Agentdiet is answering right now. Last checked 12 min ago. It exposes 4 tools.
Strips 85-97% of HTML bloat into clean Markdown, <200-token skeletons, or BM25 excerpts via MCP.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 14 October 2026. No other catalogue keeps this.
A tool that vanishes takes a piece of your agent with it, and the change arrives silently. Watch this server and every such change lands in your inbox.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 min ago.
claude mcp add agentdiet --transport http https://agentdiet-72343955726.us-central1.run.app/mcp
{
"mcpServers": {
"agentdiet": {
"url": "https://agentdiet-72343955726.us-central1.run.app/mcp"
}
}
}
[mcp_servers.agentdiet]
url = "https://agentdiet-72343955726.us-central1.run.app/mcp"
{
"mcpServers": {
"agentdiet": {
"url": "https://agentdiet-72343955726.us-central1.run.app/mcp"
}
}
}
{
"mcpServers": {
"agentdiet": {
"url": "https://agentdiet-72343955726.us-central1.run.app/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
get_agent_wallet_status
distill_webpage
extract_structured_data
recon_webpage_skeleton
Tools this server used to expose. Anything built against them stopped working on the day they went.
audit_github_repository
audit_x402_and_a2a_endpoint
discover_and_verify_x402_mcp_tools
enrich_company_domain
extract_ecommerce_catalog
fetch_arxiv_research_digest
generate_site_llms_txt
get_dex_token_intelligence
get_public_company_sec_intel
recon_domain_osint
repair_malformed_json
scan_onchain_address_risk
scan_prompt_injection
search_clean_agent_web
verify_email_deliverability
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://agentdiet-72343955726.us-central1.run.app/mcp | streamable-http | answering | 216 ms | 12 min ago |
Convert public HTML or a public URL into token-dense Markdown through one remote MCP tool.
Turn any URL or HTML into clean markdown, tables, links or JSON for agents
Turn HTML or Markdown into a clean, styled PDF and get a download link.
Clean raw HTML into LLM-ready text before agents spend tokens.
Any file → clean Markdown for AI agents: PDF, Office, EPUB, HTML, images, audio/video. Local MCP.
Any URL to clean, LLM-ready Markdown for RAG. Strips ads, nav, and boilerplate.
Convert HTML to Markdown or strip to plain text. For web-scraping agents.
Convert files, URLs, and documents to clean, AI-ready Markdown via MCP.
Answers built from our own checks of this server.