Back to Browse

Venice MCP Server

Developer ToolsModerate5.8MCP RegistryLocal
Free

Server data from the Official MCP Registry

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

About

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

Security Report

5.8
Moderate5.8Moderate Risk

The visible code is a conventional Venice API client: it uses Bearer or SIWX auth, refuses redirects, bounds response sizes, and its network access matches its purpose. The score is held down by scanner-flagged on-chain 'call' and 'receipt' tool names that do not appear in the truncated code, by an HTTP transport whose auth and bind settings were not shown, and by a configurable base URL that receives the API key. Supply chain analysis found 1 known vulnerability in dependencies (0 critical, 1 high severity). Package verification found 1 issue.

6 files analyzed ยท 7 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

HTTP Network Access

Connects to external APIs or services over the internet.

env_vars

Check that this permission is expected for this type of plugin.

What You'll Need

Set these up before or after installing:

Venice API key from venice.ai/settings/api. Use an INFERENCE key with a spend limit.Required

Environment variable: VENICE_API_KEY

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@veniceai/mcp-server@0.3.2"
      ],
      "env": {
        "VENICE_API_KEY": "your-venice-api-key-here"
      }
    }
  }
}

Some servers take additional arguments. See the repository for details.

Documentation

View on GitHub

From the project's GitHub README.

@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).

npm License: MIT

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 โ€” 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 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.

๐Ÿ’ฌ Chat & embeddings

ToolDescription
venice_chatChat 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_responsesAlpha, 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_embeddingsCompute embeddings for text input (OpenAI-compatible).
venice_chat_with_characterChat with a Venice character by slug.

๐ŸŽจ Image

ToolDescription
venice_image_generateGenerate 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_editEdit an image with a prompt. Supports free-string sizing, output format, and prompt enhancement; returns a base64 image.
venice_image_multi_editEdit multiple images together with a single prompt (multi-image composition / outpainting), including free-string sizing, quality, output format, and prompt enhancement.
venice_image_upscaleUpscale an image (2โ€“4ร— scale, with a creativity control). Returns base64 PNG.
venice_image_remove_bgRemove image background; returns a transparent PNG.
venice_image_stylesList image style presets available for venice_image_generate.

๐ŸŽฌ Video

ToolDescription
venice_video_generateQueue 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.
venice_video_statusCheck 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_completeMark a completed video as downloaded. Reports server-side deletion only when Venice confirms success.
venice_video_quoteGet a price quote for a video generation BEFORE queuing.

๐Ÿ”Š Audio (TTS / ASR)

ToolDescription
venice_ttsConvert text to speech. Supports cloned voices, temperature, and Venice's streaming flag; MCP returns the completed audio as one buffered result.
venice_asrTranscribe audio from a URL as JSON or text, with optional word and character timestamps.
venice_voice_cloneDiscover 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_<id> handle to pass as the venice_tts voice.
venice_audio_quoteGet a price quote for music generation BEFORE queuing.

๐ŸŽต Music

ToolDescription
venice_music_generateQueue 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_statusCheck status of a queued music job. Returns JSON progress while PROCESSING, then either embedded audio or a download_url resource link.
venice_music_completeMark a completed music job as downloaded and delete server-side media.

๐ŸŒ Web augment

ToolDescription
venice_web_searchSearch 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_scrapeScrape one URL into markdown text.
venice_text_parserExtract text from a document URL (PDF, DOCX, EPUB, PPTX, XLSX, โ€ฆ).

๐Ÿ“š Catalog

ToolDescription
venice_list_modelsPage 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_detailsGet one exact model's full catalog row, including model_spec constraints, capabilities, and pricing.
venice_model_traitsGet the live trait-name to model-id mapping for a model type.
venice_model_compatibility_mappingGet compatible model-name to Venice model-id mappings.
venice_list_charactersList public Venice characters with search, tag/category/model, content, capability, sort, and pagination filters. API key only.
venice_get_characterGet a public character by slug. API key only.
venice_character_reviewsList paginated public reviews for a character. API key only.

๐Ÿ” TEE attestation

ToolDescription
venice_tee_attestationFetch Intel TDX attestation evidence, optional NVIDIA evidence, and the model signing key using a caller-generated 32-byte nonce.
venice_tee_signatureFetch 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 or application/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 use application/vnd.openxmlformats-officedocument.wordprocessingml.document, for MP3 use audio/mpeg, for M4A use audio/mp4, and for Ogg audio use audio/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_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'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: "video/mp4", 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.

โ›“๏ธ Crypto

ToolDescription
venice_crypto_networksList the live network slugs supported by the crypto RPC proxy. No authentication required.
venice_crypto_rpcProxy 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 idempotency_key.

๐Ÿ’ฐ Billing (ADMIN API key only)

ToolDescription
venice_billing_balanceGet current USD, DIEM, and bundled-credit availability.
venice_billing_usage_analyticsGet beta aggregate usage by date, model, and API key using a lookback or custom date range.
venice_billing_usage_historyWalk 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.

๐Ÿ”‘ API keys

ToolDescription
venice_list_api_keysList active key metadata without full key secrets. ADMIN API key only.
venice_get_api_keyGet one key's metadata, usage, balances, and rate limits. ADMIN API key only.
venice_api_key_rate_limitsGet current balances, access status, tier, and model limits. API key only.
venice_api_key_rate_limit_logsGet 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.

๐Ÿ’ณ x402 wallet helpers

Optional โ€” only needed if you authenticate with a wallet via x402 instead of an API key. See x402 โ€” pay with a wallet.

ToolDescription
venice_x402_balanceCheck the prepaid x402 credit balance for a wallet address.
venice_x402_top_up_infoFetch 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_transactionsList recent x402 top-up + debit transactions for a wallet.

Configuration

Env varDefaultNotes
VENICE_API_KEY(none)Your Venice API key. The simplest setup.
VENICE_DEFAULT_CHAT_MODELdeepseek-v4-flash-0731
VENICE_DEFAULT_IMAGE_MODELflux-2-pro
VENICE_DEFAULT_TTS_MODELtts-kokoro
VENICE_DEFAULT_ASR_MODELopenai/whisper-large-v3
VENICE_DISABLE_NSFW0Set to 1 to remove NSFW capability notes from tool descriptions, hide the uncensored research and NSFW creative writing prompt templates, and drop "uncensored" from the server instructions.
VENICE_SEND_CLIENT_INFO1Set to 0 to leave the MCP client's name and version out of the User-Agent sent to Venice.
VENICE_HTTP_TIMEOUT_MS60000
VENICE_MAX_VIDEO_RESPONSE_BYTES26214400 (25 MiB)Maximum completed MP4 bytes buffered and base64-embedded by venice_video_status.
VENICE_MAX_IMAGE_RESPONSE_BYTES33554432 (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_BYTES33554432 (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 โ€” see x402 โ€” pay with a wallet.
PORT3333HTTP-mode listener.
VENICE_MCP_HOST127.0.0.1HTTP-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_HTTP0Emergency escape hatch for unauthenticated exposed HTTP mode. Use only behind a trusted authenticated proxy.
VENICE_MCP_ALLOWED_HOSTSLocalhost authorities on the listener portComma-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_ORIGINSLocalhost HTTP origins on the listener portComma-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_SESSIONS100Maximum active Streamable HTTP sessions.
VENICE_MCP_SESSION_TTL_MS1800000Idle 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/mcp

VENICE_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 โ€” see Development below.


x402 โ€” 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 โ€” 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_TOKEN on every call, so only the first wallet-authenticated request succeeds; later calls return 401 until you sign a new token and restart the server (#96). Use VENICE_API_KEY for 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)  โ†’  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>  โ†’  Venice settles
  the payment and credits your prepaid balance

EACH WALLET-AUTHENTICATED REQUEST (manual renewal)
  Sign a fresh EVM SIWE or Solana SIWX message โ†’ 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 token

This MCP server never sees your private key. EVM/Solana SIWX signing and USDC payment signing happen in your wallet โ€” 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?

  • โšก Latency โ€” once topped up, calls are sub-100ms (no on-chain settlement per call)
  • ๐Ÿงฎ Throughput โ€” Coinbase CDP facilitator settles top-ups in batches
  • ๐Ÿ”’ Privacy โ€” wallet โ†” credit account is the only identity link; no email/phone/KYC
  • ๐Ÿช™ DIEM shortcut โ€” wallets linked to a Venice user with DIEM staked consume from staking balance, no USDC needed
  • ๐Ÿ’ธ Min top-up $5 (anti-dust). Minimum balance to inference is $0.10.

Per-call HTTP 402 โ€” 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:

ToolAPI keyx402Notes
venice_list_charactersโœ“โœ—Character discovery endpoint is API-key only
venice_get_characterโœ“โœ—Character discovery endpoint is API-key only
venice_character_reviewsโœ“โœ—Character discovery endpoint is API-key only
venice_x402_balanceโœ—โœ“Wallet-bound by design
venice_x402_transactionsโœ—โœ“Wallet-bound by design
venice_x402_top_up_infoโœ“โœ“Auth-free; same 402 response in both modes

Hybrid

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


Architecture

โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”        stdio  OR        โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚  MCP host            โ”‚      Streamable HTTP    โ”‚  @veniceai/mcp-server  โ”‚
โ”‚  (Claude / Cursor /  โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ–ถโ”‚  - 45 tools            โ”‚
โ”‚   ChatGPT / etc.)    โ”‚                         โ”‚  - 3 resources         โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜                         โ”‚  - 9 prompts           โ”‚
                                                 โ”‚  - header forwarder    โ”‚
                                                 โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                                              โ”‚ HTTPS
                                                              โ”‚   Authorization: Bearer ***
                                                              โ”‚   OR
                                                              โ”‚   SIGN-IN-WITH-X: <SIWX>
                                                              โ–ผ
                                                 โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                                                 โ”‚  Venice API            โ”‚
                                                 โ”‚  api.venice.ai         โ”‚
                                                 โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜

Tool reference (endpoints + auth modes)

Inference (API key OR x402 wallet)

ToolEndpoint
venice_chatPOST /v1/chat/completions
venice_responsesPOST /v1/responses
venice_embeddingsPOST /v1/embeddings
venice_image_generatePOST /v1/image/generate
venice_image_editPOST /v1/image/edit
venice_image_multi_editPOST /v1/image/multi-edit
venice_image_upscalePOST /v1/image/upscale
venice_image_remove_bgPOST /v1/image/background-remove
venice_video_generatePOST /v1/video/queue
venice_video_statusPOST /v1/video/retrieve
venice_video_completePOST /v1/video/complete
venice_ttsPOST /v1/audio/speech
venice_asrPOST /v1/audio/transcriptions
venice_voice_clone (create)POST /v1/audio/voices
venice_music_generatePOST /v1/audio/queue
venice_music_statusPOST /v1/audio/retrieve
venice_music_completePOST /v1/audio/complete
venice_web_searchPOST /v1/augment/search
venice_web_scrapePOST /v1/augment/scrape
venice_text_parserPOST /v1/augment/text-parser
venice_crypto_rpcPOST /v1/crypto/rpc/:network

Catalog & quotes (auth-free)

ToolEndpoint
venice_list_modelsGET /v1/models?type=โ€ฆ (type=all when omitted)
venice_model_detailsGET /v1/models?type=:type (exact ID match in the filtered catalog)
venice_model_traitsGET /v1/models/traits
venice_model_compatibility_mappingGET /v1/models/compatibility_mapping
venice_voice_clone (list) / venice://voicesGET /v1/models?type=tts
venice_image_stylesGET /v1/image/styles
venice_audio_quotePOST /v1/audio/quote
venice_video_quotePOST /v1/video/quote
venice_crypto_networksGET /v1/crypto/rpc/networks
venice_tee_attestationGET /v1/tee/attestation?model=:model&nonce=:64_hex_chars
venice_tee_signatureGET /v1/tee/signature?model=:model&request_id=:completion_id

Characters (API key only)

ToolEndpoint
venice_list_charactersGET /v1/characters
venice_get_characterGET /v1/characters/:slug
venice_character_reviewsGET /v1/characters/:slug/reviews
venice_chat_with_characterPOST /v1/chat/completions (with character_slug)

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

ToolEndpoint
venice_billing_balanceGET /v1/billing/balance
venice_billing_usage_analyticsGET /v1/billing/usage-analytics
venice_billing_usage_historyGET /v1/billing/usage-history
venice_list_api_keysGET /v1/api_keys
venice_get_api_keyGET /v1/api_keys/:id
venice_api_key_rate_limitsGET /v1/api_keys/rate_limits (INFERENCE or ADMIN)
venice_api_key_rate_limit_logsGET /v1/api_keys/rate_limits/log (ADMIN)

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

ToolEndpoint
venice_x402_balanceGET /v1/x402/balance/:wallet
venice_x402_top_up_infoPOST /v1/x402/top-up (no payment)
venice_x402_transactionsGET /v1/x402/transactions/:wallet

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 :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.

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/
โ”œโ”€โ”€ config.test.ts             # env parsing, defaults, header precedence
โ”œโ”€โ”€ format.test.ts             # 402 formatter cases
โ”œโ”€โ”€ venice-client.test.ts      # HTTP client + real mock Venice
โ”œโ”€โ”€ tools.test.ts              # tool registry (45 tools) + endpoint/method/body mappings
โ”œโ”€โ”€ integration.test.ts        # end-to-end JSON-RPC over stdio against a mock Venice
โ””โ”€โ”€ helpers/
    โ”œโ”€โ”€ stub-client.ts         # in-process VeniceClient stub
    โ””โ”€โ”€ 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 โ†’ tools/list โ†’ tools/call โ†’ resources/list โ†’ 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 mainnetโ€”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, gitignoredโ€”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.

Phasenpm scriptCostWhat it tests
createtest:e2e:createfreeGenerate / reload wallet, print address + balance
emptytest:e2e:emptyfreeSIWX โ†’ MCP venice_chat โ†’ expect 402 with helpful diagnostics
topuptest:e2e:topup$5 USDC + gasSign EIP-3009 โ†’ POST /api/v1/x402/top-up โ†’ settle on-chain via CDP facilitator
fundedtest:e2e:funded~$0.001 / callSIWX โ†’ MCP venice_chat โ†’ real LLM completion charged to prepaid balance
balancetest:e2e:balancefreeRead on-chain USDC + Venice prepaid via venice_x402_balance tool
safetest:e2e:safefreecreate + empty + balance (no money spent)
# Comprehensive โ€” all 45 tools ร— both auth modes, side-by-side report (mint is always skipped)
env VENICE_API_KEY=<your-venice-api-key> npm run test:e2e:all-tools

FAQ

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 โ€” 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 โ€” 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

Reviews

No reviews yet

Be the first to review this server!