Onto

io.github.ravixalgorithmPublished by GitHub account ravixalgorithmv1.5.2Updated Oct 24, 2026

Clean Markdown and AI-readability scoring for any URL. Built for AI agents.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingData & Analytics

Overview

AI-generated overview

Onto reads any URL as clean Markdown, scores its AI-readability, and extracts structured data, so an assistant can consume web pages without parsing raw HTML.

What you can do
Read a URL as clean, agent-ready Markdown, optionally bypassing the cache, and get extraction metadata such as size reduction and cache state. Score a URL's AI-readability from 0 to 100 with a letter grade, hallucination risk, and penalties, benefits and recommendations. Read and score in one call, recommended as the default for agent workflows. Batch-read, score or extract many URLs from an explicit list or a whole site discovered via sitemap. Map a site's URLs from its sitemap and on-page links without reading them. Extract the structured data a page already declares, such as JSON-LD, OpenGraph and meta tags.
When to use it
Useful when an assistant needs to read, summarize or compare web pages and raw HTML would waste tokens or invite errors, and when you want a quality signal before trusting a source. Also suited to surveying many pages of a site in one call.
Requirements
A remote endpoint or the local npm package run via npx, so Node.js and npx must be available. An Onto API key in ONTO_API_KEY, obtained from the Onto dashboard; OAuth is declared as required. ONTO_API_BASE optionally overrides the API base URL. Network access to the Onto API and to the target sites.
Before you install
The API key in ONTO_API_KEY is a secret and is sent to the Onto service. Tool calls consume credits: read_url, read_and_score, extract_data and map_site cost 1 each, batch costs one per URL, and score_url is free; the free tier is 1,000 credits per month and paid tiers or credit packs cost money. URLs you submit are fetched by Onto's servers, not yours.

Installation

In SourceWeft

  1. Open Onto in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. 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.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.ravixalgorithm%2Fonto/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "onto": {
      "type": "http",
      "url": "https://api.buildonto.dev/mcp"
    }
  }
}

README

Onto MCP Server

The official Onto Model Context Protocol server. Add clean web content reading and AI-readability scoring to Claude Code, Cursor, Cline, Zed, or any MCP-compatible AI client.

What this does

Onto's MCP server exposes these tools to any AI agent:

  • read_url — Read any URL and get back clean, agent-ready Markdown (typically 10× smaller than raw HTML)
  • score_url — Get the AIO (AI-readability) score for any URL with a breakdown of what helps and what hurts AI consumption
  • read_and_score — Both at once: clean content plus quality assessment so the agent knows how much to trust the source
  • batch — Read, score, or extract many URLs (an explicit list or a whole site) in one call
  • map_site — Discover a site's URLs via its sitemap, without reading them
  • extract_data — Return the structured data a page already declares (JSON-LD, OpenGraph, meta)

Every tool response ends with a one-line ⚡ Onto report — reduction, tokens saved, and AIO score — so the value is visible on every call.

This is the official MCP wrapper for the Onto Read API. It's a thin, deterministic layer: Onto cleans and scores with a rule-based engine (no LLM in the loop), so your agent's own model never has to parse raw HTML.

Why use this?

When AI agents read websites today, they parse hundreds of KB of React noise to find a few KB of actual content. This burns tokens and causes hallucinations.

Onto strips the noise server-side, returns the agent-ready format, and reports a confidence score for the source. One tool call, one accurate answer.

Quick start

1. Get an Onto API key

Sign up at app.buildonto.dev and create an API key at Read → Keys.

Free tier: 1,000 credits / month. No credit card.

2. Install in Claude Code

Add to your Claude Code MCP config:

json
{  "mcpServers": {    "onto": {      "command": "npx",      "args": ["-y", "@ontosdk/mcp@latest"],      "env": {        "ONTO_API_KEY": "onto_sk_live_your_key_here"      }    }  }}

Restart Claude Code. The Onto tools (read_url, score_url, read_and_score, batch, map_site, extract_data) will appear in the available tools list.

3. Install in Cursor

Add the Onto server to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this repo). Or use the UI: Customize (sidebar) → MCPs → add a custom server, same JSON.

json
{  "mcpServers": {    "onto": {      "command": "npx",      "args": ["-y", "@ontosdk/mcp@latest"],      "env": {        "ONTO_API_KEY": "onto_sk_live_your_key_here"      }    }  }}

Fully quit Cursor (Cmd+Q / Ctrl+Q) and reopen.

See examples/ for Cline, Zed, and Continue configs.

4. Use it

In Claude Code or Cursor, try:

Read https://stripe.com/pricing using Onto and summarize the pricing tiers.

The agent calls read_url, gets clean Markdown, and returns an accurate summary without parsing hundreds of KB of layout HTML.

Tools

read_url

Returns clean Markdown for a URL with metadata about the extraction (sizes, reduction %, cache state).

Input:

FieldTypeRequiredDescription
urlstringyesPublicly accessible HTTP(S) URL
freshbooleannoIf true, bypass cache (default: false)

score_url

Returns the AIO (AI-readability) score for a URL — 0-100 with a letter grade, hallucination risk, and a structured list of penalties / benefits / recommendations.

Input:

FieldTypeRequiredDescription
urlstringyesURL to score

read_and_score

Returns clean Markdown plus the AIO score in one call. Recommended default for agentic workflows.

Input: same as read_url.

batch

Process many URLs in one call. N credits — one per URL in the list after the list is known. Failed URLs (ok: false) are refunded. Default mode read-and-score is still N, not 2N. Give an explicit list or a base URL whose pages are auto-discovered.

Input:

FieldTypeRequiredDescription
urlsstring[]one ofExplicit list of URLs (max 50). Use this or site.
sitestringone ofBase URL whose pages are auto-discovered via sitemap. Use this or urls.
mode"read" | "read-and-score" | "extract"noWhat to do per URL (default "read-and-score")
limitnumbernoSite mode only: max pages to discover (default 25, max 50)

map_site

Discover a site's URLs (sitemap → on-page links) without reading them. 1 credit per call (not per discovered URL) — use it to plan which pages to read or batch next.

Input:

FieldTypeRequiredDescription
urlstringyesBase URL of the site to map
limitnumbernoMax URLs to return (default 100, max 1000)

extract_data

Return the structured data a page already declares — JSON-LD, OpenGraph, and meta tags — plus the AIO score. Deterministic; no fields are inferred by a model.

Input:

FieldTypeRequiredDescription
urlstringyesURL to extract structured data from

Pricing

TierMonthly creditsPrice
Free1,000$0
Starter10,000$9
Growth100,000$49
Scale500,000$250
EnterpriseCustomContact sales

MCP tool credits match the live API meter:

ToolCredits
read_url1
read_and_score1
score_url0 (free)
extract_data1
map_site1 per call (not per discovered URL)
batchN — one per URL in the list after the list is known; failed URLs (ok: false) are refunded. Default mode read-and-score is still N, not 2N

Connect / OAuth is not a debit.

Manage your subscription at app.buildonto.dev/read/billing. Credit packs ($5–$200) are available for overflow once you're on a paid tier.

Configuration

Environment variables:

  • ONTO_API_KEY (required) — Your Onto API key from app.buildonto.dev/read/keys
  • ONTO_API_BASE (optional) — Override the API base URL (default: https://api.buildonto.dev)

Troubleshooting

"Invalid Onto API key"

Verify your key at app.buildonto.dev/read/keys. If you recently rotated keys, your MCP config may have a stale value.

"Monthly quota exceeded"

You've used your monthly allotment. Upgrade at app.buildonto.dev/read/billing or wait for the monthly reset. Paid tiers can also top up with credit packs.

Tool doesn't appear in Claude Code / Cursor

  1. Verify the config file is valid JSON
  2. Restart the MCP host (Claude Code, Cursor, etc.)
  3. Check the host's MCP logs for connection errors
  4. Make sure npx is on your PATH

"Request timed out"

The target site may be slow or unreachable. Onto's request timeout is 15 seconds. Retry, or try a different URL.

Links

About Onto

Onto is the compatibility layer for the agent web. Three products on one engine:

  • Read (this MCP server + API) — AI developers read any URL cleanly
  • Serve (Next.js SDK) — Site owners serve clean Markdown to AI crawlers
  • Act (coming Q3 2026) — Agents act on websites through semantic intent

Built for AI agents reading the web. Built so they read it correctly.

License

MIT

Source: README.md at commit ad70f63

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.5.2LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts