Divinci AI

ai.divinciv1.0.0Updated Sep 29, 2026

Release management and QA for custom AI assistants: RAG, releases, scored QA, signed TrustBench runs

VerifiedStreamable HTTPWeb executableDeveloper ToolsAI & ML

Overview

AI-generated overview

Divinci AI is a remote MCP endpoint for release management and QA of custom AI assistants, covering RAG, releases, scored QA and signed TrustBench runs.

What it does
The registry describes it as release management and QA tooling for custom AI assistants, spanning RAG, releases, scored QA and signed TrustBench runs. It is offered as a remote streamable HTTP endpoint, so an assistant connects to it rather than running it locally. No individual tools are listed in the supplied manifest, so the exact operations available are not documented here.
When to use it
Consider it when you manage custom AI assistants and want release and quality-assurance steps, such as scored evaluations or signed benchmark runs, available to an assistant. It is less relevant if you only need general-purpose tools unrelated to assistant release management.
Requirements
A remote MCP client that supports streamable HTTP, connecting to the provider's endpoint. No packages, environment variables or headers are declared, and the manifest declares no authentication, so any account or credential requirement is not documented in the supplied data.
Before you install
The manifest declares no authentication, environment variables or headers, so it is unclear what credentials, if any, the endpoint expects or what data it receives. Because the server concerns releases and QA of AI assistants, assume it may read or change assistant configurations and evaluation results; verify the provider's access and data-handling terms before connecting.

Installation

In SourceWeft

  1. Open Divinci AI 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": {
    "divinci": {
      "type": "http",
      "url": "https://mcp.divinci.app/mcp"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestSep 29, 2026