KeyShot MCP

Overview Schema Source Related Servers Discussions Admin

Prepare and render a product

keyshot_product_render

Destructive

Run a complete headless product render workflow: import or open a model, assign materials, set camera and environment, save the scene, and render one or all cameras.

Instructions

Run a complete product workflow in one headless process: open or import, assign materials, configure camera and environment, save a scene copy, and render one or all cameras.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`up`	No	Optional camera up direction [x, y, z]. Requires position and lookAt.
`width`	No	Render width in pixels. Overrides the selected quality preset when provided.
`format`	No	Output image format. Defaults to PNG when omitted.
`height`	No	Render height in pixels. Overrides the selected quality preset when provided.
`lookAt`	No	Camera target [x, y, z]. Must be provided together with position.
`samples`	No	Maximum render samples. Cannot be combined with maxTimeSeconds and overrides preset sampling when provided.
`distance`	No	Positive KeyShot camera distance applied after the transform or preset.
`position`	No	Camera position [x, y, z]. Must be provided together with lookAt.
`rotation`	No	Environment rotation in degrees, from 0 inclusive to 360 exclusive.
`modelPath`	No	Absolute path to a model to import. Provide exactly one modelPath or scenePath.
`outputDir`	No	All-cameras output directory. Invalid with single mode; a safe directory is generated when omitted.
`overwrite`	No	Allow replacement of explicitly selected output files. Defaults to false.
`scenePath`	No	Absolute path to an existing KeyShot scene. Provide exactly one scenePath or modelPath.
`brightness`	No	Positive brightness multiplier for the active environment.
`cameraName`	No	Camera to create, update, or activate. New model workflows default to Product Hero.
`outputPath`	No	Single-mode image destination. Invalid with allCameras mode; a safe name is generated when omitted.
`renderMode`	No	Render one active or named camera, or discover and render every saved camera. Defaults to single.	single
`fieldOfView`	No	Camera field of view in degrees, greater than 0 and less than 180. Cannot be combined with focalLength.
`focalLength`	No	Camera focal length from 5 to 200 mm. Cannot be combined with fieldOfView.
`snapToGround`	No	Place imported geometry on the ground. Applies only to modelPath sources and defaults to true for new models.
`baseScenePath`	No	Optional KeyShot base scene used only when modelPath is provided.
`qualityPreset`	No	Render quality preset: preview (960x540, 16 samples), standard (1920x1080, 64 samples), or final (3840x2160, 256 samples).
`centerGeometry`	No	Center imported geometry. Applies only to modelPath sources and defaults to true for new models.
`maxTimeSeconds`	No	Maximum render time in seconds. Selects time-based rendering and cannot be combined with samples.
`continueOnError`	No	In allCameras mode, continue after one camera fails. Defaults to true.
`environmentName`	No	Environment name from the KeyShot library. Cannot be combined with environmentPath.
`environmentPath`	No	Absolute path to a local KeyShot environment file. Cannot be combined with environmentName.
`outputScenePath`	No	Destination for the prepared scene. A safe numbered name is generated when omitted.
`cameraPresetName`	No	Configured camera preset to apply. Cannot be combined with a custom position/lookAt pair.
`adjustEnvironment`	No	Adjust the environment after model import. Applies only to modelPath sources and defaults to true for new models.
`adjustCameraLookAt`	No	Retarget the camera after model import. Applies only to modelPath sources and defaults to true for new models.
`materialAssignments`	No	Object-specific material changes applied before camera and environment setup.

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes	True when the requested operation completed successfully.
`data`	Yes	Operation-specific structured result data, or null when unavailable.
`error`	Yes	Human-readable failure reason, or null after success.
`warnings`	Yes	Non-fatal conditions the user or agent should review.
`errorCode`	No	Stable error category for common failures.
`outputFiles`	Yes	Absolute paths of images or scene files created by the operation.
`suggestions`	No	Actionable recovery steps for the user or agent.
`keyshotStdoutTail`	Yes	Truncated tail of KeyShot headless output for diagnostics.

Schema Changelog

Changes observed during successful MCP inspections.

Changed14 schema fields changedv0.13.0Sep 30, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

removedInput schema / additionalProperties
```
Removed value: -false
```
addedInput schema / properties / height / maximum
```
Added value: +9007199254740991
```

changedInput schema / properties / lookAt / items

Previous value: -[
-  {
-    "$ref": "#/properties/position/items/0"
-  },
-  {
-    "$ref": "#/properties/position/items/1"
-  },
-  {
-    "$ref": "#/properties/position/items/2"
-  }
-]New value: +false

addedInput schema / properties / lookAt / prefixItems

Added value: +[
+  {
+    "type": "number"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "number"
+  }
+]

removedInput schema / properties / materialAssignments / items / additionalProperties
```
Removed value: -false
```

changedInput schema / properties / position / items

Previous value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "number"
-  },
-  {
-    "type": "number"
-  }
-]New value: +false

addedInput schema / properties / position / prefixItems

Added value: +[
+  {
+    "type": "number"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "number"
+  }
+]

addedInput schema / properties / samples / maximum
```
Added value: +9007199254740991
```

changedInput schema / properties / up / items

Previous value: -[
-  {
-    "$ref": "#/properties/position/items/0"
-  },
-  {
-    "$ref": "#/properties/position/items/1"
-  },
-  {
-    "$ref": "#/properties/position/items/2"
-  }
-]New value: +false

addedInput schema / properties / up / prefixItems

Added value: +[
+  {
+    "type": "number"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "number"
+  }
+]

addedInput schema / properties / width / maximum
```
Added value: +9007199254740991
```

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedOutput schema / required

Previous value: -[
-  "ok",
-  "outputFiles",
-  "warnings",
-  "keyshotStdoutTail",
-  "error"
-]New value: +[
+  "ok",
+  "data",
+  "outputFiles",
+  "warnings",
+  "keyshotStdoutTail",
+  "error"
+]

Addedv0.10.0Aug 11, 2026

TDQS

C2.9/5.0

Behavior2/5

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

Annotations declare destructiveHint=true and idempotentHint=false, but the description never discloses the destructive side effects (overwriting output/scene files), the overwrite=false default behavior, or that this is a long-running headless render process. With zero annotation-adjacent context, the burden falls fully on the description, which omits the risk profile and runtime expectations.

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?

A single front-loaded sentence listing the workflow stages in order. It is efficient and does not pad, though the keyword-less phrasing gives the agent little to filter on when scanning tools.

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

Completeness3/5

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

For a 32-parameter destructive orchestration tool, the description is minimal. An output schema exists, so return values need not be explained, but the description omits the destructive behavior, the relationship to granular siblings, and the practical implication of overwrite/output path generation.

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 32 parameters is already documented in the schema, including mutually exclusive constraints (scenePath/modelPath, samples/maxTimeSeconds, environmentName/environmentPath). The description adds only the high-level stage ordering, not per-parameter semantics, so it sits at the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Run a complete product workflow... render one or all cameras') and enumerates the pipeline stages. However, it does not differentiate from siblings like keyshot_render, keyshot_import_model, or keyshot_apply_material, which it subsumes, leaving the agent unsure why to pick this orchestration tool over the granular ones.

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

Usage Guidelines2/5

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

No when-to-use or when-not-to-use guidance is given. The description does not mention that this bundles the workflow of the sibling tools, nor when a caller should prefer the single-purpose tools (import, material, camera, render) instead. The agent must infer selection purely from the name.

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