Venice MCP Server
OfficialVenice MCP Server exposes 45 tools across Venice AI modalities plus catalog, TEE, crypto, billing, API-key, and x402 wallet operations for any MCP host.
Chat/embeddings: OpenAI-compatible chat, Responses API, character chat, embeddings, function tools, reasoning, and multimodal inputs.
Images: generate, edit, multi-edit, upscale, remove background, and list styles.
Video: quote, queue, poll status, and complete/cleanup jobs across many video models with reference/audio inputs.
Audio/music: TTS, ASR transcription with paging, voice cloning/listing, and music quote/generate/status/complete.
Web/docs: search via Brave/Google/Exa, scrape URLs to markdown, and parse PDFs/DOCX/EPUB/PPTX/XLSX.
Catalog/characters: list models, traits, compatibility mappings, model details, image styles, characters, and character reviews.
TEE security: fetch attestation evidence and response signatures for TEE-capable text models.
Crypto: list RPC networks and proxy single or batched JSON-RPC requests.
Billing/API keys: admin balance, usage analytics/history, API-key metadata, and rate-limit details/logs.
x402 wallet: check balance, fetch top-up requirements, and list transaction history.
Auth: API key or x402 wallet; some admin and character endpoints are API-key only.
Provides a tool to proxy JSON-RPC calls (e.g., eth_call, eth_blockNumber) to the Ethereum network.
Provides a tool to proxy JSON-RPC calls (e.g., eth_call, eth_blockNumber) to the Optimism network.
Provides a tool to proxy JSON-RPC calls (e.g., eth_call, eth_blockNumber) to the Polygon network.
Provides a tool to transcribe YouTube video URLs into text.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Venice MCP Server generate an image of a dragon in a medieval castle"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@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:
{
"mcpServers": {
"venice": {
"command": "npx",
"args": ["-y", "@veniceai/mcp-server@0.3.2"],
"env": { "VENICE_API_KEY": "<your-venice-api-key>" }
}
}
}3. Restart your MCP host
That's it. Type a prompt — your agent now has chat, image, video, music, TTS, ASR, and 39 more Venice tools.
Related MCP server: fieldcure-mcp-essentials
What you get
45 tools spanning every Venice modality plus billing and API-key operations, 3 resources (venice://models, venice://styles, venice://voices) and 9 prompt templates: uncensored research, NSFW creative writing and an image style explorer, plus six creator workflows (create image, create video, create audio, YouTube thumbnail, product photoshoot and explainer video) that walk the agent from a brief to a finished result, quoting paid video and music jobs first. Hosts such as Claude Code show them as slash commands, for example /mcp__venice__create-video. VENICE_DISABLE_NSFW=1 hides the first two. The voices resource is built live from each TTS model'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's possible behavior; hosts should still enforce their own approval policy.
💬 Chat & embeddings
Tool | Description |
| 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. |
| 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. |
| Compute embeddings for text input (OpenAI-compatible). |
| Chat with a Venice character by slug. |
🎨 Image
Tool | Description |
| Generate an image. Supports model-specific width/height or free-string |
| Edit an image with a prompt. Supports free-string sizing, output format, and prompt enhancement; returns a base64 image. |
| Edit multiple images together with a single prompt (multi-image composition / outpainting), including free-string sizing, quality, output format, and prompt enhancement. |
| Upscale an image (2–4× scale, with a |
| Remove image background; returns a transparent PNG. |
| List image style presets available for |
🎬 Video
Tool | Description |
| Queue a video generation. Supports Veo 3.1, Kling, Wan, Seedance (incl. reference-to-video), MiniMax, PixVerse, Runway, LTX, Grok Imagine, and others. Accepts image, video, audio, reference inputs, and the Seedance consent attestation flow where applicable. |
| Check status of a queued video job. Returns JSON progress while |
| Mark a completed video as downloaded. Reports server-side deletion only when Venice confirms success. |
| Get a price quote for a video generation BEFORE queuing. |
🔊 Audio (TTS / ASR)
Tool | Description |
| Convert text to speech. Supports cloned voices, temperature, and Venice's streaming flag; MCP returns the completed audio as one buffered result. |
| Transcribe audio from a URL as JSON or text, with optional word and character timestamps. |
| Discover live model-scoped voice metadata, or clone a voice from a sample audio URL for |
| Get a price quote for music generation BEFORE queuing. |
🎵 Music
Tool | Description |
| Queue music generation. Uses the live QueueAudioRequest fields: |
| Check status of a queued music job. Returns JSON progress while |
| Mark a completed music job as downloaded and delete server-side media. |
🌐 Web augment
Tool | Description |
| Search with Brave (default, Zero Data Retention), Google (proxied/anonymized by Venice), or Exa (Zero Data Retention). Returns the parsed |
| Scrape one URL into markdown text. |
| Extract text from a document URL (PDF, DOCX, EPUB, PPTX, XLSX, …). |
📚 Catalog
Tool | Description |
| Page through the live model catalog, every type by default, with server-side filtering for |
| Get one exact model's full catalog row, including |
| Get the live trait-name to model-id mapping for a model type. |
| Get compatible model-name to Venice model-id mappings. |
| List public Venice characters with search, tag/category/model, content, capability, sort, and pagination filters. API key only. |
| Get a public character by slug. API key only. |
| List paginated public reviews for a character. API key only. |
🔐 TEE attestation
Tool | Description |
| Fetch Intel TDX attestation evidence, optional NVIDIA evidence, and the model signing key using a caller-generated 32-byte nonce. |
| 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.
Inline uploads for image upscale, ASR, voice cloning, and document parsing should include a concrete MIME type, for example
data:application/pdf;base64,.... Base64 and percent-encoded payloads preserve the original bytes; malformed base64 is rejected before upload. When the type is omitted orapplication/octet-stream, the server infers PDF, PNG, JPEG, GIF, WebP, WAV, or FLAC from the file signature and supplies a matching filename extension. Other formats require an explicit type; for DOCX useapplication/vnd.openxmlformats-officedocument.wordprocessingml.document, for MP3 useaudio/mpeg, for M4A useaudio/mp4, and for Ogg audio useaudio/ogg. Shared container signatures and audio tags do not uniquely identify these formats, so these inputs are rejected locally until a concrete type is supplied.venice_embeddingsaccepts 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_ratioandresolutionvalues remain free strings because supported values vary by model. Venice validates them. Whenenhance_promptis applied, image generate/edit/multi-edit results include the URL-decodedenhanced_promptreturned inx-venice-enhanced-prompt. Image responses are capped atVENICE_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_consentresponses: the tool returns Venice's policy text, affected media roles, and next step. The threeconsents.seedanceflags are legal attestations and must only be set totrueafter the user explicitly confirms all three statements. Consent is never a content-policy bypass.Completed videos may arrive as
video/mp4or as JSON with adownload_url. Binary completions are returned as an embedded MCP resource (blob,mimeType: "video/mp4", syntheticvenice://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 thedownload_urlas an MCP resource link instead of fetching that URL. Because that link stops working once the stored media is removed,delete_media_on_completionis not applied todownload_urlresults: download the file first, then callvenice_video_complete(and optionally send an HTTPDELETEto the link to revoke it). For VPS / Grok Imagine Private models,download_urlis returned only on queue; pass that URL intovenice_video_statusso aCOMPLETEDretrieve 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 syntheticvenice://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 adownload_urlreturn it as an MCP resource link; as with video,delete_media_on_completionis not applied to them: download the file first, then callvenice_music_complete.
⛓️ Crypto
Tool | Description |
| List the live network slugs supported by the crypto RPC proxy. No authentication required. |
| Proxy one JSON-RPC request or a batch of up to 100 requests. Returns compact JSON (max 64 KiB) plus Venice's credit, cost, and idempotent-replay headers. Transaction broadcasts must be sent as single requests with |
💰 Billing (ADMIN API key only)
Tool | Description |
| Get current USD, DIEM, and bundled-credit availability. |
| Get beta aggregate usage by date, model, and API key using a lookback or custom date range. |
| 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 |
| List active key metadata without full key secrets. ADMIN API key only. |
| Get one key's metadata, usage, balances, and rate limits. ADMIN API key only. |
| Get current balances, access status, tier, and model limits. API key only. |
| 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
Optional — only needed if you authenticate with a wallet via x402 instead of an API key. See x402 — pay with a wallet.
Tool | Description |
| Check the prepaid x402 credit balance for a wallet address. |
| 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. |
| List recent x402 top-up + debit transactions for a wallet. |
Configuration
Env var | Default | Notes |
| (none) | Your Venice API key. The simplest setup. |
|
| |
|
| |
|
| |
|
| |
|
| Set to |
|
| Set to |
|
| |
|
| Maximum completed MP4 bytes buffered and base64-embedded by |
|
| Maximum response bytes buffered by |
|
| Maximum audio bytes buffered and base64-embedded by |
| (none) | x402 wallet-mode auth token — see x402 — pay with a wallet. |
|
| HTTP-mode listener. |
|
| HTTP-mode bind address. Set to |
| (none) | Bearer token required by |
|
| Emergency escape hatch for unauthenticated exposed HTTP mode. Use only behind a trusted authenticated proxy. |
| 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. |
| 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 |
|
| Maximum active Streamable HTTP sessions. |
|
| 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.
A loopback bind needs no token and starts without one, but it is not guarded by default: any local process can then call /mcp and spend the server's Venice credentials. Startup warns whenever the posture is unguarded, so set VENICE_MCP_AUTH_TOKEN even for local HTTP when more than one user or process shares the machine.
VENICE_API_KEY='<your-venice-api-key>' \
VENICE_MCP_AUTH_TOKEN='<choose-a-long-random-token>' \
VENICE_MCP_HOST=0.0.0.0 \
npx -y @veniceai/mcp-server@0.3.2 --http
# server at http://localhost:3333/mcpVENICE_MCP_HOST=0.0.0.0 makes the server reachable beyond loopback; leave it out to stay on loopback. No container image is published yet, so to run it in a container, build one from this repo's Dockerfile.
Clients should send Authorization: Bearer <choose-a-long-random-token> 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. A rejected request gets a 403 whose message names the variable to set, or says the header is invalid when it is missing, repeated, or malformed (such as Origin: null) and so can't be allowlisted. The server logs each rejected value once, up to 100 per process. 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.
One-off wallet config
{
"mcpServers": {
"venice": {
"command": "npx",
"args": ["-y", "@veniceai/mcp-server@0.3.2"],
"env": { "VENICE_SIWX_TOKEN": "<base64 signed SIWX payload>" }
}
}
}The MCP server forwards the fixed VENICE_SIWX_TOKEN using Venice's preferred SIGN-IN-WITH-X header; it does not refresh the token.
Known limitation: Venice accepts each signed SIWX message only once, and only within 5 minutes of signing. The server sends the same
VENICE_SIWX_TOKENon every call, so only the first wallet-authenticated request succeeds; later calls return401until you sign a new token and restart the server (#96). UseVENICE_API_KEYfor anything beyond a one-off call.
How it works
TOP UP (when balance is low, outside this server)
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: <signed> → Venice settles
the payment and credits your prepaid balance
EACH WALLET-AUTHENTICATED REQUEST (manual renewal)
Sign a fresh EVM SIWE or Solana SIWX message → SIWX token (base64 JSON)
Set VENICE_SIWX_TOKEN and start or restart this MCP server
Make one request within 5 minutes of signing
MCP server sends SIGN-IN-WITH-X: <SIWX token>
Venice authenticates the wallet; inference debits its prepaid balance
Before another authenticated request, repeat with a new tokenThis 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 |
| ✓ | ✗ | Character discovery endpoint is API-key only |
| ✓ | ✗ | Character discovery endpoint is API-key only |
| ✓ | ✗ | Character discovery endpoint is API-key only |
| ✗ | ✓ | Wallet-bound by design |
| ✗ | ✓ | Wallet-bound by design |
| ✓ | ✓ | 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 │
└──────────────────────┘ │ - 9 prompts │
│ - header forwarder │
└────────────┬───────────┘
│ HTTPS
│ Authorization: Bearer ***
│ OR
│ SIGN-IN-WITH-X: <SIWX>
▼
┌────────────────────────┐
│ Venice API │
│ api.venice.ai │
└────────────────────────┘Tool reference (endpoints + auth modes)
Inference (API key OR x402 wallet)
Tool | Endpoint |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Catalog & quotes (auth-free)
Tool | Endpoint |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Characters (API key only)
Tool | Endpoint |
|
|
|
|
|
|
|
|
Billing and API-key reads (ADMIN API key only, except rate-limit tools)
Tool | Endpoint |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
x402 wallet helpers (SIWX reads + auth-free discovery)
Tool | Endpoint |
|
|
|
|
|
|
Development
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 :3333dist/ 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.
Published packages also bundle every production dependency at the version in package-lock.json (bundleDependencies), so npx @veniceai/mcp-server@<version> runs exactly the tested release and resolves nothing from the registry at install time.
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 testsThe 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).
Security regression tests exercise HTTP Host/Origin validation, pre-parser authentication and transport cleanup using local fixtures and synthetic credentials.
End-to-end with live Venice + Base EVM harness
test/e2e/ currently exercises the EVM rail against the real Venice API and real Base mainnet—not a mock. Venice and the MCP x402 helpers support both Base and Solana, but this harness generates a throwaway EVM wallet and signs SIWE + EIP-3009 payloads with viem. The wallet is persisted at .e2e-wallet.json (chmod 600, gitignored—never commit).
Each harness mode passes its intended credentials explicitly: wallet-mode children clear any inherited API key, and API-key children clear any inherited SIWX token. This keeps the two authentication runs independent even when the parent environment contains both credentials.
Phase | npm script | Cost | What it tests |
|
| free | Generate / reload wallet, print address + balance |
|
| free | SIWX → MCP |
|
| $5 USDC + gas | Sign EIP-3009 → POST |
|
| ~$0.001 / call | SIWX → MCP |
|
| free | Read on-chain USDC + Venice prepaid via |
|
| free |
|
# Comprehensive — all 45 tools × both auth modes, side-by-side report (mint is always skipped)
env VENICE_API_KEY=<your-venice-api-key> npm run test:e2e:all-toolsFAQ
Do I have to deal with crypto?
No. The simple path is VENICE_API_KEY + a normal Venice account. x402 is an option for users who want a wallet-only flow.
Where does the wallet's private key live? Not in this server. You sign the EVM SIWE or Solana SIWX message and any USDC top-up payment in your own wallet. The server only sees signed payloads and never accepts a private key.
Minimum top-up? $5 USD (anti-dust). Minimum balance to call inference is $0.10. Default suggested top-up is $10.
Privacy guarantees?
No email, phone, or KYC is required on the SIWX path. venice_tee_attestation and venice_tee_signature return hardware evidence for the caller to verify. This server does not encrypt chat. Its requests to Venice name the MCP client and this server in the User-Agent, for example mcp-claude-code/2.0.14 @veniceai/mcp-server/0.3.1, so Venice can see which agents use it. Set VENICE_SEND_CLIENT_INFO=0 to send only this server's name.
DIEM staking? If your wallet is linked to a Venice user with DIEM staked, calls consume from the staking balance instead of USDC credits — no top-up needed.
Getting 402 errors even though I have an API key?
The most common cause is that VENICE_API_KEY isn't being forwarded to the MCP server process. Most MCP hosts (Claude Desktop, Cursor, Codex, etc.) only pass environment variables that are explicitly listed in the "env" block of your MCP config — system-level env vars are not automatically inherited. Make sure your config looks like this:
{
"mcpServers": {
"venice": {
"command": "npx",
"args": ["-y", "@veniceai/mcp-server@0.3.2"],
"env": { "VENICE_API_KEY": "<your-venice-api-key>" }
}
}
}If the key is missing, blank or an unfilled placeholder such as ${VENICE_API_KEY}, the server falls back to x402 mode and returns a 402 payment challenge. For a placeholder, it also logs a warning to stderr at startup.
Support
Maintained by Venice AI. Report bugs and request features in GitHub issues. For account or billing help, email support@venice.ai.
License
MIT
Available Tools
45 toolsvenice_api_key_rate_limit_logsVenice API Key Rate Limit LogsARead-onlyIdempotent
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.
Inputs: no named parameters.
venice_api_key_rate_limitsVenice API Key Rate LimitsARead-onlyIdempotent
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.
Inputs: no named parameters.
venice_asrVenice ASR (Speech-to-Text)A
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.
Inputs: model, language, audio_url, timestamps, +5 more.
venice_audio_quoteVenice Music Cost QuoteARead-onlyIdempotent
Get a price quote for a music generation BEFORE queuing. Useful for budgeting. No authentication required.
Inputs: model (required), character_count, duration_seconds.
venice_billing_balanceVenice Billing BalanceARead-onlyIdempotent
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.
Inputs: no named parameters.
venice_billing_usage_analyticsVenice Billing Usage AnalyticsARead-onlyIdempotent
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.
Inputs: end_date, lookback, start_date.
venice_billing_usage_historyVenice Billing Usage HistoryARead-onlyIdempotent
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.
Inputs: cursor, format, currency, page_size, +2 more.
venice_character_reviewsVenice Character ReviewsBRead-onlyIdempotent
List paginated public reviews for a Venice character. API key required — this endpoint does not accept x402 wallet auth.
Inputs: slug (required), page, pageSize.
venice_chatVenice Chat (LLM)A
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.
Inputs: messages (required), stop, model, tools, +14 more.
venice_chat_with_characterVenice Character ChatA
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.
Inputs: messages (required), character_slug (required), model, max_tokens, +1 more.
venice_crypto_networksVenice Crypto RPC NetworksARead-onlyIdempotent
List the live, authoritative network slugs accepted by venice_crypto_rpc. No authentication required.
Inputs: no named parameters.
venice_crypto_rpcVenice Crypto RPC ProxyADestructive
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.
Inputs: network (required), request, rpc_method, rpc_params, +1 more.
venice_embeddingsVenice EmbeddingsA
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.
Inputs: input (required), model (required), encoding_format.
venice_get_api_keyVenice Get API Key DetailsARead-onlyIdempotent
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.
Inputs: id (required).
venice_get_characterVenice Get CharacterARead-onlyIdempotent
Get one public Venice character by slug. API key required — this endpoint does not accept x402 wallet auth.
Inputs: slug (required).
venice_image_editVenice Image EditB
Edit an image with a prompt. Returns base64 PNG. Supports x402 wallet auth (no Venice account needed) and API key.
Inputs: prompt (required), image_url (required), model, safe_mode, +4 more.
venice_image_generateVenice Image GenerateA
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.
Inputs: prompt (required), seed, model, steps, +14 more.
venice_image_multi_editVenice Image Multi-EditB
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.
Inputs: prompt (required), image_urls (required), model, quality, +4 more.
venice_image_remove_bgVenice Image Background RemoveB
Remove image background; returns a transparent PNG (base64). Supports x402 wallet auth (no Venice account needed) and API key.
Inputs: image_url (required).
venice_image_stylesVenice Image StylesARead-onlyIdempotent
List image style presets available for venice_image_generate. No authentication required.
Inputs: no named parameters.
venice_image_upscaleVenice Image UpscaleA
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.
Inputs: image_url (required), scale, creativity.
venice_list_api_keysVenice List API KeysARead-onlyIdempotent
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.
Inputs: no named parameters.
venice_list_charactersVenice List CharactersBRead-onlyIdempotent
List public Venice characters. API key required — this endpoint does not accept x402 wallet auth.
Inputs: tag, tags, isPro, limit, +8 more.
venice_list_modelsVenice List ModelsARead-onlyIdempotent
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.
Inputs: type, limit, offset, verbose.
venice_model_compatibility_mappingVenice Model Compatibility MappingARead-onlyIdempotent
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.
Inputs: type.
venice_model_detailsVenice Model DetailsARead-onlyIdempotent
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.
Inputs: type (required), model_id (required).
venice_model_traitsVenice Model TraitsBRead-onlyIdempotent
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.
Inputs: type.
venice_music_completeVenice Music Complete (cleanup)ADestructiveIdempotent
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.
Inputs: model (required), queue_id (required).
venice_music_generateVenice Music QueueA
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.
Inputs: model (required), prompt (required), loop, speed, +8 more.
venice_music_statusVenice Music Retrieve / StatusADestructiveIdempotent
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.
Inputs: model (required), queue_id (required), delete_media_on_completion.
venice_responsesVenice Responses APIB
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.
Inputs: input (required), model, top_p, reasoning, +3 more.
venice_tee_attestationVenice TEE AttestationARead-onlyIdempotent
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.
Inputs: model (required), nonce (required).
venice_tee_signatureVenice TEE Response SignatureARead-onlyIdempotent
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.
Inputs: model (required), request_id (required).
venice_text_parserVenice Text Parser (PDF/DOCX/EPUB/PPTX/XLSX)B
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.
Inputs: url (required).
venice_ttsVenice TTS (Speech)A
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.
Inputs: input (required), model, speed, voice, +3 more.
venice_video_completeVenice Video Complete (cleanup)BDestructiveIdempotent
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.
Inputs: model (required), queue_id (required).
venice_video_generateVenice Video QueueA
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.
Inputs: model (required), prompt (required), duration (required), seed, +18 more.
venice_video_quoteVenice Video Cost QuoteARead-onlyIdempotent
Get a price quote for a video generation BEFORE queuing. No authentication required.
Inputs: model (required), duration (required).
venice_video_statusVenice Video Retrieve / StatusADestructiveIdempotent
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.
Inputs: model (required), queue_id (required), download_url, delete_media_on_completion.
venice_voice_cloneVenice Voice Clone / ListA
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.
Inputs: action (required), model, sample_url.
venice_web_scrapeVenice Web ScrapeB
Scrape one URL into markdown text. Supports x402 wallet auth (no Venice account needed) and API key.
Inputs: url (required), format.
venice_web_searchVenice Web SearchA
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.
Inputs: query (required), limit, search_provider.
venice_x402_balanceVenice x402 Wallet BalanceARead-onlyIdempotent
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.
Inputs: wallet_address (required).
venice_x402_top_up_infoVenice x402 Top-up RequirementsARead-onlyIdempotent
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.
Inputs: no named parameters.
venice_x402_transactionsVenice x402 Transaction HistoryARead-onlyIdempotent
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.
Inputs: wallet_address (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 45 tools
Most tools target a clearly distinct resource+operation (image_generate vs image_edit vs image_upscale, video_status vs video_complete), so an agent can usually pick correctly. The main soft spots are the three chat entry points (venice_chat, venice_responses, venice_chat_with_character) and the near-overlapping venice_api_key_rate_limits vs venice_get_api_key, which also reports rate limits, plus four model-metadata tools whose boundaries require careful reading.
Casing and the `venice_` prefix are perfectly consistent snake_case, which helps a lot. However word order is mixed: noun-first compounds (venice_image_generate, venice_billing_balance, venice_model_details) coexist with verb-first (venice_list_models, venice_get_character, venice_list_api_keys) and bare acronym names (venice_tts, venice_asr, venice_chat), so the pattern is readable but not predictable.
45 tools is heavy, but the server fronts a genuinely broad platform (text, image, video, music, audio, search, crypto RPC, TEE, characters, billing, x402), so most tools map to a real endpoint. There is still consolidation slack: four model-metadata tools, three API-key tools, four billing tools, and paired quote/status/complete triples could be collapsed.
Coverage is unusually thorough: generation, polling, and cleanup exist for both video and music, plus image transforms, TTS/ASR/voice cloning, search/scrape, model discovery, billing, and x402 auth paths. Minor gaps remain, notably no API-key creation/rotation or revocation, and no character creation, but agents can work around these via other channels.
Maintenance
Related MCP Connectors
214 tools for AI agents over one MCP endpoint: image, video, audio, 3D, data, storage, mail, GPUs.
AI video, image and audio generation with 140+ AI models from any MCP agent
Generate images, video, audio and short films with 140+ AI models from any MCP client.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Related MCP Servers
- AlicenseBqualityDmaintenanceOperator-tuned MCP server for Venice AI, providing 31 tools for chat, image, video, audio, and music generation with curated presets and workflow prompts.31MIT
- AlicenseNot gradedqualityCmaintenanceProvides 20 essential tools including HTTP requests, web search, file I/O, shell commands, and persistent memory for any MCP client, with zero configuration required.MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI clients like Claude and ChatGPT to generate images and videos, animate images, create lip-synced videos, list TTS voices, and manage media via remote MCP tools.-
- AlicenseAqualityBmaintenanceEnables video and image generation from any MCP client, with support for models like Veo 3.1, Grok Imagine, and Nano Banana, including text-to-video, image-to-video, image generation and editing.478 npmMIT