@aiwerk/mcp-server-elevenlabs

get_user_voices_v2

Read-onlyIdempotent

Retrieve and filter voices from your ElevenLabs workspace by language, accent, gender, category, or use case, with sorting and pagination.

Instructions

Get Voices V2

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_user_voices_v2"
  }
}

Input Schema

Name	Required	Description
`age`	No	Age used for filtering, based on the voice's 'age' label.
`sort`	No	Which field to sort by, one of 'created_at_unix' or 'name'. 'created_at_unix' may not be available for older voices.
`accent`	No	Accent used for filtering, based on the voice's 'accent' label.
`gender`	No	Gender used for filtering, based on the voice's 'gender' label.
`search`	No	Search term to filter voices by. Searches in name, description, labels, category.
`category`	No	Category of the voice to filter by. One of 'premade', 'cloned', 'generated', 'professional'
`language`	No	Languages used for filtering, based on the voice's 'language' label. Voices matching any of the given languages are returned.
`page_size`	No	How many voices to return at maximum. Can not exceed 100, defaults to 10. Page 0 may include more voices due to default voices being included.
`use_cases`	No	Use cases used for filtering, based on the voice's 'use_case' label. Voices matching any of the given use cases are returned.
`voice_ids`	No	Voice IDs to lookup by. Maximum 100 voice IDs.
`voice_type`	No	Type of the voice to filter by. One of 'personal', 'community', 'default', 'workspace', 'non-default', 'non-community', 'saved'. 'non-default' is equal to all but 'default'. 'non-community' is equal to 'personal' and 'workspace' combined (excludes library copies). 'saved' is equal to non-default, bu
`high_quality`	No	When true, only return studio-quality voices (those whose category is 'high_quality').
`collection_id`	No	Collection ID to filter voices by.
`sort_direction`	No	Which direction to sort the voices in. 'asc' or 'desc'.
`next_page_token`	No	The next page token to use for pagination. Returned from the previous request. Use this in combination with the has_more flag for reliable pagination.
`fine_tuning_state`	No	State of the voice's fine tuning to filter by. Applicable only to professional voices clones. One of 'draft', 'not_verified', 'not_started', 'queued', 'fine_tuning', 'fine_tuned', 'failed', 'delayed'
`include_total_count`	No	Whether to include the total count of voices found in the response. NOTE: The total_count value is a live snapshot and may change between requests as users create, modify, or delete voices. For pagination, rely on the has_more flag instead. Only enable this when you actually need the total count (e.
`include_custom_rates`	No	Whether to include voices that have a custom sharing rate. Defaults to including them.
`include_live_moderated`	No	Whether to include voices that have live moderation enabled. Defaults to including them.
`min_notice_period_days`	No	Filter to voices whose sharing notice period is at least the given number of days.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 13, 2026

TDQS

D1.6/5.0

Behavior2/5

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

Annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety and read-only nature is covered. However, the description adds no behavioral context such as pagination quirks, default inclusions, or differences from V1, which is a significant gap for a tool with 20 parameters and no output schema.

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

Conciseness2/5

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

The description is only three words and lacks any structure or front-loading of key information. It is not overly verbose, but it is severely under-specified for a tool of this complexity.

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

Completeness1/5

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

Given that the tool has 20 parameters, complex filtering options, and no output schema, the description is completely inadequate. It provides no information about return values, pagination, default behaviors, or distinctions from similar tools, leaving the agent to rely entirely on the schema and annotations.

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 the schema already documents all 20 parameters in detail. The description adds no parameter meaning beyond what the schema provides, so the baseline score of 3 is appropriate.

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

Purpose1/5

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

The description 'Get Voices V2' is a tautology that merely restates the tool name. It does not specify a verb or resource meaning beyond the name, and it does not distinguish this tool from siblings like get_voices, get_library_voices, or get_voice_by_id.

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

Usage Guidelines1/5

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

There is no guidance on when to use this tool versus alternatives such as get_voices or get_library_voices. The agent must infer usage from the name alone, which is insufficient given the large number of voice-related siblings.

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

Deploy Server