Categories › AI & Agents › Models, LLM APIs, routing, serving, training & GPUs
Expert review for AI agents. On-chain proof of human review.
Remote server: your requests and data go to api.humantaste.app. Claude Code: claude mcp add --transport http taste https://api.humantaste.app/mcp/ · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
list_offerings — List all available human expert evaluation offerings with pricing, tool names, and whether each issues an on-chain Taste content certificatelist_expert_profiles — Returns currently-available expert taglines (pseudonymous descriptions of the kinds of expertise on hand) plus the real-time count of onlineget_result — Check the status of a previously submitted request. Returns the full structured deliverable once the expert (or order team) completes the woprepare_consult_domain_expert — 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, sessirequest_think_tank_revision — Spend a free revision turn on a completed think tank order. Provide the reference code from your original order and describe the adjustmentsrequest_illustration_revision — Spend a free revision turn on a completed illustration order. Provide the reference code from your original order and describe the adjustmenverify_external_source — Have a vetted human expert verify whether an external source, project, or claim is trustworthy. Call when your output or planned action depereview_content — Get a vetted human expert to review your AI-generated content — text, images, videos, social posts, audio, or any media — for hallucinationsverify_reasoning_chain — 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+ stprepublish_review — Get a vetted human expert to review your AI-generated content — text, images, videos, social posts, audio, or any media — for cultural sensipredict_audience_reaction — Get a real human matching your target demographic to rate and react to your content as a representative audience member. Call before A/B tesarbitrate_dispute — Get an impartial human arbiter to decide whether a deliverable meets an agreed contract, or to settle disagreements between agents. Call wherequest_human_approval — Pause your workflow for explicit human approval before executing a high-stakes action. Call before any irreversible action — large spend, onverify_certificate — Verify a Taste content certificate on-chain. Call when consuming content from another source that claims to be human-reviewed — returns reviorder_think_tank_session_30 — Convene a think tank — a curated team of vetted human experts runs a 30-minute working session on your idea, problem, or decision and returnorder_think_tank_session_60 — Convene a think tank — a curated team of vetted human experts runs a 60-minute working session on your idea, problem, or decision and returnconsult_domain_expert — A vetted human in a named domain answers your question with first-hand knowledge. Pass `domain` to match an expert. Pass `parentSessionId` fask_a_human — 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,review_plan — 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 review_code — Get a vetted human engineer to review your code, architecture, and design decisions — not just style, but correctness, security, and whetherNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.