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
Dry Run Reliable (measured) · 100% over 27 checks Does the job (tested) · 27/27

Monte Carlo cash-flow simulator for a small services business: odds of running short, and why.

MCP endpoint : https://mcp.modernmustardseed.com/dry-run · website · measurements and details
workflowy Not measured yet

Create, update, complete nodes, search & replace with regex and dry run, usage reports, transforms

Package oci : ghcr.io/mholzen/workflowy:0.8.1 · website · measurements and details
DataContractGate Not measured yet

Infer, dry-run, deploy, and inspect DataContractGate semantic data contracts.

Package npm : @nightmoose/contractgate-mcp-server · website · measurements and details
mcp-airlock Not measured yet

Governance proxy for MCP servers: allowlist, forced dry run, human confirmation, blast radius, audit

Package pypi : mcp-airlock · website · measurements and details
aio-geo Being measured · 50% over 2 checks Real task being tested · 1/1

AIO.GEO: audit, dry-run fixes, rescore, doctor. Remote + stdio. Not LLM rankings.

MCP endpoint : https://www.aiogeoprotocol.com/mcp · website · measurements and details
aicoreutils Not measured yet

JSON-first Coreutils CLI for AI agents. 114 commands with sandbox, dry-run, and MCP support.

Package pypi : aicoreutils · website · measurements and details
MCP Test Utils Not measured yet

Desktop UI automation for AI agents: verified clicks, UI Automation, OCR, scenario runs, recording

Package mcpb : https://github.com/JeenyJAI/mcp-test-utils/releases/download/v3.27.23/mcp-test-utils.exe · website · measurements and details
agentguard Not measured yet

MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.

Package npm : @agentwares/agentguard · website · measurements and details
Codex CCXT MCP Not measured yet

Dry-run-first CCXT MCP with market, account, derivatives, and guarded trading tools.

Package oci : ghcr.io/lucyfox199818-collab/ccxt-mcp:0.1.0 · website · measurements and details
Rail Not measured yet

Budgets, propose-then-approve, and receipts for agents that buy for a human. Dry-run by default.

Package npm : rail-mcp · website · measurements and details
mcp-simulate Not measured yet

MCP server for dry-run Ethereum transaction simulation via Crypto APIs

Package npm : @cryptoapis-io/mcp-simulate · website · measurements and details
Hevy MCP Not measured yet

MCP server for the Hevy fitness API — spec-generated schemas, dry-run-safe writes, easy setup.

Package npm : @diecoscai/hevy-mcp · website · measurements and details
Leantime MCP (Unofficial) Not measured yet

Unofficial MCP server for Leantime: 42 agent-first tools, backup/restore, dry-run validation

Package cargo : leantime-mcp · website · measurements and details
Obyte MCP Not measured yet

Query Obyte mainnet and testnet: balances, units, autonomous agents, AA state, dry runs, tokens.

Package npm : obyte-mcp · website · measurements and details
YouTube Shorts Agent Not measured yet

Agent-first YouTube Shorts uploader: dry-run validation, OAuth checks, synthetic-media metadata.

Package npm : youtube-shorts-agent · website · measurements and details
notiqo Not measured yet

Import canonical analytics tagging guides into Notiqo: dry-run first, writes only on confirmation.

Package npm : @notiqo/mcp · website · measurements and details
Mimiq: test pages and sign-up flows on simulated people Being measured · 100% over 2 checks

Simulated people test your pages, copy and sign-up flows, and say why they would leave.

MCP endpoint : https://mcp.mimiqai.com/mcp · website · measurements and details
MikroMCP Not measured yet

MCP server for MikroTik RouterOS and SwOS: typed tools, dry-run, RBAC, audit logs, and rollback.

Package npm : mikromcp · website · measurements and details
harbor-registry-mcp Not measured yet

Harbor Registry MCP — projects, repos, artifacts, storage reports, cleanup (with dry-run).

Package pypi : harbor-registry-mcp · website · measurements and details
Cookwala Not measured yet

Search Cookwala recipes by diet, allergen, method and language; dry-run them safely. Read-only.

Package npm : @cookwala/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