Lara Translate MCP Server

create_memory

Create a named translation memory in Lara Translate to store source-target segment pairs for reuse, optionally importing from MyMemory.

Instructions

Create a translation memory with a custom name in your Lara Translate account. Translation memories store pairs of source and target text segments (translation units) for reuse in future translations.

Input Schema

Name	Required	Description	Default
`name`	Yes	The name of the new memory, it should be short and generic, like 'catch_phrases' or 'brand_names'
`external_id`	No	The ID of the memory to be imported from MyMemory. Use this to initialize the memory with external content. Format: ext_my_[MyMemory ID]

Output Schema

Name	Required	Description
`id`	Yes	Unique memory identifier (format: mem_*)
`name`	Yes	Display name of the memory
`secret`	No	Memory secret, if any
`ownerId`	No	Identifier of the memory owner
`sharedAt`	No
`createdAt`	No
`updatedAt`	No
`externalId`	No	External identifier (e.g. MyMemory ID) when imported
`isPersonal`	No	True if the memory is private to the owner. Omitted for some account types (e.g. team plans).
`collaboratorsCount`	No	Number of collaborators with access to the memory

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedv2.1.0Oct 15, 2026

addedOutput schema / properties / externalId / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / externalId / type
```
Removed value: -[
-  "string",
-  "null"
-]
```

addedOutput schema / properties / isPersonal / anyOf

Added value: +[
+  {
+    "type": "boolean"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / isPersonal / type
```
Removed value: -[
-  "boolean",
-  "null"
-]
```

addedOutput schema / properties / ownerId / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / ownerId / type
```
Removed value: -[
-  "string",
-  "null"
-]
```

addedOutput schema / properties / secret / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / secret / type
```
Removed value: -[
-  "string",
-  "null"
-]
```

Changed19 schema fields changedv2.0.1Oct 13, 2026

addedOutput schema / properties / collaboratorsCount / anyOf

Added value: +[
+  {
+    "maximum": 9007199254740991,
+    "minimum": -9007199254740991,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / collaboratorsCount / maximum
```
Removed value: -9007199254740991
```
removedOutput schema / properties / collaboratorsCount / minimum
```
Removed value: --9007199254740991
```
removedOutput schema / properties / collaboratorsCount / type
```
Removed value: -"integer"
```

addedOutput schema / properties / createdAt / anyOf

Added value: +[
+  {
+    "description": "ISO 8601 timestamp",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / createdAt / description
```
Removed value: -"ISO 8601 timestamp"
```
removedOutput schema / properties / createdAt / type
```
Removed value: -"string"
```

changedOutput schema / properties / externalId / type

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

changedOutput schema / properties / isPersonal / description

Previous value: -"True if the memory is private to the owner"New value: +"True if the memory is private to the owner. Omitted for some account types (e.g. team plans)."

changedOutput schema / properties / isPersonal / type

Previous value: -"boolean"New value: +[
+  "boolean",
+  "null"
+]

changedOutput schema / properties / ownerId / type

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

changedOutput schema / properties / secret / type

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

addedOutput schema / properties / sharedAt / anyOf

Added value: +[
+  {
+    "description": "ISO 8601 timestamp",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / sharedAt / description
```
Removed value: -"ISO 8601 timestamp"
```
removedOutput schema / properties / sharedAt / type
```
Removed value: -"string"
```

addedOutput schema / properties / updatedAt / anyOf

Added value: +[
+  {
+    "description": "ISO 8601 timestamp",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / updatedAt / description
```
Removed value: -"ISO 8601 timestamp"
```
removedOutput schema / properties / updatedAt / type
```
Removed value: -"string"
```

changedOutput schema / required

Previous value: -[
-  "id",
-  "createdAt",
-  "updatedAt",
-  "sharedAt",
-  "name",
-  "ownerId",
-  "collaboratorsCount",
-  "isPersonal"
-]New value: +[
+  "id",
+  "name"
+]

Changed2 schema fields changedv2.0.0Sep 29, 2026
- addedInput schema / properties / name / description
```
Added value: +"The name of the new memory, it should be short and generic, like 'catch_phrases' or 'brand_names'"
```
- removedOutput schema / additionalProperties
```
Removed value: -{}
```

Changed1 schema field changedv1.0.4May 29, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "properties": {
+    "collaboratorsCount": {
+      "description": "Number of collaborators with access to the memory",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "createdAt": {
+      "description": "ISO 8601 timestamp",
+      "type": "string"
+    },
+    "externalId": {
+      "description": "External identifier (e.g. MyMemory ID) when imported",
+      "type": "string"
+    },
+    "id": {
+      "description": "Unique memory identifier (format: mem_*)",
+      "type": "string"
+    },
+    "isPersonal": {
+      "description": "True if the memory is private to the owner",
+      "type": "boolean"
+    },
+    "name": {
+      "description": "Display name of the memory",
+      "type": "string"
+    },
+    "ownerId": {
+      "description": "Identifier of the memory owner",
+      "type": "string"
+    },
+    "secret": {
+      "description": "Memory secret, if any",
+      "type": "string"
+    },
+    "sharedAt": {
+      "description": "ISO 8601 timestamp",
+      "type": "string"
+    },
+    "updatedAt": {
+      "description": "ISO 8601 timestamp",
+      "type": "string"
+    }
+  },
+  "required": [
+    "id",
+    "createdAt",
+    "updatedAt",
+    "sharedAt",
+    "name",
+    "ownerId",
+    "collaboratorsCount",
+    "isPersonal"
+  ],
+  "type": "object"
+}

Addedv1.0.0Jan 2, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds useful domain context about what a memory stores, but says nothing about side effects, whether external_id triggers an import, or whether duplicate names are allowed.

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?

Two sentences, front-loaded with the action and followed by a compact definition of the resource. The second sentence is explanatory rather than procedural, but it is short and aids understanding of the created object, so it largely earns its place.

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?

The tool is simple (one required, one optional parameter), an output schema exists so return values need no explanation, and annotations cover the safety profile. The only real omission is that the description does not surface the import-via-external_id behavior, which is left to the schema.

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 both parameters are fully documented in the schema, including the ext_my_ format for external_id. The description adds only the loose notion of a 'custom name' and no syntax or format detail beyond the schema, so the baseline 3 applies.

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?

The description names a specific verb and resource (create a translation memory) and defines what a translation memory contains, which separates it from the glossary siblings conceptually. It does not explicitly call out the boundary against create_glossary or import_tmx, so sibling differentiation is implicit rather than stated.

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?

There is no when-to-use guidance, no mention of prerequisites or account/permission requirements, and no routing to alternatives such as create_glossary (for term-level data) or import_tmx (for bulk-loading units). The agent must infer the appropriate context from the name alone.

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