codai

ro.codaiv1.0.0Updated Oct 2, 2026

EU-hosted AI gateway: one model name (codai), persistent memory, cloud environments, CI fixes.

VerifiedStreamable HTTPWeb executableAI & ML

Overview

AI-generated overview

A remote EU-hosted AI gateway exposing one model name, codai, with persistent memory, cloud environments, and CI fixes.

What it does
Codai is a remote MCP endpoint that acts as an AI gateway. According to its registry description, it offers a single model name (codai), persistent memory, cloud environments, and CI fixes. No individual tools are listed in the manifest, so the exact tool surface is not documented here.
When to use it
Consider it when you want an EU-hosted gateway that fronts model access and adds persistent memory, cloud environments, and CI fix workflows behind one endpoint. It is less useful if you need a documented, granular tool list before adopting.
Requirements
A remote streamable HTTP endpoint at No packages, environment variables, or headers are declared, and the manifest declares no authentication. Network access to the endpoint is required.
Before you install
The manifest declares no authentication, so it is unclear how access is controlled or what data is sent to the provider. The description mentions persistent memory and CI fixes, which implies stored context and possibly changes to code or pipelines; confirm scope and data handling before use.

Installation

In SourceWeft

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

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "codai": {
      "type": "http",
      "url": "https://ai.codai.ro/mcp"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 2, 2026