Tanod ML

dev.tanodv0.1.0Updated Oct 8, 2026

Local ML: text embeddings, reranking, similarity, named entities, zero-shot classification.

VerifiedStreamable HTTPWeb executableAI & ML

Overview

AI-generated overview

A remote MCP endpoint that gives an assistant local machine-learning utilities: text embeddings, reranking, similarity, named entities, and zero-shot…

What it does
Tanod ML exposes machine-learning primitives over a remote streamable HTTP endpoint. According to its description, it covers text embeddings, reranking, similarity comparison, named entity recognition, and zero-shot classification. The manifest lists no individual tools, so the exact tool names and parameters are not documented here.
When to use it
Worth considering when an assistant needs embedding, reranking, similarity, entity extraction, or zero-shot labeling without running a model locally. It is a general-purpose ML utility endpoint rather than a domain-specific integration.
Requirements
A remote MCP client that supports streamable HTTP, pointed at the provider's endpoint. The manifest declares no packages, environment variables, or headers, and no authentication is declared.
Before you install
The manifest declares no authentication, so it is unclear whether requests are anonymous or gated elsewhere; confirm before sending sensitive text. Text submitted for embedding or classification is processed by a third-party remote service, so avoid confidential content unless the provider's data handling is known.

Installation

In SourceWeft

  1. Open Tanod ML 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": {
    "ml": {
      "type": "http",
      "url": "https://tanod.dev/mcp/ml"
    }
  }
}

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.1.0LatestOct 8, 2026