# Taste MCP server

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

## Links
- Registry page: https://www.getdrio.com/mcp/app-humantaste-taste-mcp
- Repository: https://github.com/with0utwhy/taste-mcp
- Website: https://api.humantaste.app/llms.txt

## Install
- Endpoint: https://api.humantaste.app/mcp/
- Auth: Not captured

## Setup notes
- Remote endpoint: https://api.humantaste.app/mcp/

## Tools
- list_offerings - List all available human expert evaluation offerings with pricing, tool names, and whether each issues an on-chain Taste content certificate. Free. Endpoint: https://api.humantaste.app/mcp/
- list_expert_profiles - Check whether human experts are currently available and the typical response time. Returns aggregate count + estimated wait. No per-expert PII is exposed; use this to decide whether to call a paid tool now or later. Free. Endpoint: https://api.humantaste.app/mcp/
- get_result - 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). Endpoint: https://api.humantaste.app/mcp/
- request_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 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. Endpoint: https://api.humantaste.app/mcp/
- request_illustration_revision - 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. Endpoint: https://api.humantaste.app/mcp/
- verify_external_source - 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. Endpoint: https://api.humantaste.app/mcp/
- review_content - 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. Endpoint: https://api.humantaste.app/mcp/
- verify_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+ 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. Endpoint: https://api.humantaste.app/mcp/
- prepublish_review - 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. Endpoint: https://api.humantaste.app/mcp/
- predict_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 test commits, before ad spend, or before distribution decisions. Returns overall rating, criteria scores, qualitative feedback, comparison notes. Endpoint: https://api.humantaste.app/mcp/
- arbitrate_dispute - 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. Endpoint: https://api.humantaste.app/mcp/
- request_human_approval - 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. Endpoint: https://api.humantaste.app/mcp/
- verify_certificate - 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. Endpoint: https://api.humantaste.app/mcp/
- order_think_tank_session_30 - Convene a think tank — a curated team of vetted human experts — for a 30-minute working session on your idea, problem, or decision. Submit a description, optionally with reference URLs and the deliverables you want back. The team is hand-assembled for the problem and returns a synthesized set of directions, ideas with rationale, and recommended next steps. A longer-running human service: it returns a sessionId and a referenceCode immediately — poll get_result with either once the team is done. Includes 1 free revision turn: call request_think_tank_revision with the referenceCode to request adjustments. Endpoint: https://api.humantaste.app/mcp/
- order_think_tank_session_60 - Convene a think tank — a curated team of vetted human experts — for a 60-minute working session on your idea, problem, or decision. Submit a description, optionally with reference URLs and the deliverables you want back. The team is hand-assembled for the problem and returns a synthesized set of directions, ideas with rationale, and recommended next steps. A longer-running human service: it returns a sessionId and a referenceCode immediately — poll get_result with either once the team is done. Includes 2 free revision turns: call request_think_tank_revision with the referenceCode to request adjustments. Endpoint: https://api.humantaste.app/mcp/

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: app.humantaste
- Version: 2.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 21, 2026
- Source: https://registry.modelcontextprotocol.io