venice-mcp-server

MCP音视频

提供方 veniceai · 包名 @veniceai/mcp-server

音视频 stdio · 本地进程 API Key 社区 / 第三方 Claude DesktopClaudeCursorCodex
查看接入方式

The Venice AI MCP Server integrates Venice API's 45 AI capabilities into MCP hosts such as Claude, Cursor, and ChatGPT via the Model Context Protocol, covering chat, image, video, audio, music, web search, crypto RPC, and more, for developers needing private and uncensored AI model integration.

一句话选型结论

按资料字段整理

venice-mcp-server 属于音视频类 MCP 服务器,stdio · 本地进程,API Key,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类音视频 传输方式stdio · 本地进程 鉴权API Key 部署方式本地部署
GitHub 星标 70 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

音视频
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

Local Deployment MCP Server AI Model Integration TypeScript Multimodal Content Generation Image Generation Video Generation Text-to-Speech Web Search Augmentation Privacy Protection

支持客户端

适用场景

Local DeploymentMCP ServerAI Model Integration

安装与配置

stdio · 本地进程 API Key
客户端在本机拉起子进程,数据不出本机
npx -y @veniceai/mcp-server@0.2.0

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 node,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
转写与字幕

把音视频转成文字和字幕。

音视频处理

裁剪、转码、拼接素材。

内容分发

把成品发到对应平台。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好API Key对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在音视频场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
venice-mcp-server当前 未标注 stdio · 本地进程 本地部署 有 2026-10-10
Ableton MCP B7b69a6a 16 stdio · 本地进程 本地部署 有 2026-05-17
Mini Max MCP 8 SSE · 服务端推送 远程部署 有 2026-05-18
LocalAI 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Youtube E0eb3510 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Voicemode MCP 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

音视频
字段来自项目仓库与公开索引,中文说明由本站标注
提供方veniceai上游标注的维护方 veniceai
分类音视频本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式API Key远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时@veniceai/mcp-server · node本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-10-10上游最后核验时间

详细介绍

33.3 KB
来自项目仓库与上游目录的原文,未做删改

@veniceai/mcp-server

> Model Context Protocol server for the Venice API - uncensored, private AI for any MCP host (Claude Desktop, Cursor, ChatGPT, LM Studio, Continue, LibreChat, Open WebUI, AnythingLLM, Jan, Le Chat).

Plug Venice's chat, image, video, audio, music, and character models into any agent in 30 seconds, including billing and API-key operations. 45 tools across all modalities, one config block.

Requires Node.js 20 or newer; Node.js 22 or 24 is recommended. CI tests Node.js 20, 22, and 24. The refreshed MCP SDK dependency graph requires Node.js 20 for fresh installs, so upgrade Node.js before installing this version if you previously used Node.js 18.

Quick start

1. Get a key from venice.ai

See the API key guide for step-by-step instructions.

2. Add this to your MCP host config

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows), Cursor (~/.cursor/mcp.json), LM Studio, etc:```json
{
"mcpServers": {
"venice": {
"command": "npx",
"args": ["-y", "@veniceai/mcp-server@0.3.0"],
"env": { "VENICE_API_KEY": "<your-venice-api-key>" }
}
}
}


### 3. Restart your MCP host

That&#x27;s it. Type a prompt — your agent now has chat, image, video, music, TTS, ASR, and 39 more Venice tools.

## What you get

**45 tools** spanning every Venice modality plus billing and API-key operations, **3 resources** (`venice://models`, `venice://styles`, `venice://voices`) and **3 prompt templates** (uncensored research, NSFW creative writing, image style explorer). The voices resource is built live from each TTS model&#x27;s catalog metadata.

Every tool declares explicit `readOnlyHint`, `destructiveHint`, `idempotentHint` and `openWorldHint` annotations to help hosts decide when to request approval. Video and music status tools are marked destructive because their optional `delete_media_on_completion` argument can delete stored media before returning the result. Hints describe a tool&#x27;s possible behavior; hosts should still enforce their own approval policy.

### 💬 Chat &amp; embeddings

| Tool | Description |
|---|---|
| `venice_chat` | Chat completions with documented text/image/audio/video/file blocks, structured response formats, function tools, prompt caching, and reasoning controls. Calls are plaintext and non-streaming. |
| `venice_responses` | Alpha, stateless Responses API for text models. Supports text/image input and reasoning controls. E2EE-capable models are not supported, and this tool does not expose unreliable tool fields. |
| `venice_embeddings` | Compute embeddings for text input (OpenAI-compatible). |
| `venice_chat_with_character` | Chat with a Venice character by slug. |

### 🎨 Image

| Tool | Description |
|---|---|
| `venice_image_generate` | Generate an image. Supports model-specific width/height or free-string `aspect_ratio`/`resolution`, quality tiers, prompt enhancement, style references, web search, variants, and output format. |
| `venice_image_edit` | Edit an image with a prompt. Supports free-string sizing, output format, and prompt enhancement; returns a base64 image. |
| `venice_image_multi_edit` | Edit multiple images together with a single prompt (multi-image composition / outpainting), including free-string sizing, quality, output format, and prompt enhancement. |
| `venice_image_upscale` | Upscale an image (2–4× scale, with a `creativity` control). Returns base64 PNG. |
| `venice_image_remove_bg` | Remove image background; returns a transparent PNG. |
| `venice_image_styles` | List image style presets available for `venice_image_generate`. |

### 🎬 Video

| Tool | Description |
|---|---|
| `venice_video_generate` | Queue a video generation. Supports Sora 2, Veo 3.1, Kling, Wan, LTX 2, Seedance (incl. r2v video-to-video), Runway Gen-4, and others. Accepts image, video, audio, reference inputs, and the Seedance consent attestation flow where applicable. |
| `venice_video_status` | Check status of a queued video job. Returns JSON progress while `PROCESSING`, then either an embedded MP4 or a `download_url` resource link. Pass the queue-time `download_url` for VPS / Grok Imagine Private models. |
| `venice_video_complete` | Mark a completed video as downloaded. Reports server-side deletion only when Venice confirms success. |
| `venice_video_quote` | Get a price quote for a video generation BEFORE queuing. |

### 🔊 Audio (TTS / ASR)

| Tool | Description |
|---|---|
| `venice_tts` | Convert text to speech. Supports cloned voices, temperature, and Venice&#x27;s streaming flag; MCP returns the completed audio as one buffered result. |
| `venice_asr` | Transcribe audio from a URL as JSON or text, with optional word and character timestamps. |
| `venice_voice_clone` | Discover live model-scoped voice metadata, or clone a voice from a sample audio URL for `tts-chatterbox-hd` (default) or `tts-minimax-speech-02-hd`. Cloned voices are returned as a `vv_` handle to pass as the `venice_tts` voice. |
| `venice_audio_quote` | Get a price quote for music generation BEFORE queuing. |

### 🎵 Music

| Tool | Description |
|---|---|
| `venice_music_generate` | Queue music generation. Uses the live QueueAudioRequest fields: `force_instrumental`, `lyrics_prompt`, `lyrics_optimizer`, `loop`, `voice`, `language_code`, `speed`, and model-specific `duration_seconds`. Deprecated `instrumental` / `lyrics` are still accepted as aliases. |
| `venice_music_status` | Check status of a queued music job. Returns JSON progress while `PROCESSING`, then either embedded audio or a `download_url` resource link. |
| `venice_music_complete` | Mark a completed music job as downloaded and delete server-side media. |

### 🌐 Web augment

| Tool | Description |
|---|---|
| `venice_web_search` | Search with Brave (default, Zero Data Retention), Google (proxied/anonymized by Venice), or Exa (Zero Data Retention). Returns the parsed `{ query, results }` as structured content. |
| `venice_web_scrape` | Scrape one URL into markdown text. |
| `venice_text_parser` | Extract text from a document URL (PDF, DOCX, EPUB, PPTX, XLSX, …). |

### 📚 Catalog

| Tool | Description |
|---|---|
| `venice_list_models` | Page through the live model catalog, every type by default, with server-side filtering for `asr`, `decision`, `embedding`, `image`, `music`, `text`, `tts`, `upscale`, `inpaint`, `video`, `all`, `code`, or any newer catalog type. Returns compact summaries (50 per page by default, up to 200) with `total`, `next_offset`, and every matching model id; set `verbose` for full model objects. |
| `venice_model_details` | Get one exact model&#x27;s full catalog row, including `model_spec` constraints, capabilities, and pricing. |
| `venice_model_traits` | Get the live trait-name to model-id mapping for a model type. |
| `venice_model_compatibility_mapping` | Get compatible model-name to Venice model-id mappings. |
| `venice_list_characters` | List public Venice characters with search, tag/category/model, content, capability, sort, and pagination filters. API key only. |
| `venice_get_character` | Get a public character by slug. API key only. |
| `venice_character_reviews` | List paginated public reviews for a character. API key only. |

### 🔐 TEE attestation

| Tool | Description |
|---|---|
| `venice_tee_attestation` | Fetch Intel TDX attestation evidence, optional NVIDIA evidence, and the model signing key using a caller-generated 32-byte nonce. |
| `venice_tee_signature` | Fetch the enclave response-signature payload for a chat completion request ID. |

Both routes are currently live without authentication. They only apply to text models advertising `supportsTeeAttestation`. These tools expose evidence; they do not verify it, and this server does not encrypt chat. `venice_chat` rejects `enable_e2ee`.

Both chat tools retain the upstream completion `id` and actual `model`, when present, in `structuredContent`. Only responses with the upstream `X-Venice-TEE: true` header also include those values in an additional JSON text block for text-only clients. Pass those values to `venice_tee_signature` to retrieve the signature for that completion. Ordinary responses keep their existing answer text without an extra metadata block; the first block and tool-call fallbacks are unchanged. The header is an upstream indication, not cryptographic verification.

### Media API behavior

- Successful upstream responses have a default 16 MiB limit, including JSON and text without a declared Content-Length. Tool-specific image, video, audio, transcription, billing, and RPC limits take precedence. Oversized responses fail without a partial result; an inference may already have completed and incurred a charge before the limit is reached. There is no environment override for this default.
- `venice_embeddings` accepts at most 128 texts per call, for both float and base64 output. Larger batches are rejected locally before submission, so the rejected batch incurs no upstream charge. Split larger jobs into separate calls; the server never automatically splits or retries a batch. This conservative limit avoids the observed overflow for a 256-text, 4,096-dimension float response, but is not a byte-size guarantee for every model or response encoding. The 16 MiB guard still applies, and an unusually large response from an accepted batch can still be rejected after processing upstream.
- Upstream API redirects are rejected to keep credentials and request bodies at the configured API origin.
- Image `aspect_ratio` and `resolution` values remain free strings because supported values vary by model. Venice validates them. When `enhance_prompt` is applied, image generate/edit/multi-edit results include the URL-decoded `enhanced_prompt` returned in `x-venice-enhanced-prompt`. Image responses are capped at `VENICE_MAX_IMAGE_RESPONSE_BYTES` (default 32 MiB). Unlike an oversized video, an oversized image result cannot be retried for free, so request fewer variants, a lower resolution, or jpeg/webp output for large batches.
- Current public Seedance models may reject media containing detectable persons outright. Defensive support remains for compatible or legacy `needs_consent` responses: the tool returns Venice&#x27;s policy text, affected media roles, and next step. The three `consents.seedance` flags are legal attestations and must only be set to `true` after the user explicitly confirms all three statements. Consent is never a content-policy bypass.
- Completed videos may arrive as `video/mp4` or as JSON with a `download_url`. Binary completions are returned as an embedded MCP resource (`blob`, `mimeType: &quot;video/mp4&quot;`, synthetic `venice://video/...` URI), streamed into a bounded buffer that defaults to 25 MiB (`VENICE_MAX_VIDEO_RESPONSE_BYTES`). Oversized binary results remain queued and can be retried with the same queue ID after changing the limit. JSON completions return the `download_url` as an MCP resource link instead of fetching that URL. Because that link stops working once the stored media is removed, `delete_media_on_completion` is not applied to `download_url` results: download the file first, then call `venice_video_complete` (and optionally send an HTTP `DELETE` to the link to revoke it). For VPS / Grok Imagine Private models, `download_url` is returned only on queue; pass that URL into `venice_video_status` so a `COMPLETED` retrieve without an inline URL still yields a resource link.
- Music retrieval returns JSON status and timing while processing, then an `audio/*` body when complete (including MP3, WAV, FLAC, and M4A). Completed tracks are returned as embedded MCP blob resources with a synthetic `venice://music/...` URI and buffered up to 32 MiB by default (`VENICE_MAX_AUDIO_RESPONSE_BYTES`). That configurable limit applies only to binary media; successful status JSON uses a separate fixed 1 MiB safety limit. Oversized, empty, or non-audio responses are not deleted, so the same queue ID remains available for cleanup or a retry with a higher limit. JSON completions with a `download_url` return it as an MCP resource link; as with video, `delete_media_on_completion` is not applied to them: download the file first, then call `venice_music_complete`.

### ⛓️ Crypto

| Tool | Description |
|---|---|
| `venice_crypto_networks` | List the live network slugs supported by the crypto RPC proxy. No authentication required. |
| `venice_crypto_rpc` | Proxy one JSON-RPC request or a batch of up to 100 requests. Returns compact JSON (max 64 KiB) plus Venice&#x27;s credit, cost, and idempotent-replay headers. Transaction broadcasts must be sent as single requests with `idempotency_key`. |

### 💰 Billing (ADMIN API key only)

| Tool | Description |
|---|---|
| `venice_billing_balance` | Get current USD, DIEM, and bundled-credit availability. |
| `venice_billing_usage_analytics` | Get beta aggregate usage by date, model, and API key using a lookback or custom date range. |
| `venice_billing_usage_history` | Walk detailed usage with cursor pagination, first-page filters, and JSON or CSV output. |

Usage-history first pages default to 10 rows. JSON and CSV pages are returned whole, never truncated. A page exceeding 64 KiB returns an error without partial rows or a continuation cursor; restart with the original filters and a smaller `page_size` (minimum 10), or a narrower timestamp range. Retrying the same cursor cannot reduce the page size encoded in it.

Usage-history continuation calls must send `cursor` without the original filters. CSV pages return a `csv:`-prefixed `nextCursor` so a cursor-only follow-up stays on `text/csv`. The deprecated `/billing/usage` route is not wrapped. Billing tools require an ADMIN `VENICE_API_KEY` and fail locally instead of falling back to SIWX. Inference keys cannot call these endpoints.

### 🔑 API keys

| Tool | Description |
|---|---|
| `venice_list_api_keys` | List active key metadata without full key secrets. ADMIN API key only. |
| `venice_get_api_key` | Get one key&#x27;s metadata, usage, balances, and rate limits. ADMIN API key only. |
| `venice_api_key_rate_limits` | Get current balances, access status, tier, and model limits. API key only. |
| `venice_api_key_rate_limit_logs` | Get the last 50 exceeded rate-limit events. ADMIN API key only; experimental upstream. |

List, get, and rate-limit logs require an ADMIN `VENICE_API_KEY`. `venice_api_key_rate_limits` accepts an INFERENCE or ADMIN key. These tools never forward `SIGN-IN-WITH-X`. Web3 challenge and mint are not registered here.

### 💳 x402 wallet helpers

&gt; Optional — only needed if you authenticate with a wallet via **x402** instead of an API key. See **x402** — pay with a wallet.

| Tool | Description |
|---|---|
| `venice_x402_balance` | Check the prepaid x402 credit balance for a wallet address. |
| `venice_x402_top_up_info` | Fetch the top-up payment requirements: the accepted Base and Solana USDC options, each with network, asset, receiver wallet, and minimum amount. Takes no arguments. |
| `venice_x402_transactions` | List recent x402 top-up + debit transactions for a wallet. |

## Configuration

| Env var | Default | Notes |
|---|---|---|
| `VENICE_API_KEY` | _(none)_ | Your Venice API key. The simplest setup. |
| `VENICE_DEFAULT_CHAT_MODEL` | `deepseek-v4-flash-0731` | |
| `VENICE_DEFAULT_IMAGE_MODEL` | `flux-2-pro` | |
| `VENICE_DEFAULT_TTS_MODEL` | `tts-kokoro` | |
| `VENICE_DEFAULT_ASR_MODEL` | `openai/whisper-large-v3` | |
| `VENICE_DISABLE_NSFW` | `0` | Set to `1` to remove NSFW capability notes from tool descriptions. |
| `VENICE_HTTP_TIMEOUT_MS` | `60000` | |
| `VENICE_MAX_VIDEO_RESPONSE_BYTES` | `26214400` (25 MiB) | Maximum completed MP4 bytes buffered and base64-embedded by `venice_video_status`. |
| `VENICE_MAX_IMAGE_RESPONSE_BYTES` | `33554432` (32 MiB) | Maximum response bytes buffered by `venice_image_generate`, `venice_image_edit`, `venice_image_multi_edit`, `venice_image_upscale`, and `venice_image_remove_bg`. Larger results are discarded with an error. |
| `VENICE_MAX_AUDIO_RESPONSE_BYTES` | `33554432` (32 MiB) | Maximum audio bytes buffered and base64-embedded by `venice_tts` and `venice_music_status`. An oversized TTS result is discarded with an error; an oversized music result stays queued for a retry. |
| `VENICE_SIWX_TOKEN` | _(none)_ | **x402** wallet-mode auth token — see **x402** — pay with a wallet. |
| `PORT` | `3333` | HTTP-mode listener. |
| `VENICE_MCP_HOST` | `127.0.0.1` | HTTP-mode bind address. Set to `0.0.0.0` for LAN/container exposure. |
| `VENICE_MCP_AUTH_TOKEN` | _(none)_ | Bearer token required by `/mcp` whenever HTTP mode binds outside loopback. Use a long random value. |
| `VENICE_MCP_ALLOW_UNAUTHENTICATED_HTTP` | `0` | Emergency escape hatch for unauthenticated exposed HTTP mode. Use only behind a trusted authenticated proxy. |
| `VENICE_MCP_ALLOWED_HOSTS` | Localhost authorities on the listener port | Comma-separated exact HTTP Host values, including non-default ports. Set this for a reverse proxy, LAN hostname, or mapped port. No wildcards. |
| `VENICE_MCP_ALLOWED_ORIGINS` | Localhost HTTP origins on the listener port | Comma-separated exact browser origins, including scheme and non-default port. Requests without Origin are accepted for native clients. No wildcards or `null` origins. |
| `VENICE_MCP_MAX_SESSIONS` | `100` | Maximum active Streamable HTTP sessions. |
| `VENICE_MCP_SESSION_TTL_MS` | `1800000` | Idle Streamable HTTP session lifetime before cleanup. |

## Self-hosting (Streamable HTTP)

`/mcp` is a credential-backed tool execution endpoint: callers can spend the configured Venice API key or x402 balance. When HTTP mode binds outside loopback, startup fails unless `VENICE_MCP_AUTH_TOKEN` is set, or `VENICE_MCP_ALLOW_UNAUTHENTICATED_HTTP=1` is explicitly set behind a trusted authenticated proxy.```bash
docker run -p 3333:3333 \
  -e VENICE_API_KEY=&lt;your-venice-api-key&gt; \
  -e VENICE_MCP_AUTH_TOKEN=&lt;choose-a-long-random-token&gt; \
  ghcr.io/veniceai/venice-mcp-server:latest
# server at http://localhost:3333/mcp

Clients should send Authorization: Bearer with HTTP MCP requests. HTTP clients should create new sessions without an mcp-session-id header and then reuse the server-issued session ID; unknown or malformed caller-provided session IDs are rejected. For reproducible production installs, pin the npm package version as shown in the examples instead of using an unversioned latest install path.

HTTP requests to /mcp must also use an allowed Host and, when present, an allowed Origin. The defaults support localhost, 127.0.0.1, and [::1] on the listener port. Configure the public authority in VENICE_MCP_ALLOWED_HOSTS when using a reverse proxy or another hostname, and the browser application's origin in VENICE_MCP_ALLOWED_ORIGINS when needed. Each configured list replaces its default list, so include any local entries you still use. Forwarded headers do not grant trust. These checks also apply when bearer authentication is configured; /healthz remains available for health probes. Set a bearer token even for local HTTP when possible.

The Origin allowlist is a request validation rule; it does not enable CORS or handle browser preflight requests. Cross-origin browser clients need a separately configured trusted proxy or server-side MCP connection.

Or run from source — see Development below.


x402 — pay with a wallet, no account required

> Skip this section if you're using VENICE_API_KEY. Everything below is optional and only matters if you specifically want to pay with a crypto wallet instead of a Venice account.

Venice supports EVM SIWE or Solana SIWX wallet authentication backed by prepaid USDC credit on Base or Solana mainnet, in addition to the normal API key flow. This lets you use Venice with no email, phone, or KYC — your wallet is the only identity.

Two-line config```json

{
"mcpServers": {
"venice": {
"command": "npx",
"args": ["-y", "@veniceai/mcp-server@0.3.0"],
"env": { "VENICE_SIWX_TOKEN": "<base64 signed SIWX payload>" }
}
}
}


The MCP server forwards the existing `VENICE_SIWX_TOKEN` env format using Venice&#x27;s preferred `SIGN-IN-WITH-X` header.

### How it works```
ONE-TIME SETUP (per wallet)
  Sign an EVM SIWE or Solana SIWX message → produces a SIWX token (base64 JSON)
  Set VENICE_SIWX_TOKEN in this MCP server&#x27;s env

TOP UP (when balance is low)
  POST /api/v1/x402/top-up  (no payment header)  →  402 + payment requirements
  Choose a Base or Solana USDC option and sign it in your wallet
  POST /api/v1/x402/top-up with PAYMENT-SIGNATURE: &lt;signed&gt;  →  Venice settles
  the payment and credits your prepaid balance

EVERY INFERENCE CALL
  MCP server sends SIGN-IN-WITH-X: &lt;SIWX token&gt;
  Venice → wallet → credit account → debits and runs inference

This MCP server never sees your private key. EVM/Solana SIWX signing and USDC payment signing happen in your wallet — the server forwards only the signed SIWX token. The top-up helper discovers requirements but does not accept or submit payment signatures.

The helper tools venice_x402_balance, venice_x402_top_up_info, and venice_x402_transactions make balance + top-up flow inspectable from inside the agent.

Why prepaid instead of per-call?

  • ⚡ Latency — once topped up, calls are sub-100ms (no on-chain settlement per call)
  • 🧮 Throughput — Coinbase CDP facilitator settles top-ups in batches
  • 🔒 Privacy — wallet ↔ credit account is the only identity link; no email/phone/KYC
  • 🪙 DIEM shortcut — wallets linked to a Venice user with DIEM staked consume from staking balance, no USDC needed
  • 💸 Min top-up $5 (anti-dust). Minimum balance to inference is $0.10.

Per-call HTTP 402 — not supported

Venice rejects payment headers on inference routes. The preferred PAYMENT-SIGNATURE header is only used when submitting a signed payment to /api/v1/x402/top-up; this MCP server does not submit payments. After an external top-up, Venice debits the wallet's off-chain credit account on inference.

Auth-mode coverage notes

Some Venice endpoints don't accept both auth modes:

Tool API key x402 Notes
venice_list_characters ✓ ✗ Character discovery endpoint is API-key only
venice_get_character ✓ ✗ Character discovery endpoint is API-key only
venice_character_reviews ✓ ✗ Character discovery endpoint is API-key only
venice_x402_balance ✗ ✓ Wallet-bound by design
venice_x402_transactions ✗ ✓ Wallet-bound by design
venice_x402_top_up_info ✓ ✓ Auth-free; same 402 response in both modes

Hybrid

Set both VENICE_API_KEY AND VENICE_SIWX_TOKEN — API key wins. SIWX is only used when the key is absent.


Architecture```

┌──────────────────────┐ stdio OR ┌────────────────────────┐
│ MCP host │ Streamable HTTP │ @veniceai/mcp-server │
│ (Claude / Cursor / ├────────────────────────▶│ - 45 tools │
│ ChatGPT / etc.) │ │ - 3 resources │
└──────────────────────┘ │ - 3 prompts │
│ - header forwarder │
└────────────┬───────────┘
│ HTTPS
│ Authorization: Bearer ***
│ OR
│ SIGN-IN-WITH-X: <SIWX>
▼
┌────────────────────────┐
│ Venice API │
│ api.venice.ai │
└────────────────────────┘


## Tool reference (endpoints + auth modes)

Click to expand — full mapping of tool → Venice endpoint → auth mode

### Inference (API key OR x402 wallet)

| Tool | Endpoint |
|---|---|
| `venice_chat` | `POST /v1/chat/completions` |
| `venice_responses` | `POST /v1/responses` |
| `venice_embeddings` | `POST /v1/embeddings` |
| `venice_image_generate` | `POST /v1/image/generate` |
| `venice_image_edit` | `POST /v1/image/edit` |
| `venice_image_multi_edit` | `POST /v1/image/multi-edit` |
| `venice_image_upscale` | `POST /v1/image/upscale` |
| `venice_image_remove_bg` | `POST /v1/image/background-remove` |
| `venice_video_generate` | `POST /v1/video/queue` |
| `venice_video_status` | `POST /v1/video/retrieve` |
| `venice_video_complete` | `POST /v1/video/complete` |
| `venice_tts` | `POST /v1/audio/speech` |
| `venice_asr` | `POST /v1/audio/transcriptions` |
| `venice_voice_clone` (`create`) | `POST /v1/audio/voices` |
| `venice_music_generate` | `POST /v1/audio/queue` |
| `venice_music_status` | `POST /v1/audio/retrieve` |
| `venice_music_complete` | `POST /v1/audio/complete` |
| `venice_web_search` | `POST /v1/augment/search` |
| `venice_web_scrape` | `POST /v1/augment/scrape` |
| `venice_text_parser` | `POST /v1/augment/text-parser` |
| `venice_crypto_rpc` | `POST /v1/crypto/rpc/:network` |

### Catalog &amp; quotes (auth-free)

| Tool | Endpoint |
|---|---|
| `venice_list_models` | `GET /v1/models?type=…` (`type=all` when omitted) |
| `venice_model_details` | `GET /v1/models?type=:type` (exact ID match in the filtered catalog) |
| `venice_model_traits` | `GET /v1/models/traits` |
| `venice_model_compatibility_mapping` | `GET /v1/models/compatibility_mapping` |
| `venice_voice_clone` (`list`) / `venice://voices` | `GET /v1/models?type=tts` |
| `venice_image_styles` | `GET /v1/image/styles` |
| `venice_audio_quote` | `POST /v1/audio/quote` |
| `venice_video_quote` | `POST /v1/video/quote` |
| `venice_crypto_networks` | `GET /v1/crypto/rpc/networks` |
| `venice_tee_attestation` | `GET /v1/tee/attestation?model=:model&amp;nonce=:64_hex_chars` |
| `venice_tee_signature` | `GET /v1/tee/signature?model=:model&amp;request_id=:completion_id` |

### Characters (API key only)

| Tool | Endpoint |
|---|---|
| `venice_list_characters` | `GET /v1/characters` |
| `venice_get_character` | `GET /v1/characters/:slug` |
| `venice_character_reviews` | `GET /v1/characters/:slug/reviews` |
| `venice_chat_with_character` | `POST /v1/chat/completions` (with `character_slug`) |

### Billing and API-key reads (ADMIN API key only, except rate-limit tools)

| Tool | Endpoint |
|---|---|
| `venice_billing_balance` | `GET /v1/billing/balance` |
| `venice_billing_usage_analytics` | `GET /v1/billing/usage-analytics` |
| `venice_billing_usage_history` | `GET /v1/billing/usage-history` |
| `venice_list_api_keys` | `GET /v1/api_keys` |
| `venice_get_api_key` | `GET /v1/api_keys/:id` |
| `venice_api_key_rate_limits` | `GET /v1/api_keys/rate_limits` (INFERENCE or ADMIN) |
| `venice_api_key_rate_limit_logs` | `GET /v1/api_keys/rate_limits/log` (ADMIN) |

### x402 wallet helpers (SIWX reads + auth-free discovery)

| Tool | Endpoint |
|---|---|
| `venice_x402_balance` | `GET /v1/x402/balance/:wallet` |
| `venice_x402_top_up_info` | `POST /v1/x402/top-up` (no payment) |
| `venice_x402_transactions` | `GET /v1/x402/transactions/:wallet` |

## Development```bash
npm install
npm run build             # generate dist/ locally
npm test                  # build, then run the full test suite
npm run test:unit         # unit tests only
npm run test:integration  # build, then spawn dist/cli.js + a mock Venice over real stdio JSON-RPC
npm start                 # stdio mode
npm run start:http        # http mode on :3333

dist/ is generated by npm run build and is intentionally ignored by git rather than committed. Published npm packages include dist/. Direct source publication runs prepublishOnly; the release workflow builds and tests once, then publishes the resulting package archive without running package lifecycle scripts again.

Releases

Commit matching versions in package.json and package-lock.json before creating the release tag. The release tag must be the package's exact semantic version, optionally prefixed with v. Build metadata such as +build.5 is rejected because npm can normalize it away. The workflow builds the tagged commit and fails if the tag, package version, or lockfile version disagree; it never bumps the version or pushes a follow-up commit.

Build and publication run in separate jobs using Node.js 24 and npm 11.5.1 or newer. Release packing uses the same npm minimum as trusted publishing. This also excludes npm 10, which can run prepare despite --ignore-scripts. The build job has read-only repository permissions, tests the package, and uploads its archive. The publish job verifies the archive's checksum and publishes that exact archive using npm trusted publishing. Already-published versions are skipped. A failed build or version check requires fixing the release inputs before publication.

Test layout```

test/
├── config.test.ts # env parsing, defaults, header precedence
├── format.test.ts # 402 formatter cases
├── venice-client.test.ts # HTTP client + real mock Venice
├── tools.test.ts # tool registry (45 tools) + endpoint/method/body mappings
├── integration.test.ts # end-to-end JSON-RPC over stdio against a mock Venice
└── helpers/
├── stub-client.ts # in-process VeniceClient stub
└── mock-venice-server.ts # real http.Server fake of Venice for integration tests
```

The integration suite spawns the compiled CLI and speaks JSON-RPC on its stdin/stdout, exercising initialize → tools/list → tools/call → resources/list → resources/read against a real HTTP mock Venice in three auth scenarios (API key only, SIWX only, no auth).

…(正文过长,页面只展示前面部分,完整内容见仓库)

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
venice-mcp-server 怎么安装?

在客户端按下面的安装命令接入:npx -y @veniceai/mcp-server@0.2.0。对应的包名是 @veniceai/mcp-server。装完在客户端配置里引用同一个包或端点。

venice-mcp-server 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

venice-mcp-server 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

venice-mcp-server 需要 API Key 吗?

资料标注需要API Key认证,使用前准备好对应凭据,并按最小权限配置。

venice-mcp-server 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

venice-mcp-server 能提供哪些能力?

资料显示能力标签包括 Local Deployment、MCP Server、AI Model Integration、TypeScript、Multimodal Content Generation、Image Generation。具体工具清单以官方文档为准。

venice-mcp-server 需要什么运行环境?

运行时为 node;属于本地进程,需要在本机装好运行环境。

venice-mcp-server 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-10-10。