MrVinci Claude API

One host, landing and API together

The marketing pages you're reading and the API share this domain — the browser gets HTML at /, your client hits the API path below.

What you need

• Node.js 18+ (for the npx installer)
• A MrVinci key — sk_mv_… — from an admin
• A supported client: Claude Code, Cursor, Cline, or any Anthropic SDK

The one-minute path

The npx mrvinciapi wizard asks for your key, lets you pick your client, writes the config, and verifies the connection. Zero dependencies, pure Node — it only edits local files, never sends anything anywhere.

npx mrvinciapi

# Claude Code
npx mrvinciapi sk_mv_YOUR_KEY
# Codex (OpenAI Responses)
npx mrvinciapi sk_mv_YOUR_KEY --codex
# Cursor / Cline
npx mrvinciapi sk_mv_YOUR_KEY --openai

# print env, change nothing
npx mrvinciapi sk_mv_YOUR_KEY --print
# revert Claude Code
npx mrvinciapi --undo

Thinking is passed through

The model's chain of thought streams back as native Anthropic thinking blocks, so Claude Code shows reasoning as it works — including in extended-thinking / ultra modes. Send "thinking": {"type":"disabled"} to turn it off for a request.

Configure it yourself

Claude Code

Add to ~/.claude/settings.json:

{
  "env": {
    "ANTHROPIC_AUTH_TOKEN": "sk_mv_YOUR_KEY",
    "ANTHROPIC_BASE_URL": "https://claude.mrvinci.app"
  }
}

Cursor / Cline

Base URL https://claude.mrvinci.app, API key sk_mv_…, model claude-opus-4-8.

Claude Desktop

Menu → Developer → Configure Third-Party Inference. Set Connection to Gateway, then:

• Gateway base URL — https://claude.mrvinci.app
• Gateway API key — sk_mv_… · auth scheme bearer
• Turn on Model discovery — the picker auto-fills from /v1/models with the Claude lineup.

POST /v1/messages

curl https://claude.mrvinci.app/v1/messages \
  -H "x-api-key: sk_mv_YOUR_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-opus-4-8",
    "max_tokens": 256,
    "messages": [{"role":"user","content":"Hello"}]
  }'

Authenticate with x-api-key: sk_mv_… or Authorization: Bearer sk_mv_…. List models at /v1/models.

Tools, streaming, vision, caching

Everything the Messages API supports works through the gateway — these aren't add-ons, they're the same wire format you already use.

Tool use (function calling)

Send a tools array exactly as the Anthropic SDK does — tool_use blocks stream back exactly as the API specifies. Agents like Claude Code, Cursor, and Cline run their whole tool loop through the gateway unmodified.

curl https://claude.mrvinci.app/v1/messages \
  -H "x-api-key: sk_mv_YOUR_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-opus-4-8",
    "max_tokens": 1024,
    "tools": [{
      "name": "get_weather",
      "description": "Current weather for a city",
      "input_schema": {"type":"object","properties":{"city":{"type":"string"}},"required":["city"]}
    }],
    "messages": [{"role":"user","content":"Weather in Florence?"}]
  }'

Error reference

Errors come back in the Anthropic error envelope, so SDK retry logic behaves correctly. The rule: 429 and 529 are retryable (wait, then retry); 4xx everything else means fix the request.

When something's off