replicate-flux-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REPLICATE_API_TOKEN | Yes | Your Replicate API token for accessing the Flux Schnell model |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageC | Generate an image from a text prompt using Flux Schnell model |
| generate_multiple_imagesC | Generate multiple images from an array of prompts using Flux Schnell model |
| generate_image_variantsC | Generate multiple variants of the same image from a single prompt |
| generate_svgC | Generate an SVG from a text prompt using Recraft model |
| get_predictionC | Get details of a specific prediction by ID |
| create_predictionC | Generate an prediction from a text prompt using Flux Schnell model |
| prediction_listC | Get a list of recent predictions from Replicate |
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 7 tools
The tools have some clear distinctions, such as between image generation and prediction management, but there is significant overlap and ambiguity among the image generation tools. For example, 'generate_image' and 'create_prediction' both seem to create images from prompts, and 'generate_image_variants' and 'generate_multiple_images' could be confused for handling multiple outputs in similar ways.
The naming is mostly consistent with a verb_noun pattern, such as 'create_prediction' and 'generate_image', but there are minor deviations like 'prediction_list' (noun_verb) and inconsistent use of 'generate' vs. 'create'. Overall, the pattern is readable and predictable with only slight variations.
With 7 tools, the count is well-scoped for an image generation server, covering core operations like creating, retrieving, and listing predictions, as well as various image generation methods. Each tool appears to serve a distinct purpose within this domain, making the set appropriately sized.
The tool set provides good coverage for image generation and prediction management, including creation, retrieval, and listing. However, there is a minor gap in update or delete operations for predictions or images, which might limit full lifecycle management but is not critical for basic usage.