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

Phoenix operational_context unpaid canary Reliable (measured) · 100% over 57 checks

Unpaid qualification-gated operational_context canary. Staging data. No wallet.

MCP endpoint : https://phoenix-collective-os-isolated-validation-phoenix-collective.vercel.app/api/mcp/operational-context/mcp · website · measurements and details

Agent Hub - AI-operated public sandbox: demo data, simulated payments, no real bookings Being measured · 0% over 1 checks

Agent-to-business commerce sandbox: intents, offers, bookings. Demo data, ed25519-signed calls.

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

Penny Engine — Agent Operations Reliable (measured) · 100% over 19 checks Does the job (tested) · 19/19

Remote MCP utilities for agents: structured data, commerce checks, and x402 paid API discovery.

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

operant-mcp Reliable (measured) · 100% over 23 checks Does the job (tested) · 23/23

Read-only MCP server for the OPERANT AI operating-agent calibration benchmark.

MCP endpoint : https://operant-mcp.saagar210.workers.dev/mcp · website · measurements and details

Chipp Data operations Private (key required)

Chipp: changes to a deployed project's live data: data, script and procedure operations, bulk.

MCP endpoint : https://mcp.chipp.ai/mcp/data-ops · website · measurements and details

CSIDIA — operational notes and capabilities Flaky · 86% over 7 checks

AI regulation, data protection and compliance notes from CSIDIA, plus its capability catalogue.

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

SPLIDIA — operational notes and capabilities Flaky · 98% over 44 checks

Fibre optics, OTDR, network design and data centre notes from SPLIDIA, plus its service catalogue.

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

Burnes Atelier Operations Reconciliation Being measured · 50% over 2 checks

Deterministic operations reconciliation for AI agents: COMPLETE, INCOMPLETE, or NEEDS_REVIEW.

MCP endpoint : https://x402.burnesatelier.com/mcp · website · measurements and details

Operations Activity Ledger Being measured · 0% over 1 checks

Append an operations activity entry

MCP endpoint : https://antibody-package-occasional-floppy.trycloudflare.com/mcp/workspace-activity-reference/downstream · measurements and details

Black Label Operator Website MCP Flaky · 94% over 18 checks Fails real tasks · 0/17

Search and read public Black Label Operator pages with source URLs.

MCP endpoint : https://operator.blacklabelbots.com/agent/mcp · website · measurements and details

GraphQL operation count, query discarded Not measured yet

GraphQL operation count, query discarded

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

MCP Operation Risk Flaky · 80% over 5 checks Does the job (tested) · 4/4

Operation-level risk guidance for consolidated MCP tools, including schema drift and retry signals.

MCP endpoint : https://87-106-119-237.sslip.io/mcp-operation-risk/mcp · website · measurements and details

Hydra operation count, body discarded Not measured yet

Hydra operation count, body discarded

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

WSDL operation count, body discarded Not measured yet

WSDL operation count, body discarded

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

Borrower Operations — Loan Application Review — Fenwick & Rowe Operations (61b5d8c8) Being measured · 50% over 2 checks Real task being tested · 1/1

12 synthetic loan application exception cases: duplicate payments, policy-watch list entries, missin

MCP endpoint : https://a2awire.com/mcp/benchmarks/loan-application-review-2026-09-11-61b5d8c8/http · website · measurements and details

Bounty Operator Reliable (measured) · 100% over 49 checks Does the job (tested) · 49/49

Argues against a security finding or a draft bug bounty report before you submit it.

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

SemVer range operators, value discarded Not measured yet

SemVer range operators, value discarded

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

SigRank — AI Operator Benchmarking Flaky · 83% over 6 checks

SigRank benchmark MCP: cascade metrics, leaderboard, operator profiles, simulation, diagnostics.

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

Hitsteps Analytics and Operations Private (key required)

AI access to Hitsteps analytics, live visitors, uptime, goals, alerts, and chats.

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

VNISH Global Operator Flaky · 91% over 11 checks Does the job (tested) · 10/10

Read-only VNISH firmware metadata, Ninja guidance and input-based mining economics calculations.

MCP endpoint : https://vnish.global/ai/mcp/index.php · 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