The real catalog of tools for AI agents

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

47,279real tools

31,340callable over HTTPS

21,411measured

6,530proven reliable

Hive Exchange Being measured · 0% over 1 checks

Agent-to-agent capability exchange and prediction markets

MCP endpoint : https://hive-mcp-exchange.onrender.com/mcp · website · measurements and details

Token Diet Being measured · 0% over 1 checks

LLM token optimization gateway implementing semantic pruning.

MCP endpoint : https://token-diet-mcp.vercel.app/api/mcp · measurements and details

Qumge: Agent Capabilities & Skills Reliable (measured) · 100% over 51 checks

Find, call and pay per call: the capability layer for agents, plus skills. One key or OAuth.

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

AgentDiet — A2A Context Window Distiller & 85% Token Diet Reliable (measured) · 100% over 10 checks Does the job (tested) · 10/10

Prunes 85% of HTML/DOM/JSON token bloat into semantic Markdown for LLM agents via x402 & MPP on agentdiet.dev.

MCP endpoint : https://agentdiet.dev/mcp · measurements and details

The capability diet: tool pruning for agents Private (key required)

Per-task-type tool manifests with reversible JIT demotion, compiled from fleet telemetry.

MCP endpoint : https://textforagents.com/products/capability-diet-tool-pruning/mcp · website · measurements and details

MechanoFab Flaky · 83% over 6 checks

Manufacturing capability graph for AI agents: materials, processes, tolerances, and instant quotes.

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

warden Not measured yet

Verified context layer for AI coding agents — prunes, compresses, indexes, remembers. 32 MCP tools.

Package npm : warden-ai · website · measurements and details

ME Human Capability Reliable (measured) · 100% over 11 checks Does the job (tested) · 11/11

Human judgment for AI agents: discover capabilities, get quotes, and track paid human tasks.

MCP endpoint : https://mcp-production-ff29.up.railway.app/mcp · website · measurements and details

Pollinations Private (key required)

Access Pollinations models and API capabilities through agent tools.

MCP endpoint : https://gen.pollinations.ai/mcp/pollinations · website · measurements and details

LIGHTS OUT WORKS Capability Search Flaky · 80% over 5 checks Does the job (tested) · 4/4

Evidence-labeled Method search for AI Agents; optional contributor and Gateway discovery.

MCP endpoint : https://lightsoutworks.org/mcp · website · measurements and details

AgentDiet AI Token Diet & Context Window Distiller Reliable (measured) · 100% over 10 checks Does the job (tested) · 10/10

Strips 85-97% of HTML/DOM bloat into clean Markdown or JSON with cryptographic ROI proof.

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

Euvra Being measured · 0% over 1 checks

Discover, compare, route, and execute machine-accessible capabilities for AI agents.

MCP endpoint : https://euvra.dev/mcp · measurements and details

Nanotoll MCP Flaky · 75% over 4 checks Fails real tasks · 0/3

7 agent tools (prune, convert, estimate, diff, patch, generate, validate). USDC on Base L2.

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

agentskin Not measured yet

The Semantic Layer for AI Agents. Prunes noisy API data by 70%+ for token-efficient reasoning.

Package npm : agentskin · website · measurements and details

ChainFX Capability Network Being measured · 0% over 1 checks

Agent Pay and planning graph for stablecoin commerce.

MCP endpoint : https://api.chainfx.store/mcp/initialize · website · measurements and details

AgentDiet ArXiv AI/CS Paper Search & Structured Token-Diet Digest Reliable (measured) · 100% over 10 checks Does the job (tested) · 10/10

Queries ArXiv for AI/CS/math papers and returns structured abstracts, authors, PDF links, and Bib.

MCP endpoint : https://arxiv-digest.agentdiet.dev/mcp · website · measurements and details

Human Capability Registry Flaky · 80% over 5 checks Does the job (tested) · 4/4

Search, hire and pay a verified human per job from any AI. Humans are handles; AIs call them.

MCP endpoint : https://humancard-registry.vercel.app/api/mcp · website · measurements and details

AccessEXL Agent Capabilities Private (key required)

Find and run governed Excel model capabilities that your organisation has published for AI agents.

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

Revuo Flaky · 89% over 9 checks Does the job (tested) · 7/7

Agent-callable B2B SaaS directory: capability-structured, continuously verified listings.

MCP endpoint : https://www.revuo.ai/api/mcp · measurements and details

Imperium RAG-Diet — Web & Document Context Distiller (85-97% Token Savings) Reliable (measured) · 100% over 6 checks Does the job (tested) · 6/6

Strips 85-97% of HTML/DOM boilerplate into clean Markdown, skeletons, or BM25-ranked RAG chunks.

MCP endpoint : https://rag-diet.agentdiet.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