Skip to main content
Glama

Start Async Batch Predictions

replicate_batch_start

Run up to 50 Replicate predictions in parallel without blocking. Receive a job ID instantly and poll for progress and results.

Instructions

Run multiple Replicate predictions in parallel as a background job. Returns a job_id immediately — the predictions run in the background. Poll replicate_batch_status for progress and results.

Use this when you have 2–50 predictions to run and don't want to block. Each item specifies its own model and input, so you can mix models in one batch.

IMPORTANT: model must be a full Replicate identifier ("owner/name" or "owner/name:version"), not a curated shortcut like "flux-schnell". Use replicate_get_model_schema to look up the correct identifier.

Args:

  • items (array, 1–50): Predictions to run. Each: { model: "owner/name[:version]", input: {...} }.

  • concurrency (1–10, default 3): Max simultaneous predictions. Raise with caution — Replicate rate-limits free accounts.

  • download (boolean, default true): Download output files locally.

  • timeout_ms_per_item (default 300000): Per-prediction timeout. Timed-out items have pending=true in their result.

  • ttl_hours (1–72, default 1): How long to keep results in memory. Job state is lost if the MCP server restarts.

Returns: { job_id, total, message }

Example: items=[ { model: "black-forest-labs/flux-schnell", input: { prompt: "a red fox" } }, { model: "black-forest-labs/flux-schnell", input: { prompt: "a blue whale" } }, ] → Returns { job_id: "abc-123", total: 2, message: "..." } → Then poll: replicate_batch_status({ job_id: "abc-123" })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemsYesPredictions to run. 1–50 items.
downloadNoDownload output files locally. Default: true.
ttl_hoursNoHow long to keep job results in memory (1–72h). Default: 1h. State is lost if the server restarts.
concurrencyNoMax simultaneous predictions (1–10). Default: 3.
timeout_ms_per_itemNoPer-prediction timeout in ms (5000–1800000). Default: 300000 (5min).
Behavior5/5

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

Discloses immediate return, background execution, polling mechanism, concurrency behavior, timeout handling, TTL, and state loss on restart. Annotations (readOnlyHint=false, etc.) are consistent and the description adds rich behavioral context.

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?

Well-organized with clear sections (overview, when to use, important note, args, return, example). Each sentence is purposeful. Slightly verbose but efficient for the complexity.

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

Completeness5/5

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

Given 5 parameters, no output schema, and complexity of background jobs, the description covers all key aspects: usage, parameters, return shape, polling instructions, and edge cases (timeout, TTL, server restart). Highly complete.

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

Parameters5/5

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

Schema coverage is 100%, but the description adds significant value: explains items array structure with example, cautions about concurrency rate limits, explains download default, timeout behavior, and TTL meaning. Goes well beyond the schema.

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?

The description explicitly states 'Run multiple Replicate predictions in parallel as a background job' with specific verb and resource. It distinguishes from siblings by mentioning polling replicate_batch_status and contrasting with single prediction tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use: 'when you have 2–50 predictions to run and don't want to block.' Also warns about rate limits and suggests replicate_get_model_schema for correct identifiers.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sena-labs/replicate-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server