# Espresso MCP (npm · espresso-mcp)

Find great espresso cafes worldwide with curated data and transparent quality scoring.

- Trust score: 65/100 (medium)
- Change this week: +20
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `espresso-mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/mattgierhart-espresso-mcp/espresso-mcp.md), [page](https://verifymcp.io/servers/mattgierhart-espresso-mcp/espresso-mcp)

## Channel facts

- Registry: `npm`
- Package: `espresso-mcp`
- Version: `0.2.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 76 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 859 tokens (~143/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add mattgierhart-espresso-mcp -- npx -y espresso-mcp
```

### Codex

```bash
codex mcp add mattgierhart-espresso-mcp -- npx -y espresso-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mattgierhart-espresso-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "espresso-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mattgierhart-espresso-mcp --command npx --arg -y --arg espresso-mcp
```

### Hermes

```yaml
mcp_servers:
  mattgierhart-espresso-mcp:
    command: "npx"
    args: ["-y", "espresso-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "mattgierhart-espresso-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "espresso-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 65, +40)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → excellent
- [functional] Licence: MIT

### 2026-07-31 (score 25, −20)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 45, +18)

- [functional regression] Dependency health: partial → unverified
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 27, −18)

- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 45)

First indexed and scored.

## MCP tools (6)

### `find_espresso_near` (~132 tokens)

Find Espresso Near a Location

Find ranked specialty espresso cafes within a radius of given coordinates. Returns cafes from the curated database sorted by espresso-quality score, with distance and score reasoning for each.

Input parameters:

- `lat` (number, required): Latitude in decimal degrees (-90..90).
- `limit` (integer): Maximum number of cafes to return. Default 10.
- `lon` (number, required): Longitude in decimal degrees (-180..180).
- `min_score` (number): Filter out cafes below this espresso quality score (0-100). Default 50.
- `radius_km` (number): Search radius in kilometers. Default 2km.

### `search_cafes` (~180 tokens)

Search Curated Cafes

Search the curated specialty coffee cafe database by name, city, country, roaster, and minimum quality score. Returns scored results sorted by espresso-quality score descending.

Input parameters:

- `city` (string): Filter by city name (case-insensitive exact match).
- `country` (string): Filter by ISO-3166 alpha-2 country code (e.g. 'JP', 'DK', 'US').
- `limit` (integer): Maximum number of cafes to return. Default 20.
- `min_score` (number): Minimum espresso-quality score (0-100). Default 0 (no filter).
- `query` (string): Free-text query matched against cafe name, city, district, and notes (case-insensitive).
- `roaster` (string): Filter to cafes that roast in-house under this name, or serve beans from this roaster.

### `get_cafe_details` (~74 tokens)

Get Cafe Details

Retrieve a full curated record for a cafe by id, including the espresso-quality score breakdown (per-signal contributions) and a few nearby/related cafes.

Input parameters:

- `id` (string, required): Cafe id (slug) — e.g. 'tim-wendelboe-oslo'. Use search_cafes to find ids.

### `score_cafe` (~132 tokens)

Score a Cafe by Observed Signals

Apply the espresso-quality scoring algorithm to a set of observed signals (no database lookup required). Returns a 0-100 score, tier, per-signal contributions, and reasoning. Use this when you've gathered information about a cafe from a website, photo, or review and want a structured assessment.

Input parameters:

- `name` (string): Optional cafe name (used in reasoning and roaster lookup).
- `observed_signals` (object, required): Signals observed about the cafe. Omit fields you don't know — unknowns are skipped, not penalized.
- `source_rankings` (array): Awards / rankings the cafe appears in.

### `list_great_roasters` (~108 tokens)

List Great Coffee Roasters

List curated specialty coffee roasters from the database, filtered by country and reputation tier. Useful for finding cafes that serve a given roaster's beans, or planning a roaster-focused trip.

Input parameters:

- `country` (string): Filter by ISO-3166 alpha-2 country code.
- `limit` (integer): Maximum number of roasters to return. Default 50.
- `min_reputation` (string): Minimum reputation tier. Default: 'notable' (includes all known).

### `list_anti_patterns` (~114 tokens)

List Anti-Pattern Coffee Shops

List shops that exemplify what to AVOID when looking for great espresso. Includes mass-market chains (Starbucks, Dunkin', Costa) and 'flavor-led specialty' shops that display third-wave signage but lean heavily on flavored drinks. Each entry shows why it's flagged. Useful as contrast when recommending real specialty cafes, and as regression fixtures for the scoring algorithm.

Input parameters:

- `category` (string): Filter to a specific anti-pattern category.
- `limit` (integer): Maximum number of entries to return. Default 20.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/mattgierhart-espresso-mcp/espresso-mcp#diagnostics

## Score history

- 2026-08-03: 65
- 2026-08-02: 65
- 2026-08-01: 25
- 2026-07-31: 25
- 2026-07-30: 45
- 2026-07-28: 27
- 2026-07-27: 45

## Links

- npm package: https://www.npmjs.com/package/espresso-mcp
- Socket report: https://socket.dev/npm/package/espresso-mcp
- Repository: https://github.com/mattgierhart/espresso-mcp
- Changelog RSS feed: https://verifymcp.io/servers/mattgierhart-espresso-mcp/espresso-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/mattgierhart-espresso-mcp/espresso-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/mattgierhart-espresso-mcp/espresso-mcp