# io.github.henryjrobinson/eve-mentor-mcp (npm · eve-mentor-mcp)

AI mentor for new & returning EVE Online players: losses, skills, fits, ISK, routes, and more.

- Trust score: 70/100 (medium)
- Change this week: +24
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `eve-mentor-mcp`: 70/100 (this document), [markdown](https://verifymcp.io/servers/henryjrobinson-eve-mentor-mcp/eve-mentor-mcp.md), [page](https://verifymcp.io/servers/henryjrobinson-eve-mentor-mcp/eve-mentor-mcp)

## Channel facts

- Registry: `npm`
- Package: `eve-mentor-mcp`
- Version: `0.1.2`
- 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 49 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 81/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1941 tokens (~74/item across 26 items; 26 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.

## Install

### Claude

```bash
claude mcp add henryjrobinson-eve-mentor-mcp -- npx -y eve-mentor-mcp
```

### Codex

```bash
codex mcp add henryjrobinson-eve-mentor-mcp -- npx -y eve-mentor-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add henryjrobinson-eve-mentor-mcp --command npx --arg -y --arg eve-mentor-mcp
```

### Hermes

```yaml
mcp_servers:
  henryjrobinson-eve-mentor-mcp:
    command: "npx"
    args: ["-y", "eve-mentor-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "henryjrobinson-eve-mentor-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "eve-mentor-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.

### 2026-08-03 (score 70, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 66, +45)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: unverified
- [functional] Licence: MIT

### 2026-07-31 (score 21, −25)

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

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (26)

### `lookup_item` (~56 tokens)

Look up any EVE item, ship, or module by exact name. Returns its description and Jita market prices.

Input parameters:

- `name` (string, required): Exact in-game name, e.g. "Rifter" or "Damage Control II"

### `system_intel` (~53 tokens)

Danger report for a solar system: security status, ship/pod kills and traffic in the last hour.

Input parameters:

- `system_name` (string, required): Exact system name, e.g. "Jita" or "Tama"

### `recent_losses` (~67 tokens)

A character's recent ship losses from zKillboard with full fit detail — the raw material for explaining why they died. Works for any character name, no login needed.

Input parameters:

- `character_name` (string, required): Exact character name
- `limit` (integer): How many losses (1-10)

### `can_i_fly` (~89 tokens)

What does it take to fly/use a ship or module? Returns the full recursive skill prerequisite tree, an ordered training plan, total skillpoints, and estimated training time. If a character is logged in, the plan is diffed against their actual trained skills.

Input parameters:

- `item_name` (string, required): Exact ship or module name, e.g. "Vexor" or "Damage Control II"

### `ammo_advisor` (~94 tokens)

Which damage type to shoot (and tank) against a target: NPC pirate factions (Guristas, Serpentis, Angels, Blood Raiders, Sansha, Rogue Drones, Triglavians) or shield/armor-tanked players. Includes concrete ammo names per weapon system.

Input parameters:

- `target` (string, required): Faction or tank type, e.g. "Guristas" or "armor-tanked player"

### `analyze_fit` (~83 tokens)

Mechanical fit check: classifies each module by type and detects classic mistakes (mixed weapon systems, mixed shield+armor tank, no propulsion, damage mods without matching weapons). Feed it module names from a loss report or a pasted fit, then explain the findings to the player.

Input parameters:

- `module_names` (array, required): Module names exactly as they appear in the fit/killmail

### `fit_readiness` (~106 tokens)

Paste an EFT-format fit (the text every fitting site, PyFA, and the in-game fitting window export) and get a can-fly verdict: which skills are missing to online every module and the hull, in training order, with total skillpoints and days. Personalized against the logged-in character; when not logged in it lists every skill the fit requires.

Input parameters:

- `fit` (string, required): EFT-format fit text, starting with a header line like [Heron, My Fit]

### `proven_fits` (~105 tokens)

What modules pilots actually fly on a given ship, learned from recent killmails: the most common modules per slot with how often each appears. Use it to propose a realistic starter fit, then sanity-check that fit with analyze_fit and can_i_fly.

Input parameters:

- `sample` (integer): How many recent killmails to learn from (5-40)
- `ship_name` (string, required): Exact ship name, e.g. "Heron" or "Vexor"

### `career_test` (~101 tokens)

Data for the EVE career 'sorting hat'. Returns all recognized career paths with traits (social/risk/income/activity, who it appeals to, first ship, first steps). To use: interview the player about what they enjoy (solo vs group, risk appetite, building vs fighting vs exploring, active vs idle, how much structure they want), THEN call this and match their answers to 2-3 paths. Recommend concrete first steps, not just labels.

### `jargon` (~70 tokens)

EVE slang glossary. Pass a term to define it, or no term to list everything known. Use whenever the player hits a word like 'krab', 'tidi', 'doctrine', or 'asset safety'.

Input parameters:

- `term` (string): The slang term to define; omit to list all terms

### `isk_guidance` (~126 tokens)

Viable ways to make ISK matched to a player's skillpoint tier (0-1M, 1-5M, 5-20M, 20M+), each with an honest ISK/hour range, what it requires, and a first step. Use it to answer 'how do I make money?' for someone's actual stage — point new players at the high-ratio activities (exploration ≫ mining) and away from grinds that only pay at high skillpoints. Ranges are rough community consensus, not live data; never present them as guarantees.

### `what_should_i_do_tonight` (~80 tokens)

Answers 'what should I actually do right now?' by composing the logged-in character's real situation — skillpoints, wallet, location security, current ship, what's training — with the income options for their skillpoint tier. Returns the building blocks; you turn them into 2-3 concrete, situation-aware session suggestions. Requires login.

### `remember_goal` (~83 tokens)

Save a goal or ambition the player states ('I want to fly a Gila', 'aiming for nullsec exploration', 'save up for a freighter') so it persists across sessions. Call this whenever the player expresses a direction worth steering toward later. Stored per character.

Input parameters:

- `goal` (string, required): The goal in the player's own terms, one ambition per call

### `recall_pilot_notes` (~59 tokens)

The goals this player has previously asked you to remember, oldest first. Call it at the start of a session (or alongside what_should_i_do_tonight) to pick up where you left off and steer coaching toward what they actually want.

### `cheapest_way_to_play` (~69 tokens)

EVE's pay-vs-play economy explained with live numbers: Alpha (free) vs Omega (subscribed), how PLEX lets you buy game time with ISK instead of money, today's actual Jita price for an Omega month, and an honest grind-hours-vs-cash recommendation.

### `sitrep` (~51 tokens)

Session-start situation report in one call: login state, character overview (skillpoints/wallet/location/ship), what's training, and the most recent loss. Call this at the start of a mentoring session to orient.

### `route_danger` (~134 tokens)

Per-jump safety report for a journey between two systems: each system's security and last-hour kill activity, plus the notorious high-sec gank chokepoints (Uedama, Niarja, Sivala...) a new player wouldn't know to avoid. Use it before anyone undocks for a long haul.

Input parameters:

- `destination` (string, required): Exact destination system name, e.g. "Amarr"
- `origin` (string, required): Exact start system name, e.g. "Jita"
- `prefer_safer` (boolean): Prefer the high-sec route where one exists (true) vs the shortest route (false)

### `where_to_buy` (~91 tokens)

Compares an item's cheapest sell price across EVE's five major trade hubs (Jita, Amarr, Dodixie, Rens, Hek), and — when logged in — how many jumps each hub is from where the player is sitting, so you can weigh price against the haul.

Input parameters:

- `item_name` (string, required): Exact item/ship/module name, e.g. "Damage Control II"

### `whats_happening` (~69 tokens)

A 'what's going on in EVE right now?' briefing for new or returning players: live server status, active incursions (which make whole regions dangerous), the biggest recent kills galaxy-wide, and where to read the latest patch notes. Good for someone logging back in after time away.

### `evaluate_corp` (~95 tokens)

Newbie-friendliness signals for a corporation by exact name: size, age, war exposure, and recent activity from ESI + zKillboard, plus the questions to ask that no API can answer. Use it to sanity-check a corp before the player applies. The API can't see recruitment status or culture — be honest about that.

Input parameters:

- `corp_name` (string, required): The full corporation name (not the ticker), exactly

### `eve_login` (~33 tokens)

Start the EVE Online login flow. Opens a browser for SSO; the user must complete it within 3 minutes.

### `eve_auth_status` (~20 tokens)

Check whether an EVE character is currently logged in.

### `character_sheet` (~27 tokens)

The logged-in character's overview: total skillpoints, wallet, current location, and ship.

### `skill_queue` (~18 tokens)

The logged-in character's current skill training queue.

### `my_assets` (~44 tokens)

Everything the logged-in character owns, grouped by location. Flags asset-safety wraps and structures the character can no longer dock at — use this to find stuff stranded from years ago.

### `top_skills` (~41 tokens)

The logged-in character's highest-trained skills — useful for judging what they can fly well.

Input parameters:

- `limit` (integer): How many skills (1-50)

## Diagnostics

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

## Score history

- 2026-08-03: 70
- 2026-08-02: 66
- 2026-08-01: 21
- 2026-07-31: 21
- 2026-07-30: 46
- 2026-07-28: 46
- 2026-07-27: 46

## Links

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