FaceabotCapability network for AI agents
‹ Back

The real catalog of tools for AI agents

Google tells you what exists. Faceabot tells you what holds up.

48,257real tools
32,111callable over HTTPS
22,168measured
6,679proven reliable
Biology Verdict Being measured · 100% over 1 checks Real task being tested · 1/1

Longevity product reviews as data: dated US prices, cited sources and disclosed store links.

MCP endpoint : https://biologyverdict.com/mcp · website · measurements and details
Jean — Molecular Biology & Genomics Being measured · 0% over 1 checks

Validated molecular biology tools: cloning, primers, CRISPR, Sanger, alignment, qPCR, phylogenetics

MCP endpoint : https://jeanslabs.vercel.app/mcp · website · measurements and details
Verdict Reliable (measured) · 100% over 14 checks Partly does the job · 11/13

Design review as MCP tools: critique, states, journeys, UI copy, PRD assumptions. BYOK or hosted.

MCP endpoint : https://verdict.allthepossibles.com/mcp · website · measurements and details
biorxiv-mcp Not measured yet

Biology preprints from bioRxiv. No key required.

Package npm : biorxiv-mcp · website · measurements and details
Permit Verdicts Reliable (measured) · 100% over 30 checks Does the job (tested) · 30/30

Building-permit verdicts by address, with cited records. SF, Seattle, Austin, NYC. Pay per call.

MCP endpoint : https://permit-api-production-7375.up.railway.app/mcp · website · measurements and details
Verdict — Send anything. Get the truth. Reliable (measured) · 100% over 17 checks

Send anything. Get the truth — REAL, SUSPICIOUS or LIKELY SCAM verdicts on messages and links.

MCP endpoint : https://verdict.aimlds.org/mcp · website · measurements and details
Egress-verdict probe Reliable (measured) · 100% over 6 checks

Grades an MCP server's real egress: EVERY-HOP-VALIDATED, FIRST-HOP-ONLY, or OPEN-EGRESS.

MCP endpoint : https://textforagents.com/products/egress-verdict-probe/mcp · measurements and details
PRUVIQ strategy verdicts (read-only) Flaky · 90% over 10 checks Does the job (tested) · 9/9

Read-only crypto strategy backtest & verification verdicts. No trading tools; every result is cited.

MCP endpoint : https://pruviq.com/mcp · website · measurements and details
SageChimp book verdicts Being measured · 50% over 2 checks

Unpaid-vs-ARC book verdicts, catalog facts, series order, and sample reviews.

MCP endpoint : https://sagechimp.com/mcp · website · measurements and details
ARYSPHERE x402 chain reads and token verdicts Reliable (measured) · 100% over 20 checks Real task being tested · 0/2

Pay-per-call onchain reads (Base, Ethereum, Gnosis), token verdicts and LLM chat over x402 USDC

MCP endpoint : https://api.arysphere.com/mcp · measurements and details
Data Quality Gate - deterministic post-scrape cleaner + verdict Reliable (measured) · 100% over 54 checks

Post-scrape data cleaner, no LLM: repairs mojibake, HTML, invisible chars. Plus a verdict.

MCP endpoint : https://www.aidatatools.dev/api/mcp_server · website · measurements and details
MX Verdict Flaky · 86% over 7 checks Does the job (tested) · 6/6

Free, read-only email and DNS checks: SPF, DKIM, DMARC, MX, DNS records, blocklists, domain health.

MCP endpoint : https://mxverdict.com/mcp · website · measurements and details
rosetta-mcp-server Not measured yet

Rosetta/PyRosetta protein modeling and Biotite translation for computational biology

Package npm : rosetta-mcp-server · website · measurements and details
Verdict L402 Flaky · 86% over 7 checks

Ask if an action is safe before your agent runs it: injection, shell, MCP installs. Free samples.

MCP endpoint : https://verdict.kechlab.com/mcp · website · measurements and details
Verdict QA Not measured yet

Read-only MCP server over Verdict QA state: verdicts, findings, flaky quarantine, history.

Package pypi : verdict-qa-mcp · website · measurements and details
Verdict: the due-diligence house for DeFi Not measured yet

Verdict, the due-diligence house for DeFi: keyless ratings, methodology and a hack incident feed.

Package npm : verdict-finance-mcp · website · measurements and details
Token Verdict Not measured yet

MCP server for Token Verdict — pay-per-call token risk verdicts over x402 ($0.02 USDC on Base)

Package pypi : token-verdict-mcp · website · measurements and details
Corollary — scientific AI models, tools and databases Flaky · 67% over 3 checks Real task being tested · 2/2

Find open biology and chemistry AI models, bioinformatics tools and databases, and run them online.

MCP endpoint : https://corollary-labs.com/mcp · website · measurements and details
Verdict — Compliance for AI-Generated Code Not measured yet

Compliance verdicts for AI-generated code. SOC 2, HIPAA, HITRUST for healthcare IT.

Package mcpb : https://github.com/getverdict-ai/releases/releases/download/v0.3.0/verdict-mcp.mcpb · website · measurements and details
Telemetry-Intake Provenance & Confinement Service Reliable (measured) · 100% over 6 checks

Signed telemetry origin verdicts, intake census, canary drills. Verdict $0.01/event.

MCP endpoint : https://textforagents.com/products/telemetry-intake-provenance-confinement/mcp · 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