espresso-mcp

An MCP server that finds great espresso cafes — and codifies what makes them great.

espresso-mcp is a Model Context Protocol server you can plug into Claude Desktop, Claude.ai, ChatGPT, Google Gemini, Cursor, Hermes, OpenClaw, and any other standard MCP host. It ships with a curated database of 100+ specialty-coffee shops, 75+ specialty roasters, and a transparent scoring algorithm that captures why a shop is good — sourcing, freshness, equipment, training — and why a shop is bad (the heaviest negative signal: menus dominated by flavored syrups).

It is not a Yelp clone. The data is hand-curated, the scoring is explicit, and the philosophy is "if it's covering bad coffee with flavors, we don't want it."

The bias

espresso-mcp has an opinion. Shops that hide bad coffee behind flavored syrups are the failure pattern this tool is designed to filter out. The scoring algorithm gives syrup_emphasis the heaviest non-disqualifying penalty (−22) — heavier than any single positive signal. Mass-market chains (Starbucks, Dunkin', Costa, Tim Hortons, Peet's, Caribou) and "looks third-wave but tastes flavored" shops (the algorithm's flavor-led-specialty category) score in avoid or fair tier regardless of how good the signage looks.

Positive credit goes to the signals great shops actually invest in:

• In-house roasting, or named-partner sourcing from a known specialty roaster
• Single-origin espresso (not just blends)
• Roast date on retail bags (peak-freshness commitment)
• Espresso + pour-over both offered — the "complete program"
• Cortado on the menu — a confidence proxy; shops avoid small milk drinks when their espresso can't hold up
• Competition involvement / SCA-certified staff
• Equipment from the third-wave shortlist (Slayer, La Marzocco, Synesso, Decent, Victoria Arduino, Modbar)
• Recognition from authoritative rankings (World's 100 Best, SCA championships, Coffee Review 95+, Good Food Awards)

Every signal is documented at src/scoring/weights.ts and surfaced to clients via the score breakdown on every result — you can see exactly why a cafe is recommended.

See it in action

You: I'm near Brandenburg Gate in Berlin. Find me 3 great espresso cafes 
     within walking distance.

Claude: [resolves Brandenburg Gate → 52.5163, 13.3777]
        [calls find_espresso_near with radius_km=2]

  Found 3 specialty cafes within 2km of Brandenburg Gate, sorted by quality:

  • The Barn (Mitte)         — 0.8km — score 95 (world-class) — World's #61
    In-house roastery, single-origin focus, "never blends beans." Founded 
    2010, one of Europe's leading third-wave roasters.

  • Companion Coffee (Mitte) — 1.1km — score 83 (great)
    Curated multi-roaster with rotating guest beans. Tea + coffee crossover 
    in a quiet Mitte design space.

  • Westberlin (Mitte)       — 1.3km — score 82 (great)
    Iconic third-wave anchor since ~2010. Magazine + coffee concept; pours 
    The Barn and rotating European roasters.

What it does

Once installed in your MCP client, you can ask things like:

• "I'm at the Hotel Adlon Berlin — find me great espresso within walking distance."
• "I'm staying near the Brandenburg Gate. Recommend 3 cafes and rank by quality."
• "Search for cafes in Tokyo scoring above 80."
• "Tell me about Tim Wendelboe."
• *"Score this cafe — they have a Slaye

... View full README on GitHub