mcp server

Taste

Expert review for AI agents. On-chain proof of human review.

Description as published by the maintainer. Source

• version 2.0.0
• slowing

slowing — Most recent push to the repository was 2026-05-23.

What this server can do

20 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

arbitrate_dispute(context, termsUri, termsHash, termsJson, deliverable, partyAPosition, partyBPosition, contractDescription)

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. Required: contractDescription, deliverable, partyAPosition, partyBPosition.

ask_a_human(question)

Ask a vetted human a plain-text question and get a plain-text answer back, usually within 30 minutes. Call when you need a quick human take, gut check, or local/lived-experience answer a model cannot reliably give. No scoring, no verdict, no certificate — just a direct human response. Returns the human's answer, plus an optional note on who answered. Required: question.

consult_domain_expert(domain, context, question, referenceUrls, parentSessionId, buyerWalletAddress, requireListedDomain)

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. Required: question, domain.

get_result(sessionId, referenceCode)

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).

list_expert_profiles

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.

list_offerings

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

order_think_tank_session_30(mediaUrls, description, buyerWalletAddress, requestedDeliverables)

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. Required: description.

order_think_tank_session_60(mediaUrls, description, buyerWalletAddress, requestedDeliverables)

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. Required: description.

predict_audience_reaction(content, context, targetDemographic)

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. Required: content, targetDemographic.

prepare_consult_domain_expert(domain, context, question, referenceUrls, parentSessionId)

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. Required: question, domain.

prepublish_review(content, context)

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. Required: content.

request_human_approval(stakes, context, timeoutMinutes, actionDescription)

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. Required: actionDescription, stakes.

request_illustration_revision(adjustments, referenceCode)

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. Required: referenceCode, adjustments.

request_think_tank_revision(adjustments, referenceCode)

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. Required: referenceCode, adjustments.

review_code(code, intent, context)

Get a vetted human engineer to review your code, architecture, and design decisions — not just style, but correctness, security, and whether the structure will hold up. Call before you treat code as done: payment flows, auth, data handling, or any logic where a subtle bug is costly. Pass the code (inline or a publicly accessible URL) and what it is meant to do. Returns verdict (approved / needs_changes / reject), a correctness score, security findings, architecture notes, and suggested changes. Approved code receives a Taste content certificate on-chain. Required: code, intent.

review_content(content, context)

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. Required: content.

review_plan(goal, plan, context)

Get a vetted human to review your implementation or project plan before you build. Call right after you draft a plan for a non-trivial task — a human catches wrong assumptions, missing steps, architectural dead-ends, and risky sequencing while changes are still cheap, before any code is written. Pass the plan, the goal it serves, and any constraints. Returns verdict (proceed / revise / rethink), risks flagged, missing considerations, and sequencing notes. Approved plans receive a Taste content certificate on-chain. Required: plan, goal.

verify_certificate(contentHash, certificateId)

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, validity, and an evidence tier: "evidence-verified" certs carry the reviewer's EIP-712 verdict signature + their Human Passport score attestation (EAS on Base), independently checkable without trusting Taste. Free. Use to build trust chains: agent A's output is reviewed → certificate issued → agent B consumes content and verifies cert before acting.

verify_external_source(context, subject)

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. Required: subject.

verify_reasoning_chain(chain, context)

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. Required: chain.

Last successful function declaration observed on 2026-08-13. Source: https://api.humantaste.app/mcp/. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://api.humantaste.app/mcp/.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/with0utwhy/taste-mcp
• Website — https://api.humantaste.app/llms.txt
• Remote endpoint (streamable-http) — https://api.humantaste.app/mcp/

Related, by what their authors tagged them

• ai.tuteliq/mcp — last commit 2026-08-06, shares content-moderation
  Detect grooming, bullying, fraud, and 16+ online threats across text, voice, image, and video.
• ai.aliengiraffe/spotdb — last commit 2026-08-05, shares agentic
  Ephemeral data sandbox for AI workflows with guardrails and security
• Fodda Brand Intelligence — last commit 2026-08-06, shares agentic
  Brand health & trend footprint across PSFK expert graphs with citable sources, not web summaries.
• Fodda Deep Research — last commit 2026-08-06, shares agentic
  Autonomous deep research reports merging PSFK trend graphs with citable sources.
• Fodda Earnings Intelligence — last commit 2026-08-06, shares agentic
  Cross-company earnings trends & executive divergence with citable sources.
• Fodda Synthetic Expert Consult — last commit 2026-08-06, shares agentic
  Consult synthetic industry experts grounded in PSFK trend graphs with citable sources.
• Fodda Knowledge Graphs — last commit 2026-08-06, shares agentic
  Expert-curated knowledge, brand, research & earnings intelligence — 31 tools, 220+ graphs.
• Fodda Topic & Trend Research — last commit 2026-08-06, shares agentic
  Trend, stats & insight search across PSFK expert graphs with citable sources.
• com.blackveilsecurity/dns — last commit 2026-08-06, shares agentic
  DNS and email security scanner with 80 MCP tools for SPF, DMARC, DNSSEC, SSL, and brand audits.
• com.clauxel.agentichtmlexportqa/agentichtmlexportqa-mcp — last commit 2026-05-20, shares agentic
  Paid remote MCP for agentic HTML export QA MCP, structured receipts, audit logs, and reviewer-ready

These share tags the maintainers applied themselves, such as content-moderation, agentic. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: agentic, ai-agents, content-moderation, eu-ai-act, human-experts, human-in-the-loop, human-judgment, human-review, mcp, model-context-protocol, x402.