request. There is no overlap in functionality, making it easy for an agent to select the correct tool.
Both tools follow a consistent verb_noun pattern (generate_image, get_image_status) with clear, descriptive names. The naming is uniform and predictable, using snake_case throughout.
With only two tools, the server feels thin for its purpose of image generation via Ideogram V3. It lacks essential operations like retrieving generated images, managing requests (e.g., cancel), or handling variations, which limits functionality.
The toolset is severely incomplete for image generation workflows. While it covers initiating and checking status, there is no tool to retrieve the actual generated image, update requests, or handle errors, leaving agents unable to complete core tasks.