The real catalog of tools for AI agents

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

49,261real tools

32,919callable over HTTPS

22,804measured

6,918proven reliable

Calc Eval Reliable (measured) · 100% over 20 checks

Evaluate a+b style arithmetic. Expression discarded.

MCP endpoint : https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/calc-eval/mcp · website · measurements and details

Web Search API Eval Being measured · 100% over 1 checks Real task being tested · 1/1

Web search API benchmark for AI agents: You.com, Tavily, Exa, Parallel. Results and charts.

MCP endpoint : https://websearch-api-eval.psberkeleymba.workers.dev/mcp · website · measurements and details

IA-QA Eval & RAG — 38 tools Being measured · 100% over 1 checks Real task being tested · 1/1

LLM & RAG evals: hallucination, eval contracts, semantic tests, tokens & model info. Free, no key.

MCP endpoint : https://www.ia-qa.com/mcp/eval · website · measurements and details

Japanese Order Eval Being measured · 0% over 2 checks

Regression checks for Japanese order automations: six free cases, strict JSON scoring and CI gates.

MCP endpoint : https://shigoto-dogu.netlify.app/mcp/order-eval · website · measurements and details

ai-eval Reliable (measured) · 100% over 56 checks

Cloudflare Workers MCP server: ai-eval

MCP endpoint : https://api.lazy-mac.com/ai-eval/mcp · website · measurements and details

Eval Engine API Being measured · 0% over 1 checks

Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.

MCP endpoint : https://eval.zuluworksai.com/mcp · website · measurements and details

Palimpsest — censorship, China economy and model-eval observatory Reliable (measured) · 100% over 56 checks Does the job (tested) · 56/56

Rights-aware censorship, China-economic status, and tamper-evident AI evaluation tools.

MCP endpoint : https://api.seiche.info/palimpsest/mcp · website · measurements and details

WebMCP Eval Private (key required)

Evaluate one public URL for WebMCP readiness: intent, tools observed, recommended, do-not-expose.

MCP endpoint : https://mcp.webmcp-eval.com/mcp · website · measurements and details

chess-eval Reliable (measured) · 100% over 58 checks

Stockfish chess eval: best move, score, principal variation, multipv. $0.005/call via x402.

MCP endpoint : https://chess-eval.x402supply.com/mcp · website · measurements and details

Web Search API Being measured · 0% over 2 checks

Web search returning structured results — titles, URLs, snippets. x402 micropayment.

MCP endpoint : https://web-search.api.klymax402.com/mcp · website · measurements and details

Chipp Analytics and evals Private (key required)

Chipp: conversations, messages, usage and engagement analytics, end users and their memories, and.

MCP endpoint : https://mcp.chipp.ai/mcp/analytics · website · measurements and details

LLM Eval Harness Not measured yet

Run a golden set and gate LLM model swaps on accuracy, with latency and cost per request.

Package oci : ghcr.io/razilzul/llm-eval-harness:1.0.0 · website · measurements and details

GenPark Safe Eval Expression AST Sandbox Not measured yet

Zero-dependency AST safe mathematical and boolean expression evaluator and validator

Package mcpb :

https://github.com/Alpha-Park/genpark-safe-eval-expression-ast-sandbox-skill/releases/download/v1.0.1/genpark-safe-eval-expression-ast-sandbox-skill-v1.0.1.mcpb

· website · measurements and details

AIsa Web Search & Research Private (key required)

Web search and page extraction across several independent search providers.

MCP endpoint : https://mcp.aisa.one/search/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

Iskat — Russian-language web search for agents Being measured · 0% over 1 checks

Russian-language web search for agents: hybrid retrieval, product prices, full page text

MCP endpoint : https://iskat.io/mcp · website · measurements and details

Web Search & Data API Flaky · 86% over 7 checks

Web search, scraping, Google Trends and data lookups. Paid per call in USDC on Base via x402.

MCP endpoint : https://api.kadec0.xyz/mcp · website · measurements and details

CompletionKit Flaky · 96% over 25 checks

Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.

MCP endpoint : https://completionkit.com/mcp · website · measurements and details

AgentsHub Web Search Being measured · 0% over 1 checks

Live web search for AI agents. $0.001/call, x402 on Base, no API key.

MCP endpoint : https://api.agentshub.dev/mcp · website · measurements and details

google-web-search Reliable (measured) · 95% over 20 checks

Google Web Search: Google Web Search API. Search the world’s information, including webpages.

MCP endpoint : https://mcp.jojapi.com/google-web-search · 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