FaceabotCapability network for AI agents
‹ Back

The real catalog of tools for AI agents

Google tells you what exists. Faceabot tells you what holds up.

47,766real tools
31,719callable over HTTPS
21,482measured
6,601proven reliable
Web page reader Reliable (measured) · 100% over 86 checks Does the job (tested) · 85/85

Read any web page or URL as clean text or markdown: scrape a website page, articles, docs, blogs; also files of public GitHub repositories.

MCP endpoint : https://faceabot.com/tools-mcp/reader · website · measurements and details
Aginx Browser Being measured · 0% over 1 checks

Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions.

MCP endpoint : https://browser.aginx.net/mcp · website · measurements and details
browser-use Not measured yet

AI browser automation - navigate, click, type, extract content, and run autonomous web tasks

Package pypi : realtimex-browser-use · website · measurements and details
Bintu Web Reader Private (key required) · 100% over 1 checks

Fetch public web pages as clean, token-budgeted text for AI agents.

MCP endpoint : https://bintu-web-reader.mcpize.run/mcp · website · measurements and details
Web Reader & Search (Tanod) Flaky · 90% over 10 checks Fails real tasks · 0/9

Web search for agents: page to Markdown, screenshots, news search, metadata, sitemaps and RDAP.

MCP endpoint : https://tanod.dev/mcp/web · website · measurements and details
Jina Reader Being measured · 0% over 1 checks

Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.

MCP endpoint : https://gateway.pipeworx.io/jina-reader/mcp · website · measurements and details
PDF Reader Not measured yet

MCP server for extracting text, images, tables, links, annotations, and metadata from PDF files.

Package pypi : pdf-insight-mcp · website · measurements and details
ScrapeMole Reader Reliable (measured) · 100% over 36 checks Fails real tasks · 0/36

Pay-per-call x402 web reading: page to Markdown, link previews, RSS feeds, links, sitemaps.

MCP endpoint : https://reader.scrapemole.workers.dev/mcp · website · measurements and details
browser-use Flaky · 86% over 7 checks

Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.

MCP endpoint : https://api.browser-use.com/v3/mcp · website · measurements and details
browser-buddy Not measured yet

Let AI coding agents read pages through your real, logged-in Chrome browser.

Package pypi : browser-buddy-mcp · website · measurements and details
RSS Feed Reader Private (key required)

New items from many RSS, Atom and JSON feeds or websites, with only-new mode and keyword filters.

MCP endpoint : https://mcp.apify.com/?tools=nerolabs/rss-feed-reader · website · measurements and details
Speed Reader Flaky · 75% over 4 checks

Turn any article, document, or chat reply into a one-word-at-a-time RSVP reading session.

MCP endpoint : https://archerionlabs.com/mcp/speedread · website · measurements and details
feed-reader Not measured yet

Fetch and read RSS/Atom feeds from any MCP client.

Package npm : feed-reader-mcp · website · measurements and details
TensorFeed x402 Base Reader Not measured yet

Read-only Base mainnet reader. Verifies x402 payment settlements + AFTA federation status.

Package npm : @tensorfeed/x402-base-mcp · website · measurements and details
lean-reader Not measured yet

Token-minimized URL-to-clean-text reader for LLMs, with a token-savings receipt.

Package npm : lean-reader · website · measurements and details
APEX web reader Being measured · 50% over 2 checks

A real browser for your agent: a page to clean text for $0.009, a 25-page site for $0.14. x402.

MCP endpoint : https://apexfaucet.xyz/api/mcp/web · website · measurements and details
Brainiall Web Private (key required)

Web search, URL content extraction to Markdown, site mapping, and recursive web crawler.

MCP endpoint : https://api.brainiall.com/mcp/web/mcp · website · measurements and details
Proving Lab Reliable (measured) · 100% over 51 checks

Cite or capture a web page; installs the capture extension in Firefox and Chrome.

MCP endpoint : https://provinglab.dev/mcp · website · measurements and details
Lexifye Private (key required)

Build dictionaries & glossaries with AI: entries, senses, versions, print PDF, EPUB, web reader, RTL

MCP endpoint : https://lexifye.publifye.com/mcp · website · measurements and details
agent-web — URL to LLM-ready markdown: a polite, robots-respecting web page reader (free) Reliable (measured) · 100% over 52 checks

URL to clean markdown for LLMs: a polite, robots.txt-respecting web reader. Free, no API key

MCP endpoint : https://agent-web.foomworks.workers.dev/mcp · website · measurements and details

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms