ohu
Turn Any Website Into Clean Fine-Tuning Data & RAG Context in Seconds.
What it can do
- Crawl: Crawl a URL and extract content in multiple formats (markdown, HTML, text, links, metadata)
- Markdown: Convert a URL to clean Markdown format
- Extract: Extract structured data from a URL using CSS selectors
What data it sees
Do you need an account
An API key from the service settings is required
Turn Any Website Into Clean Fine-Tuning Data & RAG Context in Seconds. Without Scraping Bans or Prompt Injections. Ohu handles the dirty work by bypassing DOM noise, parsing PDFs, auditing hidden AI injection attacks, and feeding your LLMs pristine JSONL datasets with a single API call.
How to connect
How to connect ohu to Claude
The server address to paste into Claude settings:
https://ohu--sluxia.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect ohu to ChatGPT
The server address to paste into ChatGPT settings:
https://ohu--sluxia.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect ohu to Cursor
The server address to paste into Cursor settings:
https://ohu--sluxia.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (17)
Raw names from tools/list. Only developers need these.
| crawl | Crawl a URL and extract content in multiple formats (markdown, HTML, text, links, metadata) |
| markdown | Convert a URL to clean Markdown format |
| extract | Extract structured data from a URL using CSS selectors |
| search | Search the web using multiple providers (Bing, DuckDuckGo, Wikipedia) |
| aeo | Analyze a URL for Answer Engine Optimization (AEO) readiness — scores AI crawler access, schema markup, semantic content, and machine readability |
| rag_chunk | Chunk content for RAG (Retrieval-Augmented Generation) with vector DB exports for Pinecone, Qdrant, Weaviate, and Chroma |
| llms_generator | Generate llms.txt and llms-full.txt manifests for a website — makes your site discoverable by LLMs |
| brand_mentions | Monitor brand mentions across the web with sentiment analysis |
| pdf_to_markdown | Convert a PDF URL to structured Markdown |
| table_extract | Extract HTML tables as structured JSON and Markdown |
| clean_article | Extract the main article body from a URL (reader-mode distillation) |
| code_extract | Extract code blocks from a URL, grouped by language |
| media_extractor | Find all media assets (video, audio, images, embeds) on a page |
| link_graph | Categorize and map all links on a page (internal, external, files, social) |
| geo_competitor | Head-to-head GEO (Generative Engine Optimization) competitor comparison |
| synthetic_dataset | Generate synthetic QA instruction pairs for LLM fine-tuning (JSONL, OpenAI, DPO formats) |
| security_audit | Scan a page for prompt injection vectors and leaked secrets/API keys |