Replicate MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Logging level | INFO |
| ENABLE_DEBUG | No | Enable debug mode | false |
| MAX_BATCH_SIZE | No | Maximum batch size for concurrent image generation | 5 |
| REQUEST_TIMEOUT | No | Timeout for API requests in seconds | 300 |
| REPLICATE_API_TOKEN | Yes | Your Replicate API token |
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 | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageC | Generate a single image from a text prompt using Replicate AI models. |
| generate_image_batchC | Generate multiple images concurrently from text prompts. |
| generate_from_reference_imageC | Generate an image based on a reference image and text prompt. |
| edit_imageB | Edit an existing image based on text prompts. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| creative_image_prompt | Generate creative image prompts based on style, subject, and mood with save_to_file instruction. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
generate_image and generate_image_batch are clearly distinct by cardinality, and each has a unique input type. However, edit_image and generate_from_reference_image overlap: both take an image and text prompt and return a modified/new image, which could cause misselection.
All tool names use snake_case with a clear verb_noun or verb_preposition_noun structure. The generate_ prefix is consistent across three tools, and edit_image is a natural semantic variation.
Four tools is well within the ideal 3-15 range for a focused image generation service. It covers key workflows without redundancy, though it could arguably support more operations.
The set covers single generation, batch generation, reference-based generation, and editing, which are core for image generation. Missing operations like listing available models or retrieving generation status are minor gaps an agent could work around.