IndieML Substance API

io.github.ezchxv0.1.14Updated Oct 1, 2026

Scores text for substance, depth, and clarity in under 25ms.

VerifiedStreamable HTTPWeb executableAI & MLData & AnalyticsKnowledge & Memory

Overview

AI-generated overview

Scores text for substance, depth, and clarity through a hosted API, letting an assistant rank or filter content quickly.

What it does
IndieML's Substance API evaluates a piece of text and returns scores for substance, depth, and clarity, reportedly in under 25ms. It is a hosted, transformer-based scoring service positioned as a fast, inexpensive pre-screening step rather than a full LLM. The MCP server exposes this scoring endpoint to assistants over Streamable HTTP, and the same service is also reachable via REST, a Python SDK, and an npx bridge for stdio clients.
When to use it
Useful when an assistant needs to triage or rank large volumes of text cheaply: pre-filtering documents before vectorization or indexing, ranking feeds and archives by information density, or routing support tickets, feedback, and user-generated content by depth instead of keywords or sentiment.
Requirements
A remote endpoint at indieml.app reached over Streamable HTTP, plus an IndieML API key sent in the X-Api-Key header. For stdio-only clients such as Claude Desktop, the npx mcp-remote bridge requires Node.js v20 or higher and the key supplied through the INDIEML_API_KEY environment variable. The Python SDK requires Python 3.11 or higher. Network access is required.
Before you install
The service is remote, so any text submitted for scoring is sent to a third party; avoid sending confidential or regulated content. An API key is required and passed as X-Api-Key (or INDIEML_API_KEY for the bridge), so store it as a secret rather than in shared configuration. The README does not state pricing, rate limits, or data retention, so confirm those before relying on it in production pipelines.

Installation

In SourceWeft

  1. Open IndieML Substance API 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": {
    "indieml": {
      "type": "http",
      "url": "https://indieml.app/mcp/"
    }
  }
}

README

IndieML - Substance API

A lightweight, transformer-based API that evaluates text for substance, depth, and clarity in under 25ms while achieving 87% of the accuracy of a full-scale LLM. This package provides REST API, Python SDK, and MCP configuration details to natively connect the hosted Substance API to a wide variety of applications. For more information, including API key requests, please visit https://indieml.app.

REST API

For integrations outside the Python and MCP ecosystems (such as standard OpenAI function calling, custom AI scripts, or raw HTTP requests), the hosted endpoint accepts standard JSON payload requests.

cURL

bash
curl -X POST https://indieml.app/v1/score/substance \  -H "X-API-Key: YOUR_API_KEY_HERE" \  -H "Content-Type: application/json" \  -d '{"input_text": "This is a test run."}'

Python (Requests)

python
import requests
response = requests.post(    "https://indieml.app/v1/score/substance",    headers={"X-API-Key": "YOUR_API_KEY_HERE"},    json={"input_text": "This is a test run."})print(response.json())

Node.js (Fetch)

javascript
const response = await fetch("https://indieml.app/v1/score/substance", {  method: "POST",  headers: {    "X-API-Key": "YOUR_API_KEY_HERE",    "Content-Type": "application/json"  },  body: JSON.stringify({ input_text: "This is a test run." })});console.log(await response.json());

Python SDK

Installation (requires Python 3.11 or higher)

bash
pip install indieml

Usage

python
from indieml import Substance
# Initialize the APIapi = Substance(api_key="YOUR_API_KEY_HERE")
# Evaluate text for substance, depth, and clarityresult = api.score("This is a test run.")print(result)

MCP Server Integration

You can integrate the Substance API into AI coding assistants by routing them to our cloud-native ASGI endpoints.

Cursor, ChatGPT, and Claude Code (Streamable HTTP)

For agents that support native Streamable HTTP / SSE configurations, provide the remote URL and authorization header directly:

json
{  "mcpServers": {    "indieml": {      "type": "http",      "url": "https://indieml.app/mcp/",      "headers": {        "X-API-Key": "YOUR_API_KEY_HERE"      }    }  }}

Claude Desktop (stdio via npx Bridge)

For local Linux, Mac, and Windows clients that require stdio transport, use the npx mcp-remote bridge to route the connection to the cloud endpoint. Node.js v20+ is required. Ensure your OS environment variables include INDIEML_API_KEY.

json
{  "mcpServers": {    "indieml": {      "command": "npx",      "args": [        "-y",        "mcp-remote",        "https://indieml.app/mcp/",        "--header",        "X-Api-Key:${INDIEML_API_KEY}"      ],      "env": {        "INDIEML_API_KEY": "YOUR_API_KEY_HERE"      }    }  }}

Applications & Use Cases

The Substance API is a fast and inexpensive pre-screening tool designed to integrate with your existing classification pipeline.

While it evaluates substance across any text, it is uniquely suited for high-volume, automated data pipelines:

1. RAG & AI Knowledge-Base Preprocessing

Pre-filter text before expensive LLM vectorization and processing.

  • Knowledge Portals: Filter out bloated, low-signal documentation prior to indexing.
  • Document Archives: Rank corporate or research archives based on actual information density.
  • Feed Aggregation: Rank news, newsletters, or educational content by structural depth rather than just recency or click-through rates.

2. Automated Content Triage & Large-Scale Screening

Route inbound text based on substance, clarity, and depth rather than relying solely on keywords or sentiment analysis.

  • Support Tickets: Identify highly detailed bug reports and instantly route them past basic classification bots to human operators.
  • Customer Feedback: Isolate high-quality product critiques from generic "it's great" or "it's broken" noise.
  • User-Generated Content: Surface high-effort, high-value forum posts and survey responses while automatically burying low-effort spam.

Source: README.md at commit 15658e5

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.1.14LatestOct 1, 2026