mcpField
T
Taste Overlap

Taste Overlap

Remote
taste-overlap.onrender.comMaps & Travel0Updated 2w ago

About Taste Overlap

Taste Overlap is an MCP server for planning an evening around two people’s shared preferences. It uses Qloo affinity scores to rank places, explain matches, and arrange an activity, meal, and drink.

Key features

  1. 01Ranks places for each person and their shared tastes
  2. 02Scores overlap using Qloo affinities
  3. 03Explains picks with shared taste tags
  4. 04Arranges an activity, food, and drink

Use cases

  1. 01Plan a city evening around two people’s favourites
  2. 02Review why a recommended place matches both people

MCP support

Provides the `plan_shared_evening` tool through stdio and a remote Streamable HTTP endpoint. It returns an explained plan as text and structured content.

Configuration

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

Endpointhttps://taste-overlap.onrender.com/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

1
ParameterTypeRequiredDescription
citystringYesCity, e.g. Vienna
person_aarrayYesFavourites of person A
person_barrayYesFavourites of person B

Details

From the project README

Taste Overlap

Two people, a few favourites each (artists, films, shows, books, places). Qloo's taste graph ranks places in your city for person A, for person B and for both together. Taste Overlap keeps only the places that rank well for both (harmonic mean of the two affinities, so one-sided picks drop out), explains each pick with the shared taste tags, and orders them into an evening: something to do, food, then a drink.

Without Qloo there is nothing to show: the overlap is computed from Qloo's per-person affinities, not from an LLM guess.

Run

Needs Node.js 22.19+ and the official Qloo harness (the supported event surface):

npm install --global @qloo/qloo-harness   # qloo --version >= 0.1.26
export QLOO_API_KEY=...                    # the hackathon key (or: qloo setup --qloo)
export QLOO_BASE_URL=https://hackathon.api.qloo.com
export QLOO_TRUSTED_BASE_URL=https://hackathon.api.qloo.com   # the harness only sends a key to an approved endpoint
npm start                                  # http://localhost:8787

Demo without credentials: QLOO_TRANSPORT=demo npm start replays a real recorded run (demo/vienna.json, 11 qloo exec calls) through the same code. Only that example works (Vienna; Radiohead + Wes Anderson / Taylor Swift + Studio Ghibli); other inputs return an error instead of invented places.

Optional: QLOO_TRANSPORT=rest with QLOO_API_KEY uses the direct REST client (src/qloo.js) instead; QLOO_BASE, PORT.

Use it from an agent (MCP tool)

Remote, nothing to install: the live demo also speaks MCP at https://taste-overlap.onrender.com/mcp (streamable HTTP, JSON answers). In claude.ai or the Claude app: Settings → Connectors → Add custom connector and paste that URL. Tool calls share the demo's per-visitor and daily limits.

Local (stdio):

Taste Overlap is also an agent tool: mcp-server.js is a dependency-free MCP stdio server with one tool, plan_shared_evening (city, person_a[], person_b[]). It returns the explained evening as text plus structured content, and any MCP client can call it:

claude mcp add taste-overlap -- node /path/to/taste-overlap/mcp-server.js   # Claude Code
# or in claude_desktop_config.json / Cursor: {"command": "node", "args": ["/path/to/mcp-server.js"],
#   "env": {"QLOO_API_KEY": "...", "QLOO_BASE_URL": "https://hackathon.api.qloo.com", "QLOO_TRUSTED_BASE_URL": "https://hackathon.api.qloo.com"}}

Without a key, QLOO_TRANSPORT=demo makes the tool answer the recorded Vienna example.

Test

node --test

How it works

  • src/mcp.js (default transport) - one long-running qloo mcp process (the harness's canonical MCP adapter) serves every workflow as qloo_<op>; on a small host this takes ~0.5-1.2 s per call instead of >30 s for a fresh qloo exec. QLOO_TRANSPORT=exec switches back to one qloo exec per call.
  • src/harness.js - the Qloo workflows: recommend (target_type: place, the favourites as signals, filter_location: the city) for A, B and both; entity_tags for the tags that explain each pick. The harness resolves the names and validates input before calling Qloo; when a name is ambiguous (status: needs_input) the client takes Qloo's top-ranked non-album candidate, retries once with its entity id and returns that choice. Workflow names are fixed, user text goes in on stdin.
  • Each pick's reason comes from Qloo's per-result explainability (signal.interests.entities): which favourites drove the place and by how much.
  • src/demo.js - records and replays real harness envelopes for the credential-free demo.
  • src/qloo.js (fallback) - resolves each favourite with /search, ranks places with /v2/insights (filter.type=urn:entity:place, signal.interests.entities, filter.location.query). The key is sent as a header from the server and never reaches the browser.
  • src/overlap.js - pure logic: shared picks, reasons, evening order (unit-tested). Qloo returns at most 20 places per call, and two tastes can share none of them (measured: Berlin, Daft Punk + Christopher Nolan vs Adele + Pixar). Real overlaps come first; the rest is topped up from the joint list and labelled "combined taste". A place scored one-sided in both personal lists never comes back that way.
  • src/plan.js - three Qloo calls (A, B, both) -> overlap -> explained plan.
  • server.js - dependency-free Node server, serves public/ and POST /api/plan.
  • mcp-server.js - the same plan as an MCP tool for agents; src/transport.js picks the Qloo transport for both.

License

MIT

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.