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

22,840measured

6,970proven reliable

KARTA — spend control for AI agents Reliable (measured) · 100% over 3 checks

Task envelope, budget ledger, kill switch and signed receipts for agents that pay.

MCP endpoint : https://karta.rta.lat/mcp · website · measurements and details

Milewise Being measured · 0% over 2 checks

Buy verified human work through MCP with owner-controlled agent spend accounts.

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

ThinkNEO Control Plane Flaky · 75% over 4 checks Real task being tested · 2/2

Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.

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

Ukraine Public Spending Being measured · 0% over 1 checks

Ukraine public spending MCP — State Treasury payment transactions (keyless).

MCP endpoint : https://gateway.pipeworx.io/ukraine-public-spending/mcp · website · measurements and details

Execute ad-spend-auditor-mcp Being measured · 0% over 1 checks

Premium agentic endpoint for ad-spend-auditor-mcp.

MCP endpoint : https://api.m2mcent.com/ad-spend-auditor-mcp/sse · measurements and details

sipi.bot — Spend Firewall for AI Agents Reliable (measured) · 100% over 57 checks

Pre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.

MCP endpoint : https://sipi.bot/api/mcp · website · measurements and details

Fed-Spend Private (key required)

Federal contract intelligence: $7T+ awards, SAM.gov opps, pWin verdicts, recompetes, protests.

MCP endpoint : https://fed-spend.com/api/mcp · website · measurements and details

Argus API Spend Reliable (measured) · 100% over 6 checks

Track API spend, credit balances and runway across OpenAI, Anthropic, OpenRouter and 25 more.

MCP endpoint : https://api.argus.town/mcp · website · measurements and details

nidhipati — proof of spend for AI agents Reliable (measured) · 100% over 5 checks

Proof-of-spend and reserve checks for AI agents: receipts, spend audit, NAV, reconciliation.

MCP endpoint : https://rta.lat/nidhipati/mcp · website · measurements and details

Authoryze Private (key required)

Give your AI agent a spending limit: approval controls and single-use virtual cards.

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

Agent Spend Guard — owner-set purchasing guardrails Flaky · 67% over 3 checks Real task being tested · 0/2

Free spend guardrails for AI agents: approve/deny/ask_user, caps, dupes.

MCP endpoint : https://a2awire.com/mcp/connectors/spend-guard/http · website · measurements and details

Gvnr Private (key required)

Budget & cost control for AI agents — per-agent spend caps + rate limits before each call.

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

Meta Ad Library Spend MCP Demo by AdSpendSpy Reliable (measured) · 100% over 10 checks Does the job (tested) · 10/10

Keyless demo: Meta Ad Library ads of one advertiser with estimated ad spend and top landing pages.

MCP endpoint : https://www.adspendspy.com/mcp-demo · website · measurements and details

Fleet spend circuit-breaker Being measured · 100% over 1 checks

Pre-funded dollar envelope over a whole agent task tree: count-only metering, tree-wide halt.

MCP endpoint : https://textforagents.com/products/fleet-spend-circuit-breaker/mcp · measurements and details

SpendNod Private (key required)

AI agent spending controls. Set limits, blocklists, and caps. Approve transactions from your phone.

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

Regent Protocol Private (key required)

Spending control for AI agents: approved budgets, a decision before each payment, signed receipts.

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

Autonomy Foundry Governance Being measured · 0% over 1 checks

Governance and agentic-commerce policy tools for AI agents: spend, purchase and charter controls.

MCP endpoint : https://autonomy-foundry.autonomyfoundry.workers.dev/mcp · website · measurements and details

NexaLayer Not measured yet

Managed proxy sessions, health, rotation, usage, and spend controls for AI agents.

Package npm : @nexalayer/mcp · website · measurements and details

AP Control Labs Finance Controls Being measured · 0% over 1 checks

Read-only finance and operations controls for AI agents with evidence and safe next actions.

MCP endpoint : https://api-production-9502.up.railway.app/mcp · website · measurements and details

Cache-Control token count, value discarded Reliable (measured) · 100% over 20 checks

Cache-Control token count, value discarded

MCP endpoint : https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/cache-control-ok/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