Adorbis Mcp

io.github.adorbistechPublished by GitHub account adorbistechv1.0.2Updated Oct 24, 2026

Adorbis AI MCP server. One key, 40+ models, auto-routed.

VerifiedSTDIODesktop onlyDeveloper ToolsAI & ML

Overview

AI-generated overview

Adorbis AI gateway server that gives an assistant chat, code, reasoning and writing tools routed across 40+ models with one API key.

What you can do
  • Send general chat prompts that auto-route to a suitable model
  • Generate, debug and review code
  • Run math, logic and multi-step analysis
  • Draft documentation, articles and emails
  • Hold multi-turn conversations with history
  • Check credit balance and list available model departments
When to use it
Useful when you want a single key and one MCP server to reach several underlying models for coding, reasoning and writing tasks from Claude Code, Cursor, Cline or another MCP client, instead of configuring each provider separately.
Requirements
Node.js 18 or newer and a local install (clone and build, or npx on Mac/Linux). An Adorbis API key supplied in the ADORBIS_API_KEY environment variable; a free tier of 1,000 credits per month is offered. Network access to the Adorbis API is required.
Before you install
The ADORBIS_API_KEY is a billable credential: prompts and code are sent to Adorbis and onward to third-party models, and paid plans consume credits (1 AC = $0.001 of compute). Review what you send, since requests leave your machine. The npx install is noted as unreliable on Windows.

Installation

In SourceWeft

  1. Open Adorbis Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

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.

[npm version] [license] [node]

Get a free API key · Documentation · Dashboard

Install

Option 1 — Clone and run locally (recommended, works on all platforms)

bash
git clone https://github.com/adorbistech/adorbis-mcpcd adorbis-mcpnpm installnpm run build

Then point your tool to node /path/to/adorbis-mcp/dist/index.js.

Claude Code

Add to ~/.claude.json:

json
{  "mcpServers": {    "adorbis": {      "command": "node",      "args": ["/path/to/adorbis-mcp/dist/index.js"],      "env": {        "ADORBIS_API_KEY": "your_key_here"      }    }  }}

Windows path example:

json
"args": ["D:\\Ai-Adorbis\\MCP\\dist\\index.js"]

Mac/Linux path example:

json
"args": ["/home/user/adorbis-mcp/dist/index.js"]

Cursor

Add to ~/.cursor/mcp.json:

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:

json
{  "adorbis": {    "command": "node",    "args": ["/path/to/adorbis-mcp/dist/index.js"],    "env": {      "ADORBIS_API_KEY": "your_key_here"    }  }}

Option 2 — npx (Mac/Linux only)

bash
# Mac/LinuxADORBIS_API_KEY=your_key npx @adorbistech/mcp-server

Note: npx install is not recommended on Windows due to path resolution issues. Use the clone method above.

Auto-configure with CLI

bash
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:

ToolDescription
adorbis_chatGeneral AI chat — auto-routes to best model
adorbis_codeCode generation, debugging, review
adorbis_reasonMath, logic, multi-step analysis
adorbis_writeDocumentation, articles, emails
adorbis_balanceCheck connection and credit status
adorbis_modelsList all available departments
adorbis_multi_turnMulti-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

DepartmentBest forSpeed
adorbis/quickChat, Q&A, simple tasksFastest
adorbis/coderCode generation, debugging, reviewFast
adorbis/autoMixed workloads, smart routingVaries
adorbis/writeDocumentation, articles, emailsMedium
adorbis/reasonMath, logic, complex analysisThorough

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

VariableRequiredDescription
ADORBIS_API_KEYYesYour Adorbis API key

Get a free key (1,000 credits/month, no credit card) at https://ai.adorbistech.com

Plans

PlanPriceCredits
Free$0/mo1,000 AC
Starter$10/mo15,000 AC
Pro$30/mo50,000 AC
Business$100/mo200,000 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

Contributing

Issues and PRs welcome at github.com/adorbistech/adorbis-mcp

License

MIT © Adorbis Technologies LLC

Source: README.md at commit 0a4ee5f

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.2LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.