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

22,849measured

6,959proven reliable

Japan TITP Administrative Actions Reliable (measured) · 100% over 8 checks Does the job (tested) · 4/4

Published TITP actions (ISA) on Japanese intern supervising/implementing orgs. Tracks file changes.

MCP endpoint : https://jp-titp-actions-production.mk-career-planning.workers.dev/mcp · website · measurements and details

Enforcement Actions Being measured · 0% over 1 checks

US federal enforcement actions MCP. Keyless.

MCP endpoint : https://gateway.pipeworx.io/enforcement-actions/mcp · website · measurements and details

GitHub Actions Audit Being measured · 0% over 1 checks

GitHub Actions workflow security audit - 21 checks: pinning, permissions, secrets, injection.

MCP endpoint : https://unbearable-dev--github-actions-audit.apify.actor/mcp · website · measurements and details

Sterile Cockpit for Irreversible Actions Reliable (measured) · 100% over 10 checks

Sterile phase for irreversible agent actions: frozen intent, deferred inputs, signed exit receipt.

MCP endpoint : https://textforagents.com/products/sterile-cockpit-for-irreversible-actions/mcp · measurements and details

Uspto Office Actions Being measured · 0% over 1 checks

USPTO patent prosecution history: office action full text, examiner citations, claim-level…

MCP endpoint : https://gateway.pipeworx.io/uspto-office-actions/mcp · website · measurements and details

Chipp Actions and components Private (key required)

Chipp: custom actions, action collections, custom components, and database connections

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

Support Action Gate Being measured · 50% over 2 checks Real task being tested · 1/1

Free to compete: testnet faucet funds everything. Resolve an escalation least-privilege.

MCP endpoint : https://a2awire.com/mcp/benchmarks/support-action-gate-v1/http · website · measurements and details

IntentFence Agent Action Firewall Being measured · 0% over 1 checks

Fail-closed action authorization, MCP risk scanning, x402 checks, and signed receipts.

MCP endpoint : https://agentpass-protocol.rmalka06.chatgpt.site/api/mcp · website · measurements and details

GitHub Actions Security Audit Private (key required)

Audit GitHub Actions workflows for script injection, unpinned actions and missing permissions.

MCP endpoint : https://github-actions-audit-mcp.mcpize.run/mcp · website · measurements and details

Periodix Actions Private (key required)

Search LinkedIn & Sales Navigator. Get structured people, companies, posts, jobs data. 4.9/5 on G2.

MCP endpoint : https://actions.periodix.net/mcp · website · measurements and details

GitHub Actions run id digits, value discarded Not measured yet

GitHub Actions run id digits, value discarded

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

公正取引委員会排除措置命令・取適法勧告 Not measured yet

Japan FTC: 361 antitrust orders and subcontract-act recommendations, with source URLs.

Package mcpb : https://github.com/eoylab/jftc-actions/releases/download/v0.1.0/jftc-actions.mcpb · website · measurements and details

COTAL actions (cotal.ai) Flaky · 97% over 29 checks Does the job (tested) · 27/27

cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls

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

SecureStamp Action Proof — Cross-Cloud Public Beta (Unverified) Private (key required)

UNVERIFIED: cross-cloud beta; sandbox by default; production opt-in via customer Guardian.

MCP endpoint : https://mcp.securestamp.online/mcp · website · measurements and details

Error-actionability translation for MCP tool failures Private (key required)

Classifies MCP tool failures into enforced recovery verdicts from per-server dialect profiles.

MCP endpoint : https://textforagents.com/products/error-actionability-translation/mcp · website · measurements and details

Agent Control — Action Gate Reliable (measured) · 100% over 20 checks

Agent asks a person go/stop/wait before Slack, CRM or risky steps. $49 for 30 days.

MCP endpoint : https://agent-control.net/api/v1/mcp · website · measurements and details

RECOVER — Decide Safely After a Failed Machine Action Flaky · 88% over 8 checks

Choose the safest next action after an API, MCP, or agent failure before retrying.

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

Hermes Action Bridge Not measured yet

Delegate real-world actions from Claude Code, Codex, and other agents to Hermes Agent.

Package npm : hermes-action-bridge · website · measurements and details

R/IV — Verify Claims, Citations & Agent Actions Flaky · 75% over 4 checks

Verify claims, citations & agent actions. Free receipt trial; paid prices via live R/IV quotes.

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

ONCE — Exactly-Once Reliability for AI Agent Actions Being measured · 0% over 1 checks

Prevent duplicate AI-agent side effects with idempotency, verification, and durable receipts.

MCP endpoint : https://optimistic-compassion-production.up.railway.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