# MCP Fish Server

<!-- mcp-name: io.github.AceDataCloud/mcp-fish -->

A Model Context Protocol (MCP) server for Fish Audio TTS (Text-to-Speech) via the AceDataCloud platform.
Generate natural-sounding speech and explore the Fish voice model library.

## Features

- **High-quality TTS**: Generate speech from text via Fish Audio models
- **Voice library**: Browse, search, and fetch metadata for Fish voice models
- **Asynchronous tasks**: Submit generation tasks and poll for results
- **Batch task lookup**: Query multiple task results in one call

### One-shot voice cloning

Pass one public HTTPS reference audio URL plus its exact transcript. This conditions only the current TTS request and does not create a reusable voice model:

```python
fish_generate_audio(
    text="New speech in the referenced voice",
    reference_audio_url="https://cdn.acedata.cloud/reference.mp3",
    reference_text="The exact words spoken in the reference audio",
)
```

Use `reference_id` for saved or public voices, and the one-shot reference fields for a temporary voice. Do not combine them. Reference audio supports MP3/WAV and should be 10–270 seconds. Billing remains based on the target text's UTF-8 byte count.

### Find saved voices

Call `fish_list_models` with `self=true` to list voices created and saved through
AceDataCloud by the calling account, including those created with its other API
tokens. This is a list filter, not a privacy setting: saved voices are public and
may be searched and used by others. The voice-creation API's `visibility` input
does not make them private or unlisted; this MCP does not expose voice creation.

Use `page_size` and the 1-based `page_number` for pagination. With `self=true`,
`sort_by` supports `created_at` and `task_count`, and `author_id` further filters
those saved voices. `title_language` is only supported for public library queries,
not with `self=true`. The returned `has_more` is a boolean for account-created
voices but may be `null` for public library queries; use `total` and `page_size`
for pagination in that case. Pass a returned voice ID as `reference_id` to
`fish_generate_audio`.

## Connect: hosted OAuth, API token, or local stdio

The hosted endpoint is `https://fish.mcp.acedata.cloud/mcp`. Choose one route for the MCP client:

| Route | When to use it | Credential setup |
|---|---|---|
| Hosted OAuth | The client supports remote MCP OAuth | Add only the URL, then sign in to AceDataCloud and approve access. No token needs to be pasted into client configuration. |
| Hosted API token | The client cannot finish OAuth, or you need an explicit integration credential | Send an AceDataCloud API token in the `Authorization: Bearer …` header. Keep it in a local secret store or environment variable. |
| Local stdio | The client runs a local MCP process | Install `mcp-fish` and pass `ACEDATACLOUD_API_TOKEN` to that process. It still calls the AceDataCloud API. |

The hosted service advertises OAuth metadata and Dynamic Client Registration (DCR). **DCR registers the client application; it is not an API key.** OAuth signs you in and the client sends the resulting Bearer token; it may reuse or create an API credential for the account. Browser sign-in still requires an AceDataCloud account. The hosted service can be metered: review [current service documentation](https://platform.acedata.cloud/documents/fish?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=fish_mcp_readme_quick_start) and displayed pricing before a real operation. Do not configure both an OAuth login and a fixed `Authorization` header for the same server.

### Hosted OAuth examples

- **Claude and Claude Desktop chat:** Add a remote custom connector in `Customize → Connectors → Add custom connector`, enter `https://fish.mcp.acedata.cloud/mcp`, select sign-in, and choose **Register automatically** if Claude asks how to register its OAuth client. Complete consent. Claude Desktop's local `claude_desktop_config.json` is a separate setup. [Claude connector guide](https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp).
- **Claude Code:** `claude mcp add --transport http --scope user fish https://fish.mcp.acedata.cloud/mcp`, then `claude mcp login fish`. Check `/mcp`. [Claude Code MCP guide](https://code.claude.com/docs/en/mcp).
- **Cursor:** Add a remote server with only `https://fish.mcp.acedata.cloud/mcp`. For a project, merge the entry below into `<project>/.cursor/mcp.json`; for personal use, use `~/.cursor/mcp.json`. [Cursor MCP guide](https://cursor.com/docs/mcp).
- **VS Code / Copilot:** Run **MCP: Add Server**, select HTTP, enter `https://fish.mcp.acedata.cloud/mcp`, then finish the browser sign-in. New portable workspace configs use `<project>/.mcp.json`; the VS Code-specific format below uses `<project>/.vscode/mcp.json` or the user profile. Check **MCP: List Servers**. [VS Code MCP setup](https://code.visualstudio.com/docs/agent-customization/mcp-servers).
- **Codex:** `codex mcp add fish --url https://fish.mcp.acedata.cloud/mcp`, then `codex mcp login fish`. Its user settings are in `~/.codex/config.toml`. [Official Codex MCP guide](https://developers.openai.com/codex/mcp/).

Cursor project config (OAuth):

```json
{
  "mcpServers": {
    "fish": {"url": "https://fish.mcp.acedata.cloud/mcp"}
  }
}
```

VS Code-specific workspace config (OAuth):

```json
{
  "servers": {
    "fish": {"type": "http", "url": "https://fish.mcp.acedata.cloud/mcp"}
  }
}
```

### Hosted API token

<!-- BEGIN TOKEN ONBOARDING -->
1. Open [Ace Data Cloud → Applications](https://platform.acedata.cloud/console/applications?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=fish_mcp_readme_api_key). Sign in, or register an account first.
2. Find **General application**. If it has not been created, choose **Initialize General Application**. A general key can use the services available to your account; a dedicated application's key is limited to its service. Check the required service/model access and [current pricing](https://platform.acedata.cloud/models?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=fish_mcp_readme_models).
3. Copy the **API Key** from the application card, or open **Keys / Manage Keys → Create** to create a separate key for this integration. Give it a recognizable name so you can revoke or rotate it independently.
4. When creating a key, review **Expiration Time**, **Set Usage Limitation**, and **Allowed APIs**. Enable only the restrictions you need, allow the operations you will call, then click **Create** and copy the token from the key list. Task lookup does not grant permission to submit a generation. Confirm the application's balance can cover your first request; any trial allowance is whatever your account currently displays.
5. Copy only the token value, without quotation marks, spaces, or `Bearer `. An API Key / API Token field expects this raw value; only a manually configured HTTP `Authorization` header needs the `Bearer ` prefix. A `platform-...` account-management token cannot replace a generation API key.

![Copy an application API key or open Manage Keys](https://raw.githubusercontent.com/AceDataCloud/NanoBananaDify/2522b2f57210597af2db866445319334a1677a23/_assets/tutorial/get-api-key-en.png)

![Create a separately named key with optional restrictions](https://raw.githubusercontent.com/AceDataCloud/NanoBananaDify/2522b2f57210597af2db866445319334a1677a23/_assets/tutorial/create-api-key-en.png)

Save the key in the client's credential store or the environment variable shown below. Never put it in a prompt, shared workflow, screenshot, or Git commit. If authentication fails, check the full copied value, application/service access, expiration, usage limit, and balance before creating another key.
<!-- END TOKEN ONBOARDING -->

A fixed Bearer header bypasses OAuth. If the header is invalid, remove it before trying browser sign-in; keep the saved credential private.

For Claude Code, the shell expands the token when you add the server; treat the saved user MCP config as a secret:

```bash
export ACEDATACLOUD_API_TOKEN='YOUR_API_TOKEN'
claude mcp add --transport http --scope user fish https://fish.mcp.acedata.cloud/mcp \
  --header "Authorization: Bearer $ACEDATACLOUD_API_TOKEN"
```

For a Claude Code project config, put a variable reference in `<project>/.mcp.json` and set that variable in the environment that launches Claude Code:

```json
{
  "mcpServers": {
    "fish": {
      "type": "http",
      "url": "https://fish.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${ACEDATACLOUD_API_TOKEN}"}
    }
  }
}
```

Cursor uses a different environment-variable syntax in `~/.cursor/mcp.json` or an uncommitted project config:

```json
{
  "mcpServers": {
    "fish": {
      "url": "https://fish.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${env:ACEDATACLOUD_API_TOKEN}"}
    }
  }
}
```

In VS Code, run **MCP: Open User Configuration** and merge this server plus its masked input; `${input:...}` is for VS Code's user/workspace format and is not portable to the Agent Host `.mcp.json` format:

```json
{
  "inputs": [
    {"id": "acedata-fish-token", "type": "promptString", "description": "AceDataCloud API token", "password": true}
  ],
  "servers": {
    "fish": {
      "type": "http",
      "url": "https://fish.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${input:acedata-fish-token}"}
    }
  }
}
```

For **Cline**, use its MCP configuration UI or CLI file `~/.cline/data/settings/cline_mcp_settings.json`; its remote transport value is `streamableHttp`. For **JetBrains AI Assistant**, add a remote URL from **Settings → Tools → AI Assistant → Model Context Protocol (MCP)**. For **Zed**, use a `context_servers` entry with the URL only for OAuth or add a local Bearer header. These clients have different configuration schemas; follow their current UI rather than copying another client's JSON. [Cline](https://docs.cline.bot/mcp/mcp-overview) · [JetBrains](https://www.jetbrains.com/help/ai-assistant/mcp.html) · [Zed](https://zed.dev/docs/ai/mcp).

### Local stdio

Install the package and give the local process an API token:

```bash
python -m pip install mcp-fish
export ACEDATACLOUD_API_TOKEN='YOUR_API_TOKEN'
mcp-fish
```

For Claude Desktop local MCP, merge this entry into the file opened by its developer settings (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS). `uvx` requires [uv](https://docs.astral.sh/uv/) on `PATH`:

```json
{
  "mcpServers": {
    "fish": {
      "command": "uvx",
      "args": ["mcp-fish"],
      "env": {"ACEDATACLOUD_API_TOKEN": "YOUR_API_TOKEN"}
    }
  }
}
```

Keep this user-level file private. Self-hosted HTTP uses `mcp-fish --transport http --port 8000`; expose it only with suitable network and TLS controls. Local execution still calls the AceDataCloud API.

### Check before using the service

1. `https://fish.mcp.acedata.cloud/health` returning `{"status":"ok"}` checks endpoint reachability only.
2. Confirm that the MCP client loads tools. `fish_get_usage_guide` is a reference tool; it does not verify downstream API access or balance.
3. If you need a full API check, call `fish_generate_audio` with your own valid input after reviewing [current service documentation](https://platform.acedata.cloud/documents/fish?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=fish_mcp_readme_quick_start) and displayed pricing. If the result contains a task ID, call `fish_get_task` on that same ID until terminal success or failure. Do not resubmit the operation just to check progress.

For **401**, check which auth route the client used and whether the token or OAuth session is valid. A **403** may mean an account permission or content moderation failure; read the returned error. Insufficient balance and downstream service failures need their own diagnosis. A listed tool or submitted task does not prove a successful result.

## Tool Reference

| Tool | Description |
|------|-------------|
| `fish_generate_audio` | Generate speech from text via a Fish voice model |
| `fish_list_models` | List available Fish voice models |
| `fish_get_model` | Fetch metadata for a specific Fish voice model |
| `fish_get_task` | Get the status / result of a generation task |
| `fish_get_tasks_batch` | Batch-fetch the status / result of multiple tasks |
| `fish_get_usage_guide` | Get the API usage guide |

## Documentation

<!-- canonical-documentation -->
[Documentation](https://platform.acedata.cloud/documents/fish?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=fish_mcp_readme_quick_start)

## License

MIT — see [LICENSE](../LICENSE) at the repository root.