Taste

Name: Taste
Author: with0utwhy

@with0utwhy

About Taste

Pay-per-call MCP server. Vetted human experts review AI content, audit reasoning, gate approvals, and convene think-tank working sessions. 9 paid tools $1–$15, USDC on Base via x402.

#human-review #think-tank #human-in-the-loop #content-moderation #hallucination-detection #reasoning-audit #prepublish-safety #human-approval #x402 #base #usdc #on-chain-certificate

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "taste": {
      "url": "https://api.humantaste.app/mcp/"
    }
  }
}

Tools

List all available human expert evaluation offerings with pricing, tool names, and whether each issues an on-chain Taste content certificate. Free.

Returns currently-available expert taglines (pseudonymous descriptions of the kinds of expertise on hand) plus the real-time count of online expert seats and estimated wait. Use this as a cheap pre-flight check before calling a paid tool. Taglines describe expertise kinds, not individuals: no per-expert PII is exposed. Free.

Check the status of a previously submitted request. Returns the full structured deliverable once the expert (or order team) completes the work. Accepts a sessionId or an order reference code (think tank or illustration).

Get a humantaste.app URL where a human can place a consult_domain_expert order from a browser (Connect MetaMask, pay $15 USDC on Base, session created). Use this when your MCP client has no wallet integration (Claude Desktop, generic chat UIs). The URL is pre-filled with the brief you pass in; the user just opens it, reviews, connects a wallet, and pays. Returns the payment URL and the price. Free.

Spend a free revision turn on a completed think tank order. Provide the reference code from your original order and describe the adjustments you want — the same team revisits the brief and returns an updated deliverable. Poll get_result with the reference code to retrieve it. Free: no payment required, the turn is included with your order.

Spend a free revision turn on a completed illustration order. Provide the reference code from your original order and describe the adjustments you want — the same illustrator revisits the brief and returns an updated deliverable. Poll get_result with the reference code to retrieve it. Free: no payment required, the turn is included with your order.

Have a vetted human expert verify whether an external source, project, or claim is trustworthy. Call when your output or planned action depends on an external claim you cannot independently verify (crypto project legitimacy, social media authenticity, source credibility, vendor due diligence). Returns verdict, red flags, positive signals, confidence score.

Get a vetted human expert to review your AI-generated content — text, images, videos, social posts, audio, or any media — for hallucinations, factual errors, weak parts, and domain mistakes. Call before publishing, before forwarding to another agent, or before acting on the content. Returns verdict, issues found, suggested improvements. Approved outputs receive a Taste content certificate on-chain you can attach as proof of human review.

Audit your step-by-step reasoning for mid-chain errors before producing the final answer. Call when stakes are high and your chain has 3+ steps — humans catch wrong intermediate steps that final-output checks miss (right-looking answers built on broken intermediate logic). Returns per-step verdict, flagged errors, suggested corrections. Approved chains receive a Taste content certificate on-chain.

Get a vetted human expert to review your AI-generated content — text, images, videos, social posts, audio, or any media — for cultural sensitivity, brand safety, derivative risks, and audience appeal before you publish. Call before social posts, marketing campaigns, content distribution, or anywhere public-facing. Returns verdict (safe / needs_changes / do_not_publish), flagged issues, fix suggestions. Approved content receives a Taste content certificate on-chain, verifiable downstream.

Get a real human matching your target demographic to rate and react to your content as a representative audience member. Call before A/B test commits, before ad spend, or before distribution decisions. Returns overall rating, criteria scores, qualitative feedback, comparison notes.

Get an impartial human arbiter to decide whether a deliverable meets an agreed contract, or to settle disagreements between agents. Call when automated evaluation cannot determine quality, when two parties dispute fulfillment, or when subjective judgment is needed for contract assessment. Returns approve/reject verdict, reasoning, deliverable quality rating, contract alignment.

Pause your workflow for explicit human approval before executing a high-stakes action. Call before any irreversible action — large spend, on-chain transaction, public content publish, customer-facing decision. Returns approved/denied + reasoning. Approvals can be enforced on-chain via the Taste Gatekeeper hook for ACP and ERC-8183 jobs.

Verify a Taste content certificate on-chain. Call when consuming content from another source that claims to be human-reviewed — returns reviewer domain, date, offering, verdict, and validity. Free. Use to build trust chains: agent A's output is reviewed → certificate issued → agent B consumes content and verifies cert before acting.

Convene a think tank — a curated team of vetted human experts runs a 30-minute working session on your idea, problem, or decision and returns synthesized directions, ideas with rationale, and recommended next steps. Returns a sessionId + referenceCode immediately — poll get_result with either when the team is done. Includes 1 free revision turn: call request_think_tank_revision with the code to ask for adjustments.

Convene a think tank — a curated team of vetted human experts runs a 60-minute working session on your idea, problem, or decision and returns synthesized directions, ideas with rationale, and recommended next steps. Returns a sessionId + referenceCode immediately — poll get_result with either when the team is done. Includes 2 free revision turns: call request_think_tank_revision with the code to ask for adjustments.

A vetted human in a named domain answers your question with first-hand knowledge. Pass `domain` to match an expert. Pass `parentSessionId` for follow-ups (cap 3). Returns answer, anonymised role, confidence, first-hand flag. Approved answers get an on-chain Taste cert. Listed domains: musician, cantor, writer, farmer, UX designer, Swedish archipelago resident, Stockholm local, Protestant priest, art curator, museum staff, culture journalist, food critic. Other domains: best-effort 24-48h.

Overview

What is Taste?

Taste is a pay-per-call MCP server that puts vetted human experts in the loop for AI agents. It enables human review of an agent’s output across text, images, video, audio, and social posts; audit step-by-step reasoning chains for mid-chain errors; run prepublish safety checks; gate high-stakes actions for explicit human approval; and convene curated expert teams for 30- or 60-minute think-tank working sessions. Approved outputs receive a Taste content certificate recorded on Base that downstream agents can verify on-chain.

How to use Taste?

Connect to the MCP endpoint https://api.humantaste.app/mcp/ over Streamable HTTP (MCP 2025-06-18). No API key or signup required. Free tools (list_offerings, list_expert_profiles, get_result, verify_certificate) answer immediately. Paid tools cost $1.00–$15.00 per call, settled in USDC on Base mainnet via x402 — call without payment to receive an HTTP 402 challenge, sign an EIP-3009 USDC transfer, then retry. Typical human turnaround is 5–30 minutes for evaluations and up to 24 hours for a think tank session.

Key features of Taste

Pay-per-call model, no subscription or API key needed.
Free tools for browsing offerings, expert profiles, results, and certificates.
Paid evaluation tools: content review, reasoning chain audit, prepublish review, and more.
Paid think-tank tools: 30- or 60-minute curated expert sessions.
Payments settled in USDC on Base mainnet via x402 protocol.
On-chain content certificates verifiable by any downstream agent.

Use cases of Taste

Human review of AI-generated content across text, images, video, audio, and social posts.
Auditing step-by-step reasoning chains for mid-chain errors in agent workflows.
Running prepublish safety checks for cultural sensitivity, brand safety, and derivative risk.
Gating high-stakes actions that require explicit human approval before execution.
Convening a curated expert team for a 30- or 60-minute think-tank working session on an idea or decision.

FAQ from Taste

How much do paid tools cost?

Paid tools cost $1.00–$15.00 per call: evaluation tools are $1, and think-tank sessions are $5 (30-minute) or $15 (60-minute). All payments are settled in USDC on Base mainnet.

How do I pay for a paid tool?

Call the tool without payment to receive an HTTP 402 challenge. Then sign an EIP-3009 USDC transfer and retry the call. This x402 mechanism handles payment without an API key.

How long does human turnaround take?

Typical turnaround is 5–30 minutes for evaluation tools and up to 24 hours for a think tank session.

Do I need an API key or signup?

No. You can start using Taste immediately — free tools work instantly, and paid tools use the x402 payment flow without any prior registration.

How does Taste help with EU AI Act compliance?

EU AI Act Article 50(2) exempts AI-generated content from mandatory AI-disclosure labels when it has had human review or editorial control. Taste content certificates provide the on-chain audit trail for that exemption.