KeyShot MCP

by truman-t3

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

Apply a KeyShot material

keyshot_apply_material

Destructive

Apply a KeyShot library or local material to a specific scene object, then save the edited scene to a new file.

Instructions

Apply a KeyShot library material or local material file to a specific object, then save the edited scene.

Input Schema

TableJSON Schema

Name	Required	Description
`scenePath`	Yes	Absolute path to an existing KeyShot scene file to open. Input files may be outside the configured output directory.
`objectName`	No	Scene object name to modify. Provide either objectName or the more specific objectPath.
`objectPath`	No	Full scene-tree path of the object to modify. Use this instead of objectName when names are duplicated.
`materialName`	No	Material name from the local KeyShot library. Provide either materialName or materialPath.
`materialPath`	No	Absolute path to a local KeyShot material file. Provide either materialPath or materialName.
`outputScenePath`	Yes	Destination path for the saved KeyShot scene. The path must stay inside KEYSHOT_OUTPUT_DIR unless external outputs are explicitly enabled.

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.

Changed4 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
```

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"
+]

Changed7 schema fields changedv0.10.0Aug 11, 2026

addedInput schema / properties / materialName / description

Added value: +"Material name from the local KeyShot library. Provide either materialName or materialPath."

addedInput schema / properties / materialPath / description

Added value: +"Absolute path to a local KeyShot material file. Provide either materialPath or materialName."

addedInput schema / properties / objectName / description

Added value: +"Scene object name to modify. Provide either objectName or the more specific objectPath."

addedInput schema / properties / objectPath / description

Added value: +"Full scene-tree path of the object to modify. Use this instead of objectName when names are duplicated."

addedInput schema / properties / outputScenePath / description

Added value: +"Destination path for the saved KeyShot scene. The path must stay inside KEYSHOT_OUTPUT_DIR unless external outputs are explicitly enabled."

addedInput schema / properties / scenePath / description

Added value: +"Absolute path to an existing KeyShot scene file to open. Input files may be outside the configured output directory."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "data": {
+      "anyOf": [
+        {},
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Operation-specific structured result data, or null when unavailable."
+    },
+    "error": {
+      "description": "Human-readable failure reason, or null after success.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "errorCode": {
+      "description": "Stable error category for common failures.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "keyshotStdoutTail": {
+      "description": "Truncated tail of KeyShot headless output for diagnostics.",
+      "type": "string"
+    },
+    "ok": {
+      "description": "True when the requested operation completed successfully.",
+      "type": "boolean"
+    },
+    "outputFiles": {
+      "description": "Absolute paths of images or scene files created by the operation.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "suggestions": {
+      "description": "Actionable recovery steps for the user or agent.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "warnings": {
+      "description": "Non-fatal conditions the user or agent should review.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "ok",
+    "outputFiles",
+    "warnings",
+    "keyshotStdoutTail",
+    "error"
+  ],
+  "type": "object"
+}

First observedv0.2.1Jul 9, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already declare a destructive, non-readonly write. The description adds that the tool automatically saves the edited scene, which is useful workflow context beyond the annotations. It still omits details such as overwrite behavior, authentication needs, or rate limits.

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?

The description is a single efficient sentence that front-loads the action and outcome. There is no filler or redundant restatement.

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?

With a rich input schema, annotations, and an output schema, the description is complete enough to convey the core mutation workflow. The only notable gap is usage routing to the sibling preset-based tool.

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 all six parameters are fully documented in the input schema. The description adds no syntax, format, or constraint detail beyond what the schema already provides, making the baseline 3 appropriate.

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 ('apply') and resource ('KeyShot library material or local material file') on a specific object, plus a save step. It is clear, but it does not explicitly distinguish itself from the sibling keyshot_apply_material_preset, so it falls short of full sibling differentiation.

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?

The description only says what the tool does; it gives no when-to-use guidance, no exclusions, and does not name keyshot_apply_material_preset or other alternatives. The agent must infer the routing conditions from the schema.

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