Skip to main content
Glama
sena-labs

Replicate-MCP-Server

by sena-labs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Start a Replicate fine-tune / training run

replicate_create_training

Starts a fine-tuning run on a trainable base model using your dataset and hyperparameters, returning a training ID to poll for status and outputs.

Instructions

Kick off a fine-tuning (training) run on a trainable base model — e.g. a Flux LoRA trainer — with your dataset and hyperparameters. Returns immediately with a training ID; poll it with replicate_get_training.

Args:

  • model: BASE trainer "owner/name" (or "owner/name:version" to pin the trainer version inline). e.g. "ostris/flux-dev-lora-trainer".

  • version (optional): trainer version id. Required unless pinned inline on model.

  • destination: "owner/name" the trained weights are pushed to. The destination model must already exist on your account.

  • input: training inputs as a JSON object (dataset URL + hyperparameters). Call replicate_get_model_schema on the trainer to see its exact inputs.

Returns structuredContent: TrainingSummary { id, status, model, version, destination, created_at, completed_at, output_version, error }.

Input Schema

NameRequiredDescriptionDefault
inputNoTraining inputs as a JSON object (dataset URL + hyperparameters). The exact keys depend on the trainer — call replicate_get_model_schema on the trainer model to see them.
modelYesThe BASE trainer model as "owner/name" (or "owner/name:version" to pin the trainer version inline). Example: "ostris/flux-dev-lora-trainer".
versionNoTrainer version id. Required unless you pinned it inline on `model` as "owner/name:version".
destinationYesWhere the trained weights are pushed, as "owner/name". The destination model must already exist on your account.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.3.1
    • addedInput schema / properties / input / propertyNames
      Added value: +{
+  "type": "string"
+}
  2. First observedv3.2.3

TDQS

A4.1/5.0
Behavior4/5

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

Annotations mark it non-read-only, open-world, non-idempotent, but say nothing about asynchrony, so the description's 'returns immediately with a training ID; poll it' is genuinely additive, as is the precondition that the destination model must already exist. It omits cost/credit implications and what happens to an existing destination model's weights, so not a 5.

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?

Front-loaded with the action and the async contract, then a scannable args list and a return-shape line. Slightly redundant with the schema's own parameter descriptions, but no sentence is wasted.

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

Completeness4/5

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

No output schema exists, and the description compensates by naming the returned TrainingSummary fields, covering the required preconditions, and stating the polling follow-up. It leaves out failure modes (trainer input validation errors, billing) that an agent might need for a long-running paid job.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all four parameters, including the model/version pinning relationship and the existing-destination precondition. The description's args block largely restates those same semantics rather than adding format or constraint detail beyond them, so the baseline of 3 applies.

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?

A concrete verb plus resource ('Kick off a fine-tuning (training) run on a trainable base model') with an inline example trainer, which cleanly separates it from the generation siblings and from replicate_run_model. An agent can identify the operation without opening the schema.

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?

Explains the async contract explicitly: returns immediately with a training ID and is polled via replicate_get_training, and routes to replicate_get_model_schema to discover trainer inputs. It lacks an explicit statement of when NOT to use this versus replicate_run_model or replicate_pipeline_start, so it falls short of a 5.

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

Deploy Server

Other Tools