tavya

io.tavyav1.0.0Updated Oct 7, 2026

Run and manage AI agent tasks on tavya: create, search and steer tasks, read wikis, call the API.

VerifiedStreamable HTTPWeb executableAI & ML

Overview

AI-generated overview

Lets an assistant create, search, and steer AI agent tasks on the tavya platform and read its wikis.

What it does
This remote MCP server connects an assistant to tavya, a platform for running and managing AI agent tasks. According to the registry description, it lets the assistant create tasks, search existing tasks, and steer them, as well as read wikis and call the platform API. No individual tools are listed in the manifest, so the exact tool set is not documented here.
When to use it
Consider it when you already use tavya to run AI agent tasks and want an assistant to create, find, or adjust those tasks and read related wiki content from within a conversation. It is not useful if you do not use the tavya platform.
Requirements
A remote streamable HTTP endpoint at nothing to install locally. The manifest declares no authentication, environment variables, or headers, but a tavya account may still be needed in practice.
Before you install
The manifest declares no authentication, so it is unclear how access is controlled or whether the endpoint is open. Task creation and steering can change state on the tavya platform, and content sent to it leaves your machine for a third-party service.

Installation

In SourceWeft

  1. Open tavya 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": {
    "tavya": {
      "type": "http",
      "url": "https://tavya.io/mcp"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 7, 2026