# AvatarSay — Fictional Character, RPG NPC & Talking Video MCP (remote · avatarsay.com)

Roll RPG NPCs (Foundry VTT & SillyTavern V2), import stylized art, MP3 barks & talking MP4s.

- Trust score: 74/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `avatarsay.com`: 74/100 (this document), [markdown](https://verifymcp.io/servers/fourgit-avatarsay-mcp/avatarsay.md), [page](https://verifymcp.io/servers/fourgit-avatarsay-mcp/avatarsay)
- npm · `avatarsay-mcp`: 39/100, [markdown](https://verifymcp.io/servers/fourgit-avatarsay-mcp/avatarsay-mcp.md), [page](https://verifymcp.io/servers/fourgit-avatarsay-mcp/avatarsay-mcp)

## Channel facts

- Endpoint: `https://avatarsay.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.2.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2492 tokens (~226/item across 11 items; 10 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the AvatarSay — Fictional Character, RPG NPC & Talking Video MCP server?

AvatarSay — Fictional Character, RPG NPC & Talking Video MCP is a hosted endpoint at https://avatarsay.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http fourgit-avatarsay-mcp 'https://avatarsay.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "fourgit-avatarsay-mcp": {
      "url": "https://avatarsay.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "fourgit-avatarsay-mcp": {
      "type": "http",
      "url": "https://avatarsay.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.fourgit-avatarsay-mcp]
url = "https://avatarsay.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fourgit-avatarsay-mcp": {
      "type": "remote",
      "url": "https://avatarsay.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add fourgit-avatarsay-mcp --url 'https://avatarsay.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  fourgit-avatarsay-mcp:
    url: "https://avatarsay.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "fourgit-avatarsay-mcp": {
      "Transport": "http",
      "Url": "https://avatarsay.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add fourgit-avatarsay-mcp -t streamable-http -u 'https://avatarsay.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "fourgit-avatarsay-mcp": {
      "type": "http",
      "url": "https://avatarsay.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 74, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “list_videos” rewrote its description, which is the text the model reads
- [security] Tool “generate_avatars” rewrote its description, which is the text the model reads
- [security] Tool “create_talking_video” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 204 → 226
- [cosmetic] “create_talking_video” added an optional parameter “qualityMode”
- [cosmetic] “generate_avatars” added an optional parameter “aspectRatio”

### 2026-11-20 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 73, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “list_voices_and_styles” rewrote its description, which is the text the model reads
- [security] Tool “create_talking_video” rewrote its description, which is the text the model reads
- [security] Tool “create_npc_voice_line” rewrote its description, which is the text the model reads
- [cosmetic] “create_npc_voice_line” added an optional parameter “language”
- [cosmetic] “create_talking_video” added an optional parameter “language”
- [cosmetic] “create_npc_voice_line” reworded the description of “script”
- [cosmetic] “create_npc_voice_line” reworded the description of “voiceId”
- [cosmetic] “create_talking_video” reworded the description of “script”
- [cosmetic] “create_talking_video” reworded the description of “voice”

### 2026-11-17 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 72, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-15 (score 72)

First indexed and scored.

## MCP tools (10)

### `list_voices_and_styles` (~85 tokens)

List Avatar Styles, Voices & Credit Pricing

Return all 8 AvatarSay visual styles, all 8 built-in multilingual TTS voices (40+ languages, with audio sample URLs), supported language_boost values, per-action credit costs (including first free 5s talking clip and 2-credit NPC voice lines), and one-time credit pack pricing. Public read-only tool — does not require an API key.

### `roll_rpg_npc` (~370 tokens)

Roll Tabletop RPG / D&D NPC + VTT Exports

Deterministically roll a complete tabletop RPG / D&D NPC (name, ancestry, role, traits, quirk, plot hook, GM secret, portrait prompt, matched voice sample MP3, and a <=75-char greeting tuned for the free 5s talking video clip), plus ready-to-import SillyTavern Character Card V2 JSON and Foundry VTT NPC Actor JSON. Public zero-cost tool — requires NO API key and charges 0 credits.

Input parameters:

- `ancestry` (string): Optional ancestry filter or custom ancestry, e.g. "Dwarven", "Elven", "Half-orc", "Halfling", "Gnomish", "Fey-touched", "Tiefling".
- `exportFormat` (string): Output export format: "all" (default, includes both SillyTavern Character Card V2 and Foundry VTT Actor JSON), "summary", "sillytavern", or "foundry".
- `gender` (string): Optional character presentation filter: "f" (feminine) or "m" (masculine).
- `role` (string): Optional tabletop role filter or custom archetype, e.g. "Tavern keeper", "Runesmith", "Hedge alchemist", "Harbor smuggler", "Wandering bard".
- `seed` (string): Optional deterministic seed (e.g. "forge26a" or "42"). Same seed always produces the exact same NPC; omit to roll a fresh random seed.
- `style` (string): Visual portrait style preset (default "fantasy"). Supports fantasy, anime, 3d-cartoon (or aliases cartoon / 3d), pixel-art, cyberpunk, watercolor, realistic, professional-headshot.

### `get_credits` (~71 tokens)

Get Account Credit Balance

Return the authenticated AvatarSay account email, current non-expiring credit balance, image quality tier (standard vs hd), whether the 0-credit first talking video clip is still available, and how many avatar generations, NPC voice lines, or video seconds the balance covers. Requires Authorization: Bearer avs_...

### `list_avatars` (~88 tokens)

List Account Character Avatars

List recent fictional character avatars (both AI-generated portraits and imported stylized character illustrations) in this AvatarSay account, including assetId (ast_...) and 24-hour signed download URLs, ready to animate with create_talking_video. Requires Authorization: Bearer avs_...

Input parameters:

- `limit` (integer): Maximum number of recent avatar images to return (1–24, default 12).

### `import_character_portrait` (~289 tokens)

Import Stylized Fictional Character Illustration

Import an existing non-photorealistic fictional character illustration (anime, 2D/3D cartoon, pixel art, fantasy digital painting, VTT token art; PNG/JPG/WebP, 256–4096 px, max 5 MB) from an https:// URL or base64 data URI for 0 credits, returning an assetId (ast_...) ready for create_talking_video. Camera photographs and photorealistic human likenesses are strictly blocked by EXIF and automated vision screening. Requires confirmFictional=true and Authorization: Bearer avs_...

Input parameters:

- `confirmFictional` (boolean, required): Must be true: confirms this image is a fictional, stylized character illustration and NOT a photograph or likeness of a real person.
- `imageBase64` (string): Base64-encoded PNG, JPG, or WebP character illustration (raw base64 or data:image/...;base64,... URI, max 5 MB). Provide either imageUrl or imageBase64.
- `imageUrl` (string): Public https:// URL of a PNG, JPG, or WebP stylized character illustration (max 5 MB). Provide either imageUrl or imageBase64.
- `label` (string): Optional character name or short description (up to 160 chars), e.g. "Bramwell Copperbraid — Dwarven Runesmith".

### `list_videos` (~122 tokens)

List Account Talking Videos

List recent watermark-free talking avatar MP4 videos (9:16 720×1280, 1:1 960×960, or 16:9 1280×720 in Studio HD; 480p/640p in Fast Preview) already rendered in this AvatarSay account, including assetId (ast_v_...), spoken script, and 24-hour signed stream & download URLs. Requires Authorization: Bearer avs_...

Input parameters:

- `limit` (integer): Maximum number of recent talking videos to return (1–24, default 12).

### `generate_avatars` (~218 tokens)

Generate Fictional Character Avatars

Generate 2 fictional character portraits (1:1, 9:16, or 16:9) from a text description in one of 8 art styles. Costs 4 credits (Standard) or 6 credits (HD for accounts that have purchased a pack). Enqueues asynchronously and returns jobId immediately — call get_job after ~5–10 seconds to get the 2 assetIds and signed image URLs. Requires Authorization: Bearer avs_...

Input parameters:

- `aspectRatio` (string): Optional aspect ratio: 1:1, 9:16, 16:9 (default "1:1").
- `prompt` (string, required): Visual description of an original fictional character (3–500 chars), e.g. "weathered dwarven blacksmith with copper braids and glowing forge goggles". Avoid real people, celebrities, or explicit cont…
- `style` (string, required): Art style preset ID: anime, 3d-cartoon, pixel-art, realistic, professional-headshot, fantasy, watercolor, cyberpunk.

### `create_npc_voice_line` (~289 tokens)

Create Fast NPC / Character Voice Line (MP3)

Synthesize an instant (<3s) multilingual (40+ languages) character voice bark or tabletop NPC dialogue MP3 (1–500 chars) in one of 8 preset voices with optional language, speed, and emotion control. Costs 2 credits per 100 characters (minimum 2 credits — a new 30-credit account can generate 15 tabletop MP3 barks free). Returns a 24-hour signed MP3 download URL immediately. Requires Authorization: Bearer avs_...

Input parameters:

- `emotion` (string): Optional vocal emotion delivery: neutral, happy, angry, sad, fearful, surprised (default "neutral").
- `language` (string): Optional language hint for pronunciation (default "auto", supporting 40+ languages): auto, English, Russian, French, Spanish, German, Arabic, Portuguese, Japanese, Korean, Chinese, Italian, Turkish,…
- `script` (string, required): Spoken dialogue line in any supported language (1–500 chars).
- `speed` (number): Optional speech speed multiplier (0.8–1.2, default 1.0).
- `voiceId` (string, required): Built-in multilingual voice ID: Friendly_Person, Wise_Woman, Lively_Girl, Calm_Woman, Casual_Guy, Deep_Voice_Man, Patient_Man, Young_Knight.

### `create_talking_video` (~440 tokens)

Create Lip-Synced Talking Character Video

Animate an AvatarSay character avatar (ast_...) with lip-synced speech in 40+ languages using one of 8 preset voices. New accounts get their first short talking clip (<=5s / <=75 chars) for 0 credits in Fast Preview (~15–30s via VEED Fabric 1.0 Fast)! Subsequent or longer clips cost 12 account credits per second of speech (minimum 5s = 60 credits, maximum 30s) in Fast Preview (~15–30s) or Studio HD (~2–4 min via Kling AI Avatar v2 Standard, 720×1280 / 960×960 / 1280×720 MP4). Enqueues asynchronously and returns jobId immediately. Poll get_job for the watermark-free MP4 URL. Failed renders refund credits automatically. Requires Authorization: Bearer avs_...

Input parameters:

- `assetId` (string, required): AvatarSay character asset ID (ast_...) from generate_avatars -> get_job, import_character_portrait, or list_avatars. Camera photos of real people are not supported.
- `language` (string): Optional language hint for pronunciation (default "auto", supporting 40+ languages): auto, English, Russian, French, Spanish, German, Arabic, Portuguese, Japanese, Korean, Chinese, Italian, Turkish,…
- `qualityMode` (string): Optional render mode: "fast" (480p/640p, ~15–30s; required for 0-credit free trial) or "hd" (Studio HD 720p/960p, ~2–4m; default for credit-paid renders).
- `script` (string, required): Spoken dialogue line in any supported language (2–400 chars, up to 30 seconds of speech; <=75 chars qualifies for the 0-credit first clip on new accounts).
- `voice` (string, required): Built-in multilingual voice ID: Friendly_Person, Wise_Woman, Lively_Girl, Calm_Woman, Casual_Guy, Deep_Voice_Man, Patient_Man, Young_Knight.

### `get_job` (~81 tokens)

Get Generation Job Status & Download URLs

Check the status (queued, running, succeeded, failed) of an image or talking-video job (job_...) and return 24-hour signed download URLs once succeeded, or refund details if failed. Requires Authorization: Bearer avs_...

Input parameters:

- `jobId` (string, required): Job ID (job_...) returned by generate_avatars or create_talking_video.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/fourgit-avatarsay-mcp/avatarsay#diagnostics

## Score history

- 2026-11-21: 74
- 2026-11-20: 74
- 2026-11-19: 73
- 2026-11-18: 73
- 2026-11-17: 73
- 2026-11-16: 72
- 2026-11-15: 72

## Common questions

### What is the AvatarSay — Fictional Character, RPG NPC & Talking Video MCP server?

AvatarSay — Fictional Character, RPG NPC & Talking Video MCP is listed in the public MCP registry as io.github.fourgit/avatarsay-mcp. Roll RPG NPCs (Foundry VTT & SillyTavern V2), import stylized art, MP3 barks & talking MP4s. This page covers its hosted endpoint (https://avatarsay.com/mcp).

### Is the AvatarSay — Fictional Character, RPG NPC & Talking Video MCP server safe to use?

AvatarSay — Fictional Character, RPG NPC & Talking Video MCP scores 74 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the AvatarSay — Fictional Character, RPG NPC & Talking Video MCP server expose?

AvatarSay — Fictional Character, RPG NPC & Talking Video MCP exposes 10 tools: list_voices_and_styles, roll_rpg_npc, get_credits, list_avatars, import_character_portrait, and 5 more. Their descriptions and schemas cost roughly 2,053 tokens of context every time the server is loaded.

### Does the AvatarSay — Fictional Character, RPG NPC & Talking Video MCP server require authentication?

No. We connected to AvatarSay — Fictional Character, RPG NPC & Talking Video MCP without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AvatarSay — Fictional Character, RPG NPC & Talking Video MCP server still maintained?

AvatarSay — Fictional Character, RPG NPC & Talking Video MCP is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the AvatarSay — Fictional Character, RPG NPC & Talking Video MCP server?

VerifyMCP ran 13 checks on AvatarSay — Fictional Character, RPG NPC & Talking Video MCP, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://avatarsay.com/mcp
- Repository: https://github.com/fourgit/avatarsay-mcp
- Website: https://avatarsay.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/fourgit-avatarsay-mcp/avatarsay.xml
- Changelog JSON feed: https://verifymcp.io/servers/fourgit-avatarsay-mcp/avatarsay/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/fourgit-avatarsay-mcp/avatarsay.json
- HTML version of this page: https://verifymcp.io/servers/fourgit-avatarsay-mcp/avatarsay
