
TastePolicy
Qloo taste evidence gated by user rules into ALLOW, ASK or REJECT for agent choices
- Pricing
- Free
- Platforms
- API, Web
- Runs
- Remotely
- Version
- 0.2.0
- Listing updated
- 2 days ago
About TastePolicy
TastePolicy is a free MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.
A strong cultural match is not permission to act, and this service is built around that gap. It takes cultural evidence from Qloo, such as resolved entities and candidate affinity, and then checks the candidate against a person's factual requirements, explicit rules and an authority ceiling for the requested action.
The result is one of four outcomes: ALLOW when requirements are met and the action is within the ceiling, ASK when a critical fact is unknown or the action exceeds the ceiling, REJECT when a hard requirement or rule is violated, and UNAVAILABLE when evidence cannot be obtained. The README stresses that missing evidence is never turned into permission and that a provider outage is never reported as dislike.
The remote MCP endpoint uses OAuth discovery and explicit account consent, with tools for policy, evaluation, lease and proof operations depending on granted scopes. REST, a TypeScript SDK in source and an A2A agent card are also described. The site states that Qloo access is currently hackathon access, commercial permission is pending, and no connector listing or platform endorsement is claimed.
Install
Run in a terminal
claude mcp add --transport http tastepolicy https://tastepolicy.vercel.app/api/mcpAdd to Settings → Connectors → Add custom connector
https://tastepolicy.vercel.app/api/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"tastepolicy": {
"url": "https://tastepolicy.vercel.app/api/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"tastepolicy": {
"type": "http",
"url": "https://tastepolicy.vercel.app/api/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"tastepolicy": {
"serverUrl": "https://tastepolicy.vercel.app/api/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"tastepolicy": {
"type": "http",
"url": "https://tastepolicy.vercel.app/api/mcp"
}
}
}What it does
- Four outcomes
- Returns ALLOW, ASK, REJECT or UNAVAILABLE per candidate and context.
- Qloo evidence
- Resolves cultural anchors and asks for candidate affinity.
- Authority ceiling
- Limits how far an agent may go with a chosen option.
- OAuth consent
- Remote MCP connects with explicit account consent and scopes.
- Receipts and proofs
- Exposes versioned rules, receipts, leases and portable proofs.
Good for
- Check whether an agent may book a recommended venue
- Keep accessibility needs ahead of taste matches
- Audit why an agent was allowed or refused an action
- Build personal agents with explicit permission limits
Pricing
Free
Evaluation service with bounded quotas; paid plans not active
Prices change. Check tastepolicy.vercel.app before you buy.
TastePolicy FAQ
What does ASK mean?
A critical fact is unknown or stale, or the requested action exceeds the person's authority ceiling.
Which data provider does it use?
Qloo, which is the live cultural evidence source.
Is paid billing active?
No. The pricing page says there are currently no charges and paid checkout is not active.
How do I connect?
Use the remote MCP endpoint at https://tastepolicy.vercel.app/api/mcp.
Is TastePolicy free?
Yes. TastePolicy is free to use.
How do I add TastePolicy to Claude Code?
Run this command in your terminal: claude mcp add --transport http tastepolicy https://tastepolicy.vercel.app/api/mcp
What are the best alternatives to TastePolicy?
The closest alternatives to TastePolicy are Claude Code Ultimate Guide, signafAIde, Toolkien, Lugh and HypePaper.
Alternatives to TastePolicy

Claude Code Ultimate Guide
MCP serverMCP server for searching the Claude Code Ultimate Guide from any MCP client
Runs locally- Open source
- 6.5K GitHub stars
- AI models and LLM tooling

signafAIde
MCP serverLocal MCP server to set up, verify and check coverage of signed agent action records
Runs locally- 5 tools
- Freemium
- Security

Toolkien
MCP serverOne MCP gateway for all your MCP servers, with code mode, permissions and audit
Not checked yet- 3 tools
- Remote
- Open source
- AI models and LLM tooling
Lugh
MCP serverWrite, check and dry-run Lugh agent programs with policy, budgets and approvals
Runs locally- 5 tools
- Open source
- AI models and LLM tooling
HypePaper
MCP serverResearch papers, benchmarks, citations and topic experts for AI assistants
- 58 tools
- Remote
- Freemium
- AI models and LLM tooling

One compact entry point that finds, describes and runs hundreds of pay-per-call data tools
- 3 tools
- Remote
- Freemium
- Developer tools