About adorbis-mcp
adorbis-mcp is an MCP server for Adorbis AI, giving developers using MCP-compatible tools access to chat, coding, and analysis. It automatically routes requests across available models and also supports multi-turn conversations.
Key features
- 01Automatic routing to available models
- 02General chat and multi-turn conversations
- 03Code generation, debugging, and review
- 04Math and multi-step reasoning
- 05Writing and balance checks
Use cases
- 01Generate or review code in a coding workflow
- 02Handle continuing requests with multi-turn chat
- 03Check available departments and account balance
MCP support
The MCP server exposes Adorbis AI chat, coding, reasoning, writing, balance, and model-list tools to MCP clients. It calls the Adorbis API with one ADORBIS_API_KEY and routes requests automatically.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @adorbistech/mcp-serverADORBIS_API_KEYSecretAdorbis API key from ai.adorbistech.comLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
7Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| message | string | Yes | The message or question to send to the AI |
| department | enum | No | AI department to use: 'adorbis/quick' (fast responses), 'adorbis/coder' (code), 'adorbis/auto' (smart routing), 'adorbis/write' (writing), 'adorbis/reason' (analysis)adorbis/coder | adorbis/quick | adorbis/auto | adorbis/write | adorbis/reason |
| max_tokens | integer | No | Maximum tokens in the response |
| system_prompt | string | No | Optional system prompt to set context for the AI |
Details
From the project README@adorbistech/mcp-server
Adorbis AI MCP Server
One API key. 40+ models. Auto-routed. Use Adorbis AI from Claude Code, Cursor, Cline, and any MCP-compatible tool.
Install
Option 1 — Clone and run locally (recommended, works on all platforms)
git clone https://github.com/adorbistech/adorbis-mcp
cd adorbis-mcp
npm install
npm run build
Then point your tool to node /path/to/adorbis-mcp/dist/index.js.
Claude Code
Add to ~/.claude.json:
{
"mcpServers": {
"adorbis": {
"command": "node",
"args": ["/path/to/adorbis-mcp/dist/index.js"],
"env": {
"ADORBIS_API_KEY": "your_key_here"
}
}
}
}
Windows path example:
"args": ["D:\\Ai-Adorbis\\MCP\\dist\\index.js"]
Mac/Linux path example:
"args": ["/home/user/adorbis-mcp/dist/index.js"]
Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"adorbis": {
"command": "node",
"args": ["/path/to/adorbis-mcp/dist/index.js"],
"env": {
"ADORBIS_API_KEY": "your_key_here"
}
}
}
}
Cline (VS Code)
Add to Cline MCP settings:
{
"adorbis": {
"command": "node",
"args": ["/path/to/adorbis-mcp/dist/index.js"],
"env": {
"ADORBIS_API_KEY": "your_key_here"
}
}
}
Option 2 — npx (Mac/Linux only)
# Mac/Linux
ADORBIS_API_KEY=your_key npx @adorbistech/mcp-server
Note:
npxinstall is not recommended on Windows due to path resolution issues. Use the clone method above.
Auto-configure with CLI
npx adorbis-init --mcps
Automatically writes the correct MCP config for every tool you have configured.
Available Tools
Once connected, your AI assistant has access to 7 tools:
| Tool | Description |
|---|---|
adorbis_chat | General AI chat — auto-routes to best model |
adorbis_code | Code generation, debugging, review |
adorbis_reason | Math, logic, multi-step analysis |
adorbis_write | Documentation, articles, emails |
adorbis_balance | Check connection and credit status |
adorbis_models | List all available departments |
adorbis_multi_turn | Multi-turn conversation with history |
Usage examples
Check my Adorbis balance
Use adorbis_code to write a TypeScript debounce function
What Adorbis departments are available?
Use adorbis_reason to analyze the time complexity of merge sort
Departments
| Department | Best for | Speed |
|---|---|---|
adorbis/quick | Chat, Q&A, simple tasks | Fastest |
adorbis/coder | Code generation, debugging, review | Fast |
adorbis/auto | Mixed workloads, smart routing | Varies |
adorbis/write | Documentation, articles, emails | Medium |
adorbis/reason | Math, logic, complex analysis | Thorough |
How Adorbis AI works
Your tool (Claude Code / Cursor / Cline)
│
▼ MCP call
@adorbistech/mcp-server
│
▼ HTTPS
api.adorbistech.com ←── your single API key
│
┌───────┴────────┐
│ Department │
│ routing │
└───────┬────────┘
│
┌─────────┼──────────┐
▼ ▼ ▼
Gemini DeepSeek Claude
Flash V3 Sonnet
│
▼
Best model
for your task
Adorbis monitors model health, latency, and cost in real time. When you send a request, it routes to the best available model automatically. No manual model switching. No vendor lock-in.
Environment Variables
| Variable | Required | Description |
|---|---|---|
ADORBIS_API_KEY | Yes | Your Adorbis API key |
Get a free key (1,000 credits/month, no credit card) at https://ai.adorbistech.com
Plans
| Plan | Price | Credits |
|---|---|---|
| Free | $0/mo | 1,000 AC |
| Starter | $10/mo | 15,000 AC |
| Pro | $30/mo | 50,000 AC |
| Business | $100/mo | 200,000 AC |
1 AC = $0.001 of underlying compute. Upgrade →
Also available
- VS Code Extension —
ext install adorbis.adorbis-ai - CLI setup wizard —
npx adorbis-init - Full docs — ai.adorbistech.com/docs
Requirements
- Node.js >= 18
- An Adorbis API key — get one free
Contributing
Issues and PRs welcome at github.com/adorbistech/adorbis-mcp
License
MIT © Adorbis Technologies LLC
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.