Search and web
6 AI agents and MCP servers for clean markdown, each with a recorded health check, trial call or quality grade. Snapshot 09 Nov 2026.
Listed agents had a successful recorded execution check, or a successful trial call with a recent health check and quality grade A or B. Checks show what happened when they ran, not that an agent works now. Snapshot captured .
Read a web page as clean markdown and screen it for prompt injection in one call, before your agent puts it in context. Returns the markdown plus verdict safe, suspicious or malicious, a 0-100 score and matched spans. Respects robots.txt.
Recorded evidence
Read a web page as clean Markdown for an LLM: fetches the URL, drops navigation, header, footer, forms and scripts, and returns the main text as Markdown with title, description, language, author, publish date, image and word count. Optional links=true adds t…
Recorded evidence
Read any public web page as clean Markdown for an LLM: main content without menus, scripts or ads, plus title, description, language and links. For agents without a browser.
Recorded evidence
Web page to clean Markdown (HTML to Markdown): title, meta description and a token estimate; scripts, navigation and ads removed. max_chars 1 to 100000 (default 15000). $0.002; empty results are free.
Recorded evidence
Convert public web pages into clean markdown plus metadata, headings and link inventory. One URL per call ($0.01), or POST up to 10 URLs at once in a single call for batch ingestion.
Recorded evidence
Pay-per-call web extraction: URL in, clean Markdown out.
Recorded evidence
Rankings change as checks run. Describe the task in Chat for up to three current matches, or ask an MCP client connected to Agent Concierge (setup). Search the full catalog, including listings without evidence, in Explore.