search_modelsLABSCO SUMMARY
Find a model and run it in the same breath.
The useful pairing is search_models with create_and_poll_prediction: describe the kind of model you want, get one, run it, and see the image — without opening Replicate to copy a version string. The templates matter more than they look, since they save the assistant from inventing plausible-sounding image parameters. Worth knowing before you build on it: the author has stopped maintaining this and Replicate now ships an official server.
What it is
A community MCP server for Replicate, covering model discovery, prediction runs and viewing the images that come out. The README marks it as no longer in active development and points to Replicate's own official MCP server; the code remains installable and is a reasonable base to fork.
What you get
- Find something to run — search_models by meaning, list_models by owner, and get_model for versions and details
- Browse Replicate's curated groupings — list_collections and get_collection
- Run a model — create_prediction returns immediately, create_and_poll_prediction waits until it finishes
- Follow work in flight — get_prediction for status, list_predictions for what you ran recently, cancel_prediction to stop one
- See the result — view_image opens generated output in your browser, with clear_image_cache and get_image_cache_stats managing what is kept
- Presets so a prompt does not have to carry every parameter: quality levels from draft to extreme, styles such as photographic, cinematic or anime, and sizes including square at 1024x1024 and portrait at 832x1216
- create_prediction accepts a webhook_url, so a long run can call back instead of being polled
Requirements
A Replicate API token, set as REPLICATE_API_TOKEN in the client config or the environment. Install globally with npm install -g mcp-replicate, or run it with npx. Replicate bills for the compute a prediction uses, and its rate limits apply to this the same as to any other client.
Setup effort
One command plus a key — npm install -g mcp-replicate, then supply credentials
USE CASES
01
Finding a model that does something specific
Search by describing the job rather than the name, then read the versions and inputs it expects.
02
Generating an image and actually looking at it
Run the model, wait for it to finish, and open the output in your browser.
03
Iterating on a prompt
Reuse a quality and style preset so only the prompt changes between runs.
04
A run is taking too long or was a mistake
Check its status and stop it before it costs more.
05
Reviewing what you have been running
List recent predictions, and clear the cached images once you are done with them.
13 tools
Listed in project docs. Your client may show a different list.
list_modelsget_modellist_collectionsget_collectioncreate_predictioncreate_and_poll_predictionget_predictioncancel_predictionlist_predictionsview_imageclear_image_cacheget_image_cache_statsBEFORE YOU INSTALL
What to know first
Tools you get
13 tools named in the project's documentation.
Requires
- mcp-replicate on PATH
- Node.js >= 18.0.0
- REPLICATE_API_TOKEN in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
npm install -g mcp-replicateMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"replicate": {
"command": "mcp-replicate",
"env": {
"REPLICATE_API_TOKEN": "<YOUR_REPLICATE_API_TOKEN>"
}
}
}
}
