mcpField
T
Taste

Taste

Remote
api.humantaste.appAI & Agents0Updated 23w ago

About Taste

Taste is a hosted MCP server that routes AI work to vetted human experts for review, approval, and collaborative sessions. Its paid calls use x402 with USDC on Base, and reviewed outputs can receive certificates recorded on-chain.

Key features

  1. 01Review AI content for errors
  2. 02Audit reasoning chains
  3. 03Check prepublication safety
  4. 04Pause workflows for human approval
  5. 05Order expert team sessions
  6. 06Issue verifiable review certificates

Use cases

  1. 01Review generated content before publication
  2. 02Audit an AI agent's reasoning
  3. 03Require approval before an irreversible action
  4. 04Get expert input on a decision

MCP support

Provides free discovery, result, and certificate tools, plus paid human-review tools to MCP clients. Paid calls use x402 payments in USDC on Base.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.humantaste.app/mcp/
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

17

This tool takes no parameters.

Details

From the project README

Taste

smithery badge

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

MCP endpoint:  https://api.humantaste.app/mcp/
Transport:     Streamable HTTP (MCP 2025-06-18)
Payment:       x402, USDC on Base mainnet, $1.00–$15.00 per paid call
Free tools:    list_offerings, list_expert_profiles, get_result, verify_certificate
Typical wait:  5–30 min for evaluation calls; up to 24h for a think tank session

No authentication, no API key. Paid tools answer an unauthenticated call with HTTP 402; sign an EIP-3009 USDC transfer and retry.

tools

Free (no payment, no session):

ToolPurpose
list_offeringslist offerings, prices, certificate flag, operating-hours state
list_expert_profilesaggregate availability + estimated response time, no PII
get_resultpoll session status by sessionId or order reference code; returns the full deliverable when complete
verify_certificateread-only Taste content certificate lookup on Base, rate-limited 60/min/IP

Paid (x402 — USDC on Base):

ToolPricePurpose
verify_external_source$1.00verify whether an external source, project, or claim is trustworthy
review_content$1.00review AI-generated content for hallucinations, factual errors, domain mistakes — issues a certificate
verify_reasoning_chain$1.00audit a step-by-step reasoning chain for mid-chain errors — issues a certificate
prepublish_review$1.00review content for cultural sensitivity, brand safety, derivative risk before publishing — issues a certificate
predict_audience_reaction$1.00a human matching a target demographic rates and reacts to content
arbitrate_dispute$1.00an impartial human arbiter decides whether a deliverable meets a contract
request_human_approval$1.00pause a workflow for explicit human approval before an irreversible action
order_think_tank_session_30$5.00convene a curated team of human experts for a 30-min working session on an idea, problem, or decision; returns synthesized directions (1 free revision turn)
order_think_tank_session_60$15.00as above, 60-min session (2 free revision turns)

Each think tank order returns a TASTE-XXXX-XXXX-XXXX reference code. Two contextual helper tools — request_think_tank_revision and request_illustration_revision — spend a free revision turn against that code.

The live tool list is authoritative — server.json sets tools: "dynamic", so MCP clients call tools/list against the endpoint for the current surface.

example

curl -X POST https://api.humantaste.app/mcp/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
       "params":{"name":"list_offerings","arguments":{}}}'

Paid calls return HTTP 402 with an X-Payment-Requirements header (base64 JSON). Sign EIP-3009 transferWithAuthorization for USDC on Base, then retry the same request with an X-Payment header.

compliance

EU AI Act Article 50(2) exempts AI-generated content from mandatory AI-disclosure labels when it has undergone human review or editorial control. Taste content certificates are the on-chain audit trail for that exemption.

links

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.