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

22,816measured

6,941proven reliable

Agentic Prompt Reliable (measured) · 100% over 57 checks

1,177 free agentic trading prompts for Claude and Robinhood MCP.

MCP endpoint : https://agentic-prompt.com/mcp · website · measurements and details

PaperBanana Research Figure Prompts Reliable (measured) · 100% over 29 checks Does the job (tested) · 29/29

Search and read public research figure prompt templates from PaperBanana.

MCP endpoint : https://paperbanana-prompts-mcp.873217126.workers.dev/mcp · website · measurements and details

Execute adversarial-prompt-shield-mcp Being measured · 0% over 1 checks

Premium agentic endpoint for adversarial-prompt-shield-mcp.

MCP endpoint : https://api.m2mcent.com/adversarial-prompt-shield-mcp/sse · measurements and details

Execute brotli-prompt-compressor-mcp Being measured · 0% over 1 checks

Premium agentic endpoint for brotli-prompt-compressor-mcp.

MCP endpoint : https://api.m2mcent.com/brotli-prompt-compressor-mcp/sse · measurements and details

Ultra Prompt Private (key required)

Your prompt library inside your AI: 1,000+ pro templates, frameworks, vocab & pipelines.

MCP endpoint : https://up-mcp.unpluggedfeed.workers.dev · measurements and details

The Builder's Prompt Library Reliable (measured) · 100% over 4 checks Does the job (tested) · 4/4

Search 3,323 graded AI prompts for software builders; fetch any prompt by slug. No key needed.

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

Tamer Prompt Marketplace Reliable (measured) · 100% over 47 checks

Prompt marketplace for AI agents: browse and buy prompts with x402 (USDC on Base).

MCP endpoint : https://agents.tamer-ai.ir/mcp · website · measurements and details

.prompts Private (key required)

.prompts, the home to all your AI prompts, everywhere you need them.

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

AgentDiet A2A Indirect Prompt-Injection & Jailbreak Firewall Reliable (measured) · 100% over 18 checks Does the job (tested) · 17/17

Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.

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

Prompt Maker Studio Private (key required)

Your prompt library in any MCP client: list, fetch, save and version prompt templates.

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

thinkhard.si prompt tools Flaky · 88% over 8 checks Does the job (tested) · 7/7

Search 300+ expert prompt templates for work, grade a prompt out of 10, and price AI models.

MCP endpoint : https://thinkhard.si/mcp · website · measurements and details

Agent Prompts A to Z Reliable (measured) · 100% over 8 checks Does the job (tested) · 8/8

Read-only catalog of prompt packs and rule files: Cursor, CLAUDE.md, AGENTS.md, SKILL.md.

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

Prompt Compass Private (key required)

Decision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.

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

Prompt-cache prefix guardian Private (key required)

Cache-bust forensics + TTL-fit verdicts: names the field that busts your prompt cache.

MCP endpoint : https://textforagents.com/products/prompt-cache-prefix-guardian/mcp · measurements and details

Into the Prompt Flaky · 93% over 14 checks Does the job (tested) · 13/13

Search Into the Prompt's short AI videos, get a learning path and see how the creator program works.

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

prompts.chat MCP Server Not measured yet

Search and retrieve AI prompts from prompts.chat, the social platform for AI prompts.

Package npm : @fkadev/prompts.chat-mcp · website · measurements and details

Imperium MCP Security — Prompt-Injection, Jailbreak & Tool Poisoning Firewall Reliable (measured) · 100% over 13 checks Does the job (tested) · 13/13

Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.

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

Feeling Search — Art Style Reference & Prompt Encyclopedia Being measured · 100% over 1 checks Real task being tested · 1/1

One sentence in, the best-matching visual style out: art reference chart and prompt encyclopedia.

MCP endpoint : https://xiximm.cloud/mcp · website · measurements and details

prompt-protection Not measured yet

Scan prompts, tool definitions and model output for injection, and guard agent tool calls.

Package npm : prompt-protection · website · measurements and details

Prompt Injection Scanner Reliable (measured) · 100% over 24 checks Does the job (tested) · 23/24

Check text before your agent reads it: hidden instructions, invisible text and links that leak data.

MCP endpoint : https://injectionscan.openkrill.app/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