Taste MCP Server

by humantaste Your server? Claim it

answering

Taste is answering right now. Last checked 2 min ago. It exposes 20 tools. Last commit 23 May 2026.

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

Uptime history 48 days of history

48 days agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

454 ms

Response time

average over 24h

Stars

last commit 23 May 2026

Nothing serious here today

Today is the operative word: we check Taste every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add taste-mcp --transport http https://api.humantaste.app/mcp/

~/Library/Application Support/Claude/claude_desktop_config.json

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

~/.codex/config.toml

[mcp_servers.taste-mcp]
url = "https://api.humantaste.app/mcp/"

.cursor/mcp.json

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

.vscode/mcp.json

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

Available tools 20

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

request

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.

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.

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.

review

review_code

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.

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.

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 — 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.

verify

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, 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

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.

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.

order

order_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 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.

order_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 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.

arbitrate

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.

ask

ask_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, 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.

consult

consult_domain_expert

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.

expert

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.

offerings

list_offerings

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

predict

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.

prepare

prepare_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, 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.

prepublish

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.

result

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).

Endpoints

URL	Transport	State	Latency	Checked
https://api.humantaste.app/mcp/	streamable-http	answering	412 ms	2 min ago

Alternatives to Taste

same job, measured the same way

Proctor

by louissarvin

Human oversight for AI agents: block a tool call on a verified human, with on-chain proof.

196 installs/wk local only

Callable

by ccstt-dev

API for AI agents to delegate tasks to real humans.

3 tools answering

Agent Browser

by aetherai3

Self-hosted Chrome for AI agents, with a live noVNC view a human can take over.

1 675 installs/wk local only

Cryptair MCP Server

by syronius

Tamper-evident attestation tools for AI agents — on-chain receipts on Hedera Hashgraph mainnet.

31 installs/wk local only

Elicitly Pro

by elicitly

Human-in-the-loop for AI agents over MCP: durable approvals with a hosted review page & audit trail

answering

Regex

by rog0x

Regex test, explain, replace patterns for AI agents

27 installs/wk local only

Penholder

by penholder

Preventive human-approval write-gate for AI agents: writes commit only after a human approves.

answering

Agentschat MCP

by swswordholy-tech

Shared live rooms for AI agents to chat, vote, run OKRs, hand off to humans - join, don't rebuild.

399 installs/wk local only

Taste — questions

Answers built from our own checks of this server.

What can Taste do?

It exposes 20 tools, read directly from the server on our last check. Among them: arbitrate_dispute, ask_a_human, consult_domain_expert, get_result, list_expert_profiles, list_offerings and 14 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

What is Taste mostly used for?

Its tools cluster around verify, request and review. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.

Is Taste working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 454 ms. The bar chart above shows every period we have measured.

How do I connect Taste?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Taste need an API key?

No. Taste completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 20 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Taste?

It answers our handshake in 454 ms on average, which is faster than 32% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Taste open source?

Yes — it is published under the MIT licence, 0 stars on GitHub and 2 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.