# Venice AI (npm · @veniceai/mcp-server)

Images, video, music, speech and private chat from Venice AI's models, on one API key.

- Trust score: 74/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `@veniceai/mcp-server`: 74/100 (this document), [markdown](https://verifymcp.io/servers/veniceai-venice-mcp-server/veniceai-mcp-server.md), [page](https://verifymcp.io/servers/veniceai-venice-mcp-server/veniceai-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@veniceai/mcp-server`
- Version: `0.3.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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.

- **Supply Chain Security**: 80/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 40 of 121 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to veniceai/venice-mcp-server).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 10 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 75/100
  - 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 7350 tokens (~153/item across 48 items; 45 tools + 3 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 87/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 61% 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.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 47 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.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Venice AI MCP server?

Venice AI runs locally as an npm package, launched with npx -y @veniceai/mcp-server. 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 veniceai-venice-mcp-server -- npx -y @veniceai/mcp-server
```

### Cursor

```json
{
  "mcpServers": {
    "veniceai-venice-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@veniceai/mcp-server"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "veniceai-venice-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@veniceai/mcp-server"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add veniceai-venice-mcp-server -- npx -y @veniceai/mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "veniceai-venice-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@veniceai/mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add veniceai-venice-mcp-server --command npx --arg -y --arg @veniceai/mcp-server
```

### Hermes

```yaml
mcp_servers:
  veniceai-venice-mcp-server:
    command: "npx"
    args: ["-y", "@veniceai/mcp-server"]
```

### Netclaw

```json
{
  "McpServers": {
    "veniceai-venice-mcp-server": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@veniceai/mcp-server"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add veniceai-venice-mcp-server -t stdio -c npx -a -y @veniceai/mcp-server
```

### Other

```json
{
  "mcpServers": {
    "veniceai-venice-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@veniceai/mcp-server"
      ]
    }
  }
}
```

## 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.

### 2026-11-11 (score 74, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-10 (score 59)

First indexed and scored.

## MCP tools (45)

### `venice_chat` (~368 tokens)

Venice Chat (LLM)

Run an OpenAI-compatible chat completion via Venice's text-model catalog. Calls are non-streaming plaintext. Completion text longer than 8000 characters is truncated and the result reports omitted_chars in structured content. Completion id and actual model, when returned upstream, are available in structured content. Responses marked X-Venice-TEE: true also include a JSON text block for venice_tee_signature. enable_e2ee is rejected: this server does not encrypt chat. Uncensored: NSFW prompts allowed where the model permits. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `max_completion_tokens` (integer): Maximum visible plus reasoning tokens. Preferred over deprecated max_tokens.
- `max_tokens` (integer)
- `messages` (array, required): Chat messages. Multimodal image, audio, video, and file blocks belong in user messages.
- `model` (string): Model id. Defaults to deepseek-v4-flash-0731.
- `parallel_tool_calls` (boolean)
- `prompt_cache_key` (string)
- `prompt_cache_retention` (string)
- `reasoning` (object)
- `reasoning_effort`: Takes precedence over reasoning.effort.
- `response_format`
- `stop`
- `temperature` (number)
- `timeout_ms` (integer): Upstream timeout for this call, covering the full response body. Long generations may need more than the VENICE_HTTP_TIMEOUT_MS default.
- `tool_choice`
- `tools` (array)
- `top_p` (number)
- `venice_parameters` (object): Venice-only options: web search, citations, system prompt control, reasoning control, and characters.
- `verbosity` (string): How much text the model returns.

### `venice_responses` (~171 tokens)

Venice Responses API

Alpha, stateless OpenAI-compatible Responses API for Venice text models. Supports text/image input and reasoning controls, but this MCP tool does not advertise tool calling because the endpoint does not reliably accept those fields. E2EE-capable models are not supported. Uncensored: NSFW prompts allowed where the model permits. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `input` (required): Plain text or an array of text/image message inputs.
- `max_output_tokens` (integer)
- `model` (string)
- `reasoning` (object)
- `temperature` (number)
- `top_p` (number)
- `venice_parameters` (object): Venice-only options supported by /responses: web search, citations, scraping, system prompt control, characters.

### `venice_embeddings` (~92 tokens)

Venice Embeddings

Compute embeddings for text input (OpenAI-compatible). Accepts up to 128 texts per call; split larger jobs into separate batches. Oversized batches are rejected before submission. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `encoding_format` (string)
- `input` (required): Text or array of at most 128 texts.
- `model` (string, required): Embedding model id.

### `venice_image_generate` (~339 tokens)

Venice Image Generate

Generate an image. Supports Flux 2 Pro/Max, Lustify SDXL, Anime (WAI), Qwen Image, GPT Image, Nano Banana Pro and others. Uncensored: NSFW prompts allowed where the model permits. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `aspect_ratio` (string): Model-specific aspect ratio such as "1:1" or "16:9"; the API validates supported values.
- `disable_prompt_optimization_thinking` (boolean): Skip prompt-optimization thinking on supported models.
- `enable_web_search` (boolean): Allow supported models to use web search; additional credits may apply.
- `enhance_prompt` (boolean): Rewrite the prompt before generation. Adds up to ~30 seconds and a charge when applied.
- `format` (string)
- `height` (integer)
- `model` (string): Defaults to flux-2-pro.
- `negative_prompt` (string)
- `prompt` (string, required)
- `quality` (string): Model-specific quality tier; may change pricing.
- `resolution` (string): Model-specific resolution tier such as "1K", "2K", or "4K"; the API validates supported values.
- `safe_mode` (boolean)
- `seed` (integer)
- `steps` (integer)
- `style_preset` (string): See venice://styles.
- `style_references` (array): Model-specific style references. Check the model maxStyleReferences capability.
- `variants` (integer): Number of images. Only supported with non-binary responses.
- `width` (integer)

### `venice_image_edit` (~186 tokens)

Venice Image Edit

Edit an image with a prompt. Returns base64 PNG. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `aspect_ratio` (string): Output aspect ratio, e.g. "1:1", "16:9", "9:16", "4:5". Supported values vary by model; the API validates.
- `enhance_prompt` (boolean): Rewrite the edit prompt with awareness of the input image. May add time and cost.
- `image_url` (string, required): URL of the image to edit (will be passed through to the edit endpoint).
- `model` (string): Edit model id; defaults to firered-image-edit.
- `output_format` (string)
- `prompt` (string, required)
- `resolution` (string): Model-specific output resolution tier; the API validates supported values.
- `safe_mode` (boolean)

### `venice_image_multi_edit` (~178 tokens)

Venice Image Multi-Edit

Edit multiple images together with a single prompt (multi-image composition / outpainting). Returns base64 PNG. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `aspect_ratio` (string): Output aspect ratio, e.g. "1:1", "16:9", "9:16", "4:5". Supported values vary by model; the API validates.
- `enhance_prompt` (boolean): Rewrite the edit prompt with awareness of the input images. May add time and cost.
- `image_urls` (array, required)
- `model` (string)
- `output_format` (string)
- `prompt` (string, required)
- `quality` (string): Model-specific quality tier; may change pricing.
- `resolution` (string): Model-specific output resolution tier; the API validates supported values.

### `venice_image_upscale` (~177 tokens)

Venice Image Upscale

Upscale an image (2-4× scale). Endpoint requires base64 image; this tool fetches the URL and uploads it. Returns base64 PNG. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `creativity` (number): How much detail and texture the upscaler invents, 0 to 0.02. Defaults to 0.01. Higher stays further from the source.
- `image_url` (string, required): Image to upscale: an http(s) URL or an inline base64 data URL. Include a concrete media type in data URLs, e.g. image/jpeg.
- `scale` (number): Upscale factor, 2 to 4. Defaults to 2. Large inputs are scaled down automatically to stay under the 4096x4096 output cap.

### `venice_image_remove_bg` (~46 tokens)

Venice Image Background Remove

Remove image background; returns a transparent PNG (base64). Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `image_url` (string, required)

### `venice_video_generate` (~1130 tokens)

Venice Video Queue

Queue a video generation. Supports Veo 3.1, Kling, Wan, Seedance, MiniMax, PixVerse, Runway, LTX, Grok Imagine, and others. Pick a specific id like "veo3.1-fast-text-to-video", "veo3.1-fast-image-to-video", "kling-2.6-pro-text-to-video", "wan-2.6-text-to-video", "seedance-2-5-reference-to-video-basic" etc. Uncensored: NSFW prompts allowed where the model permits. Supports x402 wallet auth (no Venice account needed) and API key. Returns { model, queue_id }; poll with venice_video_status. NOTE: 'duration' is a model-specific string enum like '4s' / '6s' / '8s'; inspect it with venice_model_details. Current public Seedance models may reject detectable persons outright. Consent flags are defensive compatibility support, not a policy bypass; set them only after showing a returned policy to the user and receiving explicit confirmation.

Input parameters:

- `aspect_ratio` (string): Output aspect ratio, e.g. "16:9", "9:16", "1:1", "4:5", "9:21". Model-specific; see venice_model_details.
- `audio` (boolean): Enable or disable audio generation for models that support it. Defaults to true.
- `audio_url` (string): For models that support audio input: background music. URL or data URL. Supported: WAV, MP3. Max 30s, 15MB.
- `camera_trajectory` (array): For minimax-h3-max-multi-angle only: 2–12 camera keyframes with strictly increasing time from 0 to 1, azimuth in degrees (signed, at most 32 full turns of travel in total), elevation from -90 to 90 d…
- `consents` (object): Defensive compatibility support for a returned Seedance needs_consent flow. Current public models may reject detectable persons outright. All three flags must be true after explicit user confirmation…
- `duration` (string, required): Duration as model-specific string enum, e.g. "4s", "6s", "8s". See venice_model_details.
- `elements` (array): For Kling O3 R2V and similar: up to 4 character/object elements. Reference in prompt as @Element1, @Element2, etc.
- `end_image_url` (string): For models that support end frames or transitions. URL or data URL.
- `image_url` (string): For image-to-video models: starting frame. URL or data URL.
- `model` (string, required): Required. Full model id, e.g. "veo3.1-fast-text-to-video".
- `negative_prompt` (string): Negative prompt (what to avoid). Supported by Seedance and other models.
- `omni_reference_task_type` (string): For seedance-2-5-reference-to-video-basic only: what to do with reference_video_urls. "edit" changes the referenced clip and "extend" continues it; both need reference_video_urls and a prompt that as…
- `prompt` (string, required)
- `reference_audio_urls` (array): For Seedance 2.0 R2V and similar: up to 3 reference audio clips for vocal timbre, narration, or sound effects. Per-clip 2–15s, WAV/MP3; aggregate ≤15s. Must be paired with at least one reference imag…
- `reference_image_urls` (array): For models with reference image support: up to 9 images for character/style consistency. Each a URL or data URL.
- `reference_video_urls` (array): For Seedance 2.0 R2V and similar: up to 3 reference video clips to inherit subject motion, camera movement, and style. Per-clip 2–15s, MP4/MOV, ≤50MB; aggregate ≤15s. Each a URL or data URL.
- `resolution` (string): Output resolution, e.g. "720p", "1080p", "4k". Model-specific; see venice_model_details.
- `scene_image_urls` (array): For models with advanced element support: up to 4 scene reference images. Reference in prompt as @Image1, @Image2, etc.
- `seed` (integer)
- `upscale_factor` (integer): For upscale models only: 1 = quality enhance, 2 = double resolution, 4 = quadruple.
- `video_references` (array): For models with per_reference_audio, e.g. wan-2-7-reference-to-video: reference clips, up to the model's reference-video limit. Each has an optional ref_name to cite in the prompt and an optional aud…
- `video_url` (string): For video-to-video and upscale models (e.g. wan-2-7-video-to-video, topaz-video-upscale): input video. URL or data URL. Supported: MP4, MOV, WebM.

### `venice_video_status` (~239 tokens)

Venice Video Retrieve / Status

Check status of a queued video job. Returns JSON progress while PROCESSING. Completed jobs are either an embedded base64 video/mp4 MCP resource or a download_url resource link. For VPS / Grok Imagine Private models, retrieve returns COMPLETED JSON without a URL: this process reuses the queue-time download_url when venice_video_generate ran here, or accepts a Venice-host download_url argument. POST endpoint with body {model, queue_id}. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `delete_media_on_completion` (boolean): Delete server-side media after an embedded MP4 has been buffered, before the tool result returns to the client. Ignored for download_url results: download first, then call venice_video_complete.
- `download_url` (string): Queue-time download_url from venice_video_generate. Must be an https Venice host. Needed for VPS / Grok Imagine Private only when this process did not queue the job (retrieve returns COMPLETED withou…
- `model` (string, required): Same model id used to queue.
- `queue_id` (string, required): Returned by venice_video_generate.

### `venice_video_complete` (~60 tokens)

Venice Video Complete (cleanup)

Mark a completed video as downloaded and delete server-side media. Reports removal only when Venice confirms success. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `model` (string, required)
- `queue_id` (string, required)

### `venice_tts` (~180 tokens)

Venice TTS (Speech)

Convert text to speech. Supports cloned voices + emotion tags ([whispers], [sarcastically], etc.). When streaming=true, Venice streams upstream but this MCP tool buffers and returns one complete audio result; it does not emit incremental MCP chunks. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `input` (string, required): Text to convert to speech (max 4096 chars).
- `model` (string)
- `response_format` (string)
- `speed` (number)
- `streaming` (boolean): Forward Venice's streaming flag. The MCP result is still buffered into one complete audio response, not delivered incrementally.
- `temperature` (number): Sampling temperature. Only supported by some TTS models; unsupported models ignore it.
- `voice` (string): Voice id; see venice://voices.

### `venice_asr` (~421 tokens)

Venice ASR (Speech-to-Text)

Transcribe audio. Fetches the URL server-side and forwards as multipart/form-data file upload. Upstream transcription JSON larger than 1 MiB is rejected so word/character timestamps cannot exhaust memory. Timestamp arrays and transcripts longer than 8000 characters are paged in the MCP result: such a transcription returns result_handle alongside the first page, and every later page must be requested with that handle so the clip is transcribed — and charged — exactly once. Handles are held in memory, per MCP session, for 10 minutes and only the 16 most recent survive, after which paging fails and a fresh transcription is needed. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `audio_url` (string): Audio to transcribe, as an http(s) URL or an inline base64 data URL. Include a concrete media type in data URLs, e.g. audio/mpeg for MP3 or audio/mp4 for M4A. Required unless result_handle is supplie…
- `language` (string)
- `model` (string)
- `response_format` (string)
- `result_handle` (string): Handle returned by an earlier paged transcription. Pages that retained result without submitting another transcription, so audio_url is ignored when this is set. Expires after 10 minutes or once 16 n…
- `text_offset` (integer): Start character of the transcript page (8000 characters each). Defaults to 0. Use result_handle with next_text_offset to read past the first page.
- `timestamp_limit` (integer): Max entries returned per timestamp array. Defaults to 200. Follow next_timestamp_offset; it is null on the last page.
- `timestamp_offset` (integer): Start index into each timestamp array (word/segment/char). Defaults to 0. Use result_handle to move past the first page.
- `timestamps` (boolean): Include word and character timestamps in JSON responses. Defaults to false.

### `venice_voice_clone` (~249 tokens)

Venice Voice Clone / List

Discover or clone TTS voices. Action 'list' reads live per-model voice metadata from auth-free GET /v1/models?type=tts. Action 'create' requires sample_url, then uploads the sample to POST /v1/audio/voices for the chosen cloning model. Cloned voices come back as a `vv_<id>` handle; pass it as venice_tts voice together with the same model. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `action` (string, required): list = fetch live TTS model voice metadata; create requires sample_url
- `model` (string): TTS model the cloned voice is paired with (action=create). Defaults to tts-chatterbox-hd.
- `sample_url` (string): Required for action=create. Audio sample as an http(s) URL or an inline base64 data URL; tts-chatterbox-hd accepts MP3/WAV/FLAC/M4A, tts-minimax-speech-02-hd MP3/WAV only. Include a concrete media ty…

### `venice_music_generate` (~321 tokens)

Venice Music Queue

Queue music generation. Available models: ace-step-15, elevenlabs-music, minimax-music-v2/v25/v26, stable-audio-25, mmaudio-v2-text-to-audio, elevenlabs-sound-effects-v2. Uncensored: NSFW prompts allowed where the model permits. Supports x402 wallet auth (no Venice account needed) and API key. Returns { model, queue_id }; poll with venice_music_status.

Input parameters:

- `duration_seconds`: Optional duration in seconds as a positive integer or numeric string. Model-specific.
- `force_instrumental` (boolean): Only for models reporting supports_force_instrumental.
- `instrumental` (boolean): Deprecated: use force_instrumental. Ignored when force_instrumental is set.
- `language_code` (string): ISO 639-1 language code on supported models.
- `loop` (boolean): Create a seamless loop on models reporting supports_loop.
- `lyrics` (string): Deprecated: use lyrics_prompt. Ignored when lyrics_prompt is set.
- `lyrics_optimizer` (boolean): Auto-generate lyrics. lyrics_prompt must be empty when enabled.
- `lyrics_prompt` (string): Lyrics/text for lyric-capable models. Length limits come from model metadata.
- `model` (string, required): Required. Music model id, e.g. "elevenlabs-music".
- `prompt` (string, required)
- `speed` (number): Model-specific speed multiplier. Check model min_speed/max_speed.
- `voice` (string): Model-supported voice id/name.

### `venice_music_status` (~129 tokens)

Venice Music Retrieve / Status

Check status of a queued music job. Returns JSON progress while PROCESSING. Completed jobs are either an embedded base64 audio MCP resource or a download_url resource link. POST endpoint with body {model, queue_id}. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `delete_media_on_completion` (boolean): Delete server-side media after embedded audio has been buffered, before the tool result returns to the client. Ignored for download_url results: download first, then call venice_music_complete.
- `model` (string, required)
- `queue_id` (string, required)

### `venice_music_complete` (~61 tokens)

Venice Music Complete (cleanup)

Mark a completed music job as downloaded and delete server-side media. Reports removal only when Venice confirms success. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `model` (string, required)
- `queue_id` (string, required)

### `venice_web_search` (~116 tokens)

Venice Web Search

Search the web with Brave Search (default, Zero Data Retention), Google Search (proxied and anonymized by Venice), or Exa (Zero Data Retention). Returns structured results with titles, URLs, snippets, and dates. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `limit` (integer)
- `query` (string, required)
- `search_provider` (string): brave (default) and exa use Zero Data Retention; google is proxied/anonymized by Venice.

### `venice_web_scrape` (~48 tokens)

Venice Web Scrape

Scrape one URL into markdown text. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `format` (string)
- `url` (string, required)

### `venice_text_parser` (~101 tokens)

Venice Text Parser (PDF/DOCX/EPUB/PPTX/XLSX)

Extract text from a document URL. Fetches the URL server-side and uploads the file as multipart/form-data. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `url` (string, required): Document to parse: an http(s) URL or an inline base64 data URL. Include a concrete media type in data URLs, e.g. application/pdf or application/vnd.openxmlformats-officedocument.wordprocessingml.docu…

### `venice_crypto_networks` (~30 tokens)

Venice Crypto RPC Networks

List the live, authoritative network slugs accepted by venice_crypto_rpc. No authentication required.

### `venice_crypto_rpc` (~303 tokens)

Venice Crypto RPC Proxy

Proxy one JSON-RPC request or a batch of up to 100 requests to a supported blockchain network. Use venice_crypto_networks for the live network list. For a simple call, pass rpc_method/rpc_params; for complete request IDs or batches, pass request. Relays (eth_sendRawTransaction, eth_sendUserOperation, Solana sendTransaction, and Starknet writes) must be sent as single requests (not batched) with idempotency_key; reuse the same key when retrying. Results are returned as compact JSON; responses larger than 64 KiB are rejected after Venice has billed them, so keep queries narrow. Supports x402 wallet auth (no Venice account needed) and API key.

Input parameters:

- `idempotency_key` (string): Reuse the same key when retrying a request. Required for eth_sendRawTransaction, eth_sendUserOperation, Solana sendTransaction, and Starknet writes so a lost response is not broadcast again.
- `network` (string, required): Network slug returned by venice_crypto_networks, e.g. "ethereum-mainnet".
- `request`: A single JSON-RPC request object (ID optional) or a non-empty batch of at most 100 request objects (ID required per item).
- `rpc_method` (string): Convenience form for a single request. Do not combine with request.
- `rpc_params`: Parameters for rpc_method, by position (array) or by name (object).

### `venice_tee_attestation` (~128 tokens)

Venice TEE Attestation

Fetch hardware-attestation evidence for a TEE-capable text model. The caller must supply a fresh 32-byte nonce and independently verify the echoed nonce, Intel TDX quote, optional NVIDIA evidence, debug-mode state, and signing-key binding before trusting the key. Fetching this evidence does not itself establish E2EE. No authentication required.

Input parameters:

- `model` (string, required): TEE-capable text model id; check supportsTeeAttestation in venice_list_models.
- `nonce` (string, required): Caller-generated 32-byte freshness challenge encoded as exactly 64 hexadecimal characters.

### `venice_tee_signature` (~106 tokens)

Venice TEE Response Signature

Fetch the enclave signature for a completed TEE text-model chat request. The caller must cryptographically verify it against the signing identity bound by a separately verified attestation; this tool only returns the provider payload. No authentication required.

Input parameters:

- `model` (string, required): Actual TEE-capable model returned in the chat completion metadata.
- `request_id` (string, required): Completion id returned by venice_chat or venice_chat_with_character, in structured content or the additional metadata text block.

### `venice_list_models` (~235 tokens)

Venice List Models

List the live model catalog, one page at a time. Omitting type lists every model type (sent upstream as type=all). Each entry is a compact summary (id, type, name, context length, enabled capabilities, traits, privacy, pricing); set verbose=true for the full upstream model objects. Returns total, next_offset, and every matching model id in ids; call again with offset=next_offset until next_offset is null. No authentication required.

Input parameters:

- `limit` (integer): Max models per page. Defaults to 50. A page may hold fewer when entries are large; follow next_offset.
- `offset` (integer): Index of the first model to return. Defaults to 0.
- `type` (string): Catalog type: text, image, inpaint, upscale, video, music, tts, asr, embedding, decision, "code", or "all" (default). Without a type Venice returns only text models, so pass one to find video, image…
- `verbose` (boolean): Return full upstream model objects instead of compact summaries. Defaults to false.

### `venice_model_traits` (~75 tokens)

Venice Model Traits

Return the live trait-name to model-id mapping for a model type. The API defaults to text when type is omitted. No authentication required.

Input parameters:

- `type` (string): Catalog type: text, image, inpaint, upscale, video, music, tts, asr, embedding, decision. Defaults to text upstream.

### `venice_model_compatibility_mapping` (~80 tokens)

Venice Model Compatibility Mapping

Return the live compatible model-name to Venice model-id mapping for a model type. The API defaults to text when type is omitted. No authentication required.

Input parameters:

- `type` (string): Catalog type: text, image, inpaint, upscale, video, music, tts, asr, embedding, decision. Defaults to text upstream.

### `venice_model_details` (~110 tokens)

Venice Model Details

Get one exact model's full catalog row, including model_spec constraints, capabilities, and pricing when available. Requires a concrete type to keep the upstream catalog response bounded. No authentication required.

Input parameters:

- `model_id` (string, required): Exact model id, e.g. from venice_list_models({ type: "video" }).
- `type` (string, required): Catalog type the model belongs to: text, image, inpaint, upscale, video, music, tts, asr, embedding, decision.

### `venice_image_styles` (~25 tokens)

Venice Image Styles

List image style presets available for venice_image_generate. No authentication required.

### `venice_audio_quote` (~84 tokens)

Venice Music Cost Quote

Get a price quote for a music generation BEFORE queuing. Useful for budgeting. No authentication required.

Input parameters:

- `character_count` (integer): Required for character-based pricing models.
- `duration_seconds`: Optional duration in seconds as a positive integer or numeric string. Model-specific.
- `model` (string, required): Music model id, e.g. "elevenlabs-music".

### `venice_video_quote` (~78 tokens)

Venice Video Cost Quote

Get a price quote for a video generation BEFORE queuing. No authentication required.

Input parameters:

- `duration` (string, required): Duration as model-specific string enum, e.g. "4s", "6s", "8s".
- `model` (string, required): Video model id, e.g. "veo3.1-fast-text-to-video".

### `venice_list_characters` (~133 tokens)

Venice List Characters

List public Venice characters. API key required — this endpoint does not accept x402 wallet auth.

Input parameters:

- `categories` (array)
- `isAdult` (boolean)
- `isPro` (boolean)
- `isWebEnabled` (boolean)
- `limit` (integer)
- `modelId` (array)
- `offset` (integer)
- `search` (string)
- `sortBy` (string)
- `sortOrder` (string)
- `tag` (string): Deprecated: use tags. A single tag, merged into tags.
- `tags` (array)

### `venice_get_character` (~50 tokens)

Venice Get Character

Get one public Venice character by slug. API key required — this endpoint does not accept x402 wallet auth.

Input parameters:

- `slug` (string, required): Public character slug, e.g. "alan-watts".

### `venice_character_reviews` (~67 tokens)

Venice Character Reviews

List paginated public reviews for a Venice character. API key required — this endpoint does not accept x402 wallet auth.

Input parameters:

- `page` (integer)
- `pageSize` (integer)
- `slug` (string, required): Public character slug, e.g. "alan-watts".

### `venice_chat_with_character` (~142 tokens)

Venice Character Chat

Chat with a Venice character by slug. Completion id and actual model, when returned upstream, are available in structured content. Responses marked X-Venice-TEE: true also include a JSON text block for venice_tee_signature. Note: the character lookup itself is API-key-only, but the chat completion supports x402 — so x402 users may need to fetch character info via API key first. Uncensored: NSFW prompts allowed where the model permits.

Input parameters:

- `character_slug` (string, required)
- `max_tokens` (integer)
- `messages` (array, required)
- `model` (string)
- `temperature` (number)

### `venice_billing_balance` (~50 tokens)

Venice Billing Balance

Get current USD, DIEM, and bundled-credit availability for the authenticated Venice account. ADMIN API key required — inference keys cannot call this endpoint. This endpoint does not accept x402 wallet auth.

### `venice_billing_usage_analytics` (~135 tokens)

Venice Billing Usage Analytics

Get beta aggregated usage by date, model, and API key. Data is cached for 10 minutes. Choose either lookback or a complete start/end date range. ADMIN API key required — inference keys cannot call this endpoint. This endpoint does not accept x402 wallet auth.

Input parameters:

- `end_date`: Custom range end in YYYY-MM-DD format. Requires start_date.
- `lookback` (string): Relative lookback from 1d through 90d. Cannot be combined with start_date/end_date.
- `start_date` (string): Inclusive custom range start in YYYY-MM-DD format. Requires end_date.

### `venice_billing_usage_history` (~270 tokens)

Venice Billing Usage History

Walk detailed billing usage in ascending timestamp order using cursor pagination. Supports complete JSON or upstream CSV pages, defaulting to 10 rows. Pages exceeding 64 KiB fail without returning partial rows or a next cursor. On continuation, send cursor without the original filters; CSV nextCursor values already encode format=csv so a cursor-only follow-up stays on text/csv. This uses /billing/usage-history, never deprecated /billing/usage. ADMIN API key required — inference keys cannot call this endpoint. This endpoint does not accept x402 wallet auth.

Input parameters:

- `currency` (string)
- `cursor` (string): Opaque nextCursor from the previous page. CSV pages return a csv: prefix so continuation stays on text/csv. Cannot be combined with filters or page_size.
- `end_timestamp`: Exclusive first-page upper bound, ISO 8601 UTC with Z suffix.
- `format` (string): Defaults to json. Optional on continuation; CSV nextCursor values already stay on CSV.
- `page_size` (integer): First-page row count. Defaults to 10. Complete pages larger than 64 KiB are rejected; use smaller pages or narrower timestamp filters.
- `start_timestamp` (string): Inclusive first-page lower bound, ISO 8601 UTC with Z suffix.

### `venice_list_api_keys` (~51 tokens)

Venice List API Keys

List active API-key metadata, including only the documented last six characters—not full key secrets. ADMIN API key required — inference keys cannot call this endpoint. This endpoint does not accept x402 wallet auth.

### `venice_get_api_key` (~76 tokens)

Venice Get API Key Details

Get metadata, usage, balances, and rate-limit details for one API-key ID. The documented response does not reveal the full key secret. ADMIN API key required — inference keys cannot call this endpoint. This endpoint does not accept x402 wallet auth.

Input parameters:

- `id` (string, required): API-key ID, not the key secret.

### `venice_api_key_rate_limits` (~46 tokens)

Venice API Key Rate Limits

Get the current key's balances, access status, tier, expiration, and model-specific rate limits. API key required — this endpoint does not accept x402 wallet auth.

### `venice_api_key_rate_limit_logs` (~55 tokens)

Venice API Key Rate Limit Logs

Get the last 50 exceeded rate-limit events for the account. This read-only endpoint is experimental. ADMIN API key required — inference keys cannot call this endpoint. This endpoint does not accept x402 wallet auth.

### `venice_x402_balance` (~79 tokens)

Venice x402 Wallet Balance

Check the prepaid x402 credit balance for an EVM or Solana wallet address. SIWX-ONLY: this endpoint rejects API key auth and requires SIGN-IN-WITH-X (forwarded from VENICE_SIWX_TOKEN). The wallet in the path must match the SIWX-authenticated wallet.

Input parameters:

- `wallet_address` (string, required)

### `venice_x402_top_up_info` (~89 tokens)

Venice x402 Top-up Requirements

Fetch the x402 top-up payment requirements: the accepted USDC payment options (currently Base and Solana), each with network, asset, receiver wallet (payTo), minimum amount in base units, and settlement timeout. Sends an empty POST with no payment header, so nothing is charged. Signing and PAYMENT-SIGNATURE submission happen OUTSIDE this MCP server. No authentication required.

### `venice_x402_transactions` (~81 tokens)

Venice x402 Transaction History

List recent x402 top-up + debit transactions for an EVM or Solana wallet. SIWX-ONLY: rejects API key, requires SIGN-IN-WITH-X (VENICE_SIWX_TOKEN). The wallet in the path must match the SIWX-authenticated wallet.

Input parameters:

- `limit` (integer)
- `wallet_address` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/veniceai-venice-mcp-server/veniceai-mcp-server#diagnostics

## Score history

- 2026-11-21: 74
- 2026-11-20: 74
- 2026-11-19: 74
- 2026-11-18: 74
- 2026-11-17: 74
- 2026-11-16: 74
- 2026-11-15: 74
- 2026-11-14: 74
- 2026-11-13: 74
- 2026-11-12: 74
- 2026-11-11: 74
- 2026-11-10: 59

## Common questions

### What is the Venice AI MCP server?

Venice AI is an MCP server listed in the public MCP registry as io.github.veniceai/venice-mcp-server. Images, video, music, speech and private chat from Venice AI's models, on one API key. This page covers its npm package (@veniceai/mcp-server).

### Is the Venice AI MCP server safe to use?

Venice AI scores 74 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 Venice AI MCP server expose?

Venice AI exposes 45 tools: venice_chat, venice_responses, venice_embeddings, venice_image_generate, venice_image_edit, and 40 more. Their descriptions and schemas cost roughly 7,190 tokens of context every time the server is loaded.

### Is the Venice AI MCP server still maintained?

Venice AI 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 licence is the Venice AI MCP server under?

Venice AI declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the Venice AI MCP server?

VerifyMCP ran 15 checks on Venice AI, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Venice AI: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/@veniceai/mcp-server
- Socket report: https://socket.dev/npm/package/@veniceai/mcp-server
- Repository: https://github.com/veniceai/venice-mcp-server
- Website: https://docs.venice.ai/guides/integrations/venice-mcp
- Changelog RSS feed: https://verifymcp.io/servers/veniceai-venice-mcp-server/veniceai-mcp-server.xml
- Changelog JSON feed: https://verifymcp.io/servers/veniceai-venice-mcp-server/veniceai-mcp-server/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/veniceai-venice-mcp-server/veniceai-mcp-server.json
- HTML version of this page: https://verifymcp.io/servers/veniceai-venice-mcp-server/veniceai-mcp-server
