MCP Fish Server

fish_list_models

List and filter Fish Audio voices or models by language, author, tag, or title to select voices for text-to-speech tasks.

Instructions

List Fish voices; has_more is boolean for self=true, otherwise possibly null.

Input Schema

Name	Required	Description
`tag`	No	Filter by a single tag.
`self`	No	When true, only list voices created and saved through this platform by the calling account, across its API tokens. This does not restrict public use.
`title`	No	Filter by partial title match.
`sort_by`	No	Sort field; self=true supports created_at and task_count.
`language`	No	Filter by language code (e.g. en, zh).
`author_id`	No	Filter by author id.
`page_size`	No	Number of items per page. Defaults to 10.
`page_number`	No	1-based page number. Defaults to 1.
`title_language`	No	Filter the public voice library by title language; not with self=true.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.1.8Oct 19, 2026

changedInput schema / properties / self / description

Previous value: -"When true, only return models owned by the calling account."New value: +"When true, only list voices created and saved through this platform by the calling account, across its API tokens. This does not restrict public use."

changedInput schema / properties / sort_by / description

Previous value: -"Sort by field accepted by upstream (e.g. created_at, task_count)."New value: +"Sort field; self=true supports created_at and task_count."

changedInput schema / properties / title_language / description

Previous value: -"Filter by title language."New value: +"Filter the public voice library by title language; not with self=true."

Changed2 schema fields changedv0.1.1Aug 21, 2026

addedInput schema / properties / self

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "When true, only return models owned by the calling account.",
+  "title": "Self"
+}

removedInput schema / properties / self_only

Removed value: -{
-  "anyOf": [
-    {
-      "type": "boolean"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "When true, only return models owned by the calling account.",
-  "title": "Self Only"
-}

First observedv0.1.0Aug 1, 2026

TDQS

C2.9/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. It discloses one nuance (has_more is boolean only when self=true, otherwise possibly null), but that is a return-shape detail already implied by the output schema, and it says nothing about pagination limits, auth requirements, or read-only safety.

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 with no filler; the verb+resource leads. It is efficient, though the second clause about has_more reads as an afterthought rather than essential information.

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

Completeness2/5

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

For a 9-parameter listing tool with no annotations and several sibling retrieval tools, the description is too thin: it omits when to use it over fish_get_model and says nothing about the paging behavior that 9 optional filter params imply. The rich schema and output schema offset some of this, but routing guidance is absent.

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 9 parameters, including the self/title_language interaction constraint. The description adds no parameter-level meaning beyond what the schema provides, which makes 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+resource ('List Fish voices'), which is clearer than the ambiguous name 'list_models' and tells the agent this returns a collection of voices. However, it does not distinguish the tool from the sibling fish_get_model (single-voice retrieval) or explain what a 'voice/model' is in this context.

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 statement of when to use this tool versus fish_get_model, nor any prerequisites or exclusions. The only conditional note (has_more semantics under self=true) is about return values, not usage selection, so the agent gets no routing guidance.

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

Deploy Server