FaceabotFREN
‹ Back

The real catalog of tools for AI agents

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

44,737real tools
29,284callable over HTTPS
19,874measured
6,054proven reliable
AgentKernel AI model data Reliable (measured) · 100% over 16 checks Does the job (tested) · 16/16

Live prices, rankings, licences and privacy of AI models: best model per task, costs, alternatives.

MCP endpoint : https://www.agentkernel.si/mcp · website · measurements and details
OPC UA Modeler Reliable (measured) · 100% over 17 checks Does the job (tested) · 17/17

OPC UA companion spec types, namespace dependencies, and engineering units for AI agents

MCP endpoint : https://api.opcua-modeler.sterfive.io/api/mcp · website · measurements and details
ctxstore — memory that follows you across models Flaky · 91% over 11 checks

Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model.

MCP endpoint : https://mcp.ctxstore.ai/mcp · website · measurements and details
Memory Kernel Not measured yet

Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.

Package pypi : amormorri-memory-kernel · website · measurements and details
MIL — Machine Intelligence Layer Reliable (measured) · 100% over 16 checks Does the job (tested) · 16/16

Swedish company data (Bolagsverket, SCB) for AI agents, verified, with history and annual reports

MCP endpoint : https://www.milquery.com/api/mcp?src=registry · website · measurements and details
ai-model-pricing Flaky · 83% over 6 checks

Live pricing data for AI models across vendors: input/output prices per 1k tokens as JSON.

MCP endpoint : https://data.dataleads.pro/mcp/ai-model-pricing · website · measurements and details
Model ID Cheatsheet Being measured · 0% over 1 checks

Accurate API model IDs, pricing, and specs for 46 models across 7 AI providers.

MCP endpoint : https://universal-model-registry-production.up.railway.app/sse · website · measurements and details
arifOS — Constitutional AI Kernel Being measured · 0% over 1 checks

Constitutional verdict layer for AI agents. SEAL/HOLD before mutation. F1-F13 floors; audit ledger.

MCP endpoint : https://mcp.arif-fazil.com/mcp · website · measurements and details
RouteMyAgent Model Helper Private (key required)

Discover available AI models and delegate analysis or code review from your existing agent.

MCP endpoint : https://routemyagent.dev/mcp · website · measurements and details
searchit model catalog Private (key required)

AI model prices, providers, EU hosting and benchmarks: find, compare, save and watch offers.

MCP endpoint : https://models.searchit-agent.ai/mcp · website · measurements and details
AI Pricing Hub Being measured · 50% over 2 checks Real task being tested · 1/1

Source-backed AI model pricing, rankings, history, and benchmark data.

MCP endpoint : https://aipricinghub.com/mcp/rpc · website · measurements and details
370.ai — AI Gateway: 100+ Chat Models, Image & Speech Generation Flaky · 91% over 11 checks

One key, 100+ models: chat with any LLM, generate images and speech. Live model list. Free trial.

MCP endpoint : https://mcp.router.ai/mcp · website · measurements and details
Actenon Kernel Not measured yet

Verify consequential AI actions before they execute.

Package pypi : actenon-kernel · website · measurements and details
XF Model Source Reliable (measured) · 100% over 42 checks Does the job (tested) · 14/14

Find the right AI model for your job. Free discovery and ranking; tests on your own key.

MCP endpoint : https://xfms.xpansion.dev/mcp · website · measurements and details
Learn with Agents Private (key required)

Your AI agent builds interactive block-based courses over MCP; take them at learnwithagents.app.

MCP endpoint : https://learnwithagents.app/mcp · website · measurements and details
China NMPA Medical Device Data Flaky · 96% over 23 checks Does the job (tested) · 22/22

Structured China NMPA UDI data for AI agents: devices, registrants, models and registration numbers.

MCP endpoint : https://mcp.agentdatacore.com/mcp · website · measurements and details
What's That Model? Being measured · 50% over 2 checks Real task being tested · 1/1

Sourced AI video/image capabilities, explained task recommendations and verified access context.

MCP endpoint : https://whatsthatmodel.com/mcp · website · measurements and details
NLP.COM.AI Open Model Catalog Reliable (measured) · 100% over 3 checks Does the job (tested) · 3/3

Search curated open-weight AI model releases, licenses, architectures, and primary sources.

MCP endpoint : https://nlp.com.ai/mcp · measurements and details
Ai Model Experiments Being measured · 0% over 1 checks

AI Model Experiments MCP ('Model Lab') — run the same prompts across many AI models simultaneously…

MCP endpoint : https://gateway.pipeworx.io/ai-model-experiments/mcp · website · measurements and details
Coinslot — the vending machine for machines Reliable (measured) · 100% over 42 checks

13 micro-tools for agents: read pages, verify email, convert, validate, diff, extract. AI-operated.

MCP endpoint : https://coinslot.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