Taste

with0utwhy/taste-mcp

Adds human review as a service for AI agents through nine paid tools that run $1 to $15 per call via x402 payments in USDC on Base. You can verify external sources, audit reasoning chains, run prepublish safety checks, or convene expert think tank sessions. Every approved output gets an on-chain certificate recorded to Base that downstream agents can verify. The free tools let you list offerings, check expert availability, poll session status, and verify certificates without payment. Built for workflows where you need a human in the loop before high-stakes actions or when EU AI Act Article 50 exemptions matter. Hosted endpoint, no installation, uses streamable HTTP transport.

tools: 20
transport: HTTP
last updated: May 21, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://api.humantaste.app/mcp/ --name taste-mcp

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

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

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 20 tools

Verified live against the running server on Nov 6, 2026.

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

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

No parameters. Call it with no arguments.

list_expert_profilesReturns 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...

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...

No parameters. Call it with no arguments.

get_resultCheck 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).2 params

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).

Parameters* required

referenceCodestring

An order reference code (TASTE-...) from a think tank or illustration order. Use this instead of sessionId to retrieve the result — it always returns the latest revision.

sessionIdstring

The session ID returned by a paid tool call.

prepare_consult_domain_expertGet 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 b...5 params

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 b...

Parameters* required

contextstring

Optional. Why you are asking and what you are working on.

domain*string

Area of expertise needed (e.g. Farmer, Protestant priest, UX designer, Stockholm local, art curator, museum staff, culture journalist, food critic).

parentSessionIdstring

Optional. If present, the URL submits a follow-up to an existing consultation (capped at 3 per parent, same expert).

question*string

The specific question to ask the expert.

referenceUrlsarray

Optional. Publicly accessible URLs the expert should review.

request_think_tank_revisionSpend 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....2 params

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....

Parameters* required

adjustments*string

What you want the team to adjust, expand, or rethink.

referenceCode*string

The TASTE-... reference code returned when you placed the think tank order.

request_illustration_revisionSpend 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 retr...2 params

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 retr...

Parameters* required

adjustments*string

What you want the illustrator to adjust, expand, or rethink.

referenceCode*string

The TASTE-... reference code returned when you placed the illustration order.

verify_external_sourceHave 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, vendo...2 params

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, vendo...

Parameters* required

contextstring

Optional context. Use to clarify intent, constraints, audience, or anything that helps the expert evaluate.

subject*string

The URL, project name, or claim to verify. Be specific (e.g. a URL, a project name + token address, or a verbatim claim).

review_contentGet 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 co...2 params

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 co...

Parameters* required

content*string

The content to review. Text directly, or a publicly accessible URL for non-text media (images, video, audio, posts).

contextstring

Optional context. Use to clarify intent, constraints, audience, or anything that helps the expert evaluate.

verify_reasoning_chainAudit 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). Ret...2 params

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). Ret...

Parameters* required

chain*array

Ordered array of reasoning steps. Each step: { step (number), reasoning (string), output (string), toolUsed? (string) }.

contextstring

Optional context. Use to clarify intent, constraints, audience, or anything that helps the expert evaluate.

prepublish_reviewGet 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 di...2 params

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 di...

Parameters* required

content*string

The content to review. Text directly, or a publicly accessible URL for non-text media.

contextstring

Optional context. Use to clarify intent, constraints, audience, or anything that helps the expert evaluate.

predict_audience_reactionGet 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 n...3 params

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 n...

Parameters* required

content*string

The content to evaluate. Text or a publicly accessible URL for non-text media.

contextstring

Optional context. Use to clarify intent, constraints, audience, or anything that helps the expert evaluate.

targetDemographic*string

The audience whose reaction matters. Required — load-bearing for expert matching. E.g. "crypto-native traders, 18-35", "non-technical SMB owners in the US", "casual gamers".

arbitrate_disputeGet 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...8 params

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...

Parameters* required

contextstring

Optional context. Use to clarify intent, constraints, audience, or anything that helps the expert evaluate.

contractDescription*string

The agreed contract or deliverable specification.

deliverable*string

The deliverable to assess. Text or a publicly accessible URL.

partyAPosition*string

One side of the dispute. The expert evaluates both impartially — order is arbitrary.

partyBPosition*string

The other side of the dispute.

termsHashstring

Terms anchor this dispute is bound to: keccak256 of the att/v1 terms manifest (as echoed from the x402 payment), or an opaque 32-byte document hash such as an LCP atrHash ("sha256:0x…" accepted). P...

termsJsonobject

The full att/v1 terms manifest object. If provided it must be a valid manifest whose keccak256 equals termsHash.

termsUristring

Where the att/v1 manifest is hosted (https/ipfs). Convenience only — the hash is the identity.

request_human_approvalPause 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-c...4 params

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-c...

Parameters* required

actionDescription*string

Describe the action awaiting approval. Include numbers (amounts, recipients, URLs) the human needs to see.

contextstring

Optional context. Use to clarify intent, constraints, audience, or anything that helps the expert evaluate.

stakes*string

What kind of risk the action carries. Reversible: undoable. Irreversible: cannot be undone. Financial: moves value. Public: visible externally.one of reversible · irreversible · financial · public

timeoutMinutesinteger

Maximum minutes to wait for a human response before returning denied_timeout. Default 30, max 120.

verify_certificateVerify 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 sign...2 params

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 sign...

Parameters* required

certificateIdvalue

Numeric certificate id. Provide this OR contentHash.

contentHashstring

keccak256 hash of the content, as 0x-prefixed hex. Provide this OR certificateId.

order_think_tank_session_30Convene 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_re...4 params

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_re...

Parameters* required

buyerWalletAddressstring

Optional. An EVM wallet address. If provided, you can later retrieve the deliverable on humantaste.app by connecting this wallet.

description*string

The idea, concept, or problem you want the think tank to work on. Be specific about the goal and any constraints.

mediaUrlsarray

Optional. Publicly accessible URLs to reference material (images, decks, docs, links) the team should review.

requestedDeliverablesarray

Optional. What you want out of the session — e.g. "5 campaign concepts", "a positioning statement", "product name ideas".

order_think_tank_session_60Convene 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_re...4 params

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_re...

Parameters* required

buyerWalletAddressstring

Optional. An EVM wallet address. If provided, you can later retrieve the deliverable on humantaste.app by connecting this wallet.

description*string

The idea, concept, or problem you want the think tank to work on. Be specific about the goal and any constraints.

mediaUrlsarray

Optional. Publicly accessible URLs to reference material (images, decks, docs, links) the team should review.

requestedDeliverablesarray

Optional. What you want out of the session — e.g. "5 campaign concepts", "a positioning statement", "product name ideas".

consult_domain_expertA 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...7 params

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...

Parameters* required

buyerWalletAddressstring

Optional. An EVM wallet address. If provided, you can later retrieve the deliverable on humantaste.app by connecting this wallet.

contextstring

Optional. Why you are asking and what you are working on (essay, research, product decision, etc.). Helps the expert frame their answer.

domain*string

Area of expertise needed. Examples of currently listed domains: "Professional musician", "Cantor", "Writer", "Farmer", "UX designer", "Person living in the Swedish Archipelago", "Stockholm local",...

parentSessionIdstring

Optional. If present, this is a follow-up question to the same expert on an existing consultation. Up to 3 follow-ups per parent. Server validates the parent is completed and within the follow-up cap.

question*string

The specific question to ask the expert. Be precise — the more specific the question, the better the answer.

referenceUrlsarray

Optional. Publicly accessible URLs the expert should review before answering.

requireListedDomainboolean

Optional. If true, the job is declined immediately when the domain is not on the supported listed-domain list, instead of being queued for best-effort sourcing.

ask_a_humanAsk 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 r...1 params

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 r...

Parameters* required

question*string

The plain-text question for a human to answer. Anything you want a quick human take on.

review_planGet 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 a...3 params

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 a...

Parameters* required

contextstring

Optional context. Use to clarify intent, constraints, audience, or anything that helps the expert evaluate.

goal*string

What the plan is meant to achieve — the objective or task it addresses.

plan*string

The implementation or project plan to review. Paste the full plan — steps, approach, architecture, sequencing.

review_codeGet 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 c...3 params

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 c...

Parameters* required

code*string

The code to review. Paste it inline, or pass a publicly accessible URL (e.g. a gist or raw file).

contextstring

Optional context. Use to clarify intent, constraints, audience, or anything that helps the expert evaluate.

intent*string

What the code is meant to do — the behaviour and constraints, plus any correctness or security concerns to focus on.

Readme

Taste

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

This is the public manifest repository for the Taste MCP server. The server is hosted — there is nothing to install. server.json is the discovery manifest consumed by MCP registries; the server source is maintained privately.

what

Pay-per-call human work for AI agents over MCP + x402. Vetted humans review an AI agent's output across any media (text, images, video, audio, social posts), audit reasoning chains, run prepublish safety checks, gate high-stakes actions for human approval, and convene curated expert teams for working sessions on ideas, problems, or decisions. Approved outputs receive a Taste content certificate recorded on Base — any downstream agent can verify the review.

connect

View the full README on GitHub

Details

Repository: github.com/with0utwhy/taste-mcp
Website: api.humantaste.app/llms.txt
Transport: HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026