Skip to main content
Glama
amanharshx

ultralytics-mcp

by amanharshx
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

export_create

Create a model export job for a project or model with a format and optional settings. Requires confirm_cost=true; format validates upfront, but compatibility failures show only after the job runs.

Instructions

Create a model export job by owner/project/model, ul://owner/project/model, or slug with a project (state-changing, may cost credits). The format is validated immediately by the server; task and architecture compatibility is only known when the job runs, so a queued export can still fail. Use export_status and exports_list for the real outcome. Requires confirm_cost=true.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
imgszNoImage size for export.
modelYesModel ref by owner/project/model, ul:// URI, or slug (requires project).
formatYesRequested export format (validated by the server).
dynamicNoDynamic input shapes.
projectNoProject ref required when model is given by slug.
gpu_typeNoGPU type required for TensorRT engine exports.
quantizeNoExport precision. Server-validated; for example 16 or "fp16" for FP16, 8 or "int8" for INT8. Omit to let the exporter choose.
confirm_costNoMust be true to allow a credit-costing export job.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.15
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / half
      Removed value: -{
-  "description": "Legacy FP16 export precision flag.",
-  "type": "boolean"
-}
    • addedInput schema / properties / quantize
      Added value: +{
+  "description": "Export precision. Server-validated; for example 16 or \"fp16\" for FP16, 8 or \"int8\" for INT8. Omit to let the exporter choose.",
+  "type": [
+    "number",
+    "string"
+  ]
+}
  2. Changed3 schema fields changedv0.1.13
    • addedInput schema / properties / dynamic / description
      Added value: +"Dynamic input shapes."
    • addedInput schema / properties / half / description
      Added value: +"Legacy FP16 export precision flag."
    • addedInput schema / properties / imgsz / description
      Added value: +"Image size for export."
  3. Changed4 schema fields changedv0.1.12
    • changedInput schema / properties / format / description
      Previous value: -"Requested export format."New value: +"Requested export format (validated by the server)."
    • addedInput schema / properties / gpu_type / description
      Added value: +"GPU type required for TensorRT engine exports."
    • changedInput schema / properties / model / description
      Previous value: -"Model id, or slug when project is also provided."New value: +"Model ref by owner/project/model, ul:// URI, or slug (requires project)."
    • addedInput schema / properties / project / description
      Added value: +"Project ref required when model is given by slug."
  4. Changed3 schema fields changedv0.1.6
    • addedInput schema / properties / confirm_cost / description
      Added value: +"Must be true to allow a credit-costing export job."
    • addedInput schema / properties / format / description
      Added value: +"Requested export format."
    • addedInput schema / properties / model / description
      Added value: +"Model id, or slug when project is also provided."
  5. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only cover the generic profile (not read-only, not idempotent, open-world, non-destructive). The description adds the substantive traits: it is state-changing, it may consume credits, format validation is synchronous while task/architecture compatibility is only determined at run time, and a queued job can still fail. This is exactly the kind of context annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compact sentences, with the effect ('state-changing, may cost credits') front-loaded in the first, followed by the failure-mode caveat and the routing pointer. Every sentence carries distinct, non-redundant information.

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?

With no output schema, the description compensates by redirecting the agent to export_status and exports_list for real results, and it discloses the asynchronous failure semantics an agent needs to set expectations. Nothing essential for calling this tool correctly appears to be missing.

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 every one of the eight parameters is already documented in the schema itself, including the model ref forms, project requirement for slugs, gpu_type for TensorRT, and quantize examples. The description's mention of the model reference forms and confirm_cost=true largely restates schema content, so the baseline 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?

The description states a specific verb and resource ('Create a model export job') and enumerates the accepted model reference forms (owner/project/model, ul:// URI, or slug plus project). It is immediately distinguishable from siblings export_status and exports_list, which are explicitly referenced as the outcome-checking path.

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?

It gives clear conditions: use this to create an export job, then use export_status and exports_list for the real outcome, and confirm_cost=true is required. It also warns that success at creation does not imply success at runtime. It stops short of an explicit exclusion against the closely related sibling dataset_export, so a 4 rather than 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