# io.github.farssaadeldin7-ux/trail-split (mcpb · trail-split.mcpb)

Plan shared gear, food, weight and cost across a group trip so nothing is carried twice and...

- Trust score: 36/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- mcpb · `trail-split.mcpb`: 36/100 (this document), [markdown](https://verifymcp.io/servers/farssaadeldin7-ux-trail-split/trail-split.md), [page](https://verifymcp.io/servers/farssaadeldin7-ux-trail-split/trail-split)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/trail-split.mcpb`
- Version: `0.1.3`
- Transport: `stdio`
- SHA-256: `f99a7f77e31766c62d0536ce706225a8721216c47fd05c1e4abaf5a1d533e675`

## 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 2026-10-23.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1517 tokens (~126/item across 12 items; 12 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

**Unverified: 2 categories.** Categories scored 0 because we could not verify them: 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

### How do I install the io.github.farssaadeldin7-ux/trail-split MCP server?

io.github.farssaadeldin7-ux/trail-split ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, f99a7f77e31766c62d0536ce706225a8721216c47fd05c1e4abaf5a1d533e675; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/trail-split.mcpb`
- SHA-256: `f99a7f77e31766c62d0536ce706225a8721216c47fd05c1e4abaf5a1d533e675`

### Verify on macOS / Linux

```bash
echo "f99a7f77e31766c62d0536ce706225a8721216c47fd05c1e4abaf5a1d533e675  trail-split.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\trail-split.mcpb).Hash -eq "f99a7f77e31766c62d0536ce706225a8721216c47fd05c1e4abaf5a1d533e675"
```

## 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.

### 2026-10-21 (score 36)

First indexed and scored.

## MCP tools (12)

### `gear_taxonomy` (~102 tokens)

The shared-versus-personal classification test, the three tags (SHARED, REDUNDANT-SHARED, PERSONAL) and their rules, the typical classification of common kit, which items split across carriers, and the duplication audit. Reference tables only — it does not classify your list for you. Omit section to get everything.

Input parameters:

- `section` (string): Optional: classification_test, tags, typical_classification, splittable_items or duplication_audit.

### `spof_systems` (~109 tokens)

The seven-system single-point-of-failure table — shelter, water treatment, fire/stove, navigation, first aid, communications, repair — with what counts as an acceptable backup for each, what does not, and the rules that go with the table. Every system needs a named owner and a backup in a different pack, or the plan is not finished. Omit system to get all seven.

Input parameters:

- `system` (string): Optional single system id, e.g. "water_treatment".

### `planning_figures` (~115 tokens)

The planning tables: kcal/person/day by exertion band, food dry weight and ration density, the rationing reserve, water by conditions, treatment throughput by method, fuel by conditions, the per-person carry bands, and the three cost split models. All stated convention with ranges — not physiology, not a forecast, and not a substitute for weighing real kit. Omit section to get everything.

Input parameters:

- `section` (string): Optional: energy, food, reserve, water, treatment, fuel, carry_bands or split_models.

### `size_consumables` (~285 tokens)

Compute food, reserve, water and fuel for a party from the planning figures: dry grams per person per day from kcal and ration density, the mandatory one-day reserve at roughly 60% ration, daily water by conditions, and net canister gas by conditions. Where a figure is a range in the reference and no point is chosen, the result is a range — never an invented midpoint. Requires a paid plan.

Input parameters:

- `days` (number, required): Days on the trip.
- `exertion` (string): sedentary, moderate (default) or cold_or_heavy.
- `fuel_conditions` (string): Optional: temperate, freezing or snow_melt.
- `gas_grams_per_person_day` (number): Optional chosen figure inside the fuel range for the conditions.
- `kcal_per_day` (number): Optional chosen figure inside the exertion band, e.g. 3200.
- `people` (number, required): Number of people.
- `person_days` (number): Optional override where people join or leave mid-trip. Defaults to people × days.
- `ration_density_kcal_per_g` (number): Calorie density of the menu. 4.0 (default) is ordinary mixed hill food, 4.5 is deliberately fat-forward.
- `water_conditions` (string): Optional: temperate, hot_arid, cold_dry or snow_melt.

### `weight_ledger` (~119 tokens)

Total each person's load — personal kit, water, consumables and assigned group mass — against their carry band, and name what binds: who is over, whether the trip fits in aggregate but not as split, whose limit is exceeded before any group mass is added, and who starts with too little headroom. Bands are load convention, not physiology, and a person without a body weight is handled as a self-declared target load, never an assumed 70 kg. Requires a paid plan.

Input parameters:

- `roster` (array, required): One entry per person.

### `settle_costs` (~131 tokens)

Build the cost ledger and settle it: per-expense shares under each expense's own model (even, weighted by nights or person-days, itemised), balances as paid minus owed with an exact zero-sum check, then the greedy settle-up with zero-sum subgroups split out first. Works in whole pennies, gives rounding leftovers to the largest creditor, and reports "settles in N transfers" — never "the minimum", which it cannot prove. Requires a paid plan.

Input parameters:

- `expenses` (array, required): One entry per expense.
- `people` (array, required): Everyone in the ledger, by name.

### `reconcile_plan` (~301 tokens)

Run the four finishing checks: every SHARED instance has exactly one named carrier and every REDUNDANT-SHARED item at least two in different packs; all seven systems have an owner and a backup with a different person; nobody exceeds their band; balances sum to zero and every expense has a payer and a model. Also records the two always-required items — emergency communications and a route plan left with someone off the trip — as recorded, declined or missing. Mechanical checks on names, tags, packs and sums: it cannot judge whether a backup or a first aid kit is any good. Requires a paid plan.

Input parameters:

- `costs` (object): {balances: {name: balance}, expenses: [{label, payer, model}]}, e.g. from settle_costs.
- `emergency_communications` (string): Who carries what and who the named contact is — or "declined".
- `gear` (array): One entry per instance of each shared item.
- `loads` (array): Per person: {name, load_kg, limit_kg} at the heaviest point, e.g. from weight_ledger.
- `route_plan_left_with` (string): Who holds the route plan and when they raise the alarm — or "declined".
- `systems` (object): The seven systems, keyed shelter, water_treatment, fire_stove, navigation, first_aid, communications, repair — each {owner, backup, backup_owner}.

### `license_status` (~49 tokens)

Check the Trail Split licence on this machine: plan, included capabilities, remaining quota and seat usage. Call this when a paid tool reports a licence problem, or when the user asks what their plan includes.

### `license_activate` (~66 tokens)

Store and activate a Trail Split licence key on this machine. Use when the user pastes a licence key, or after a purchase completes.

Input parameters:

- `license_key` (string, required): The licence key, e.g. PS-XXX-00000-00000-00000-0000

### `start_checkout` (~73 tokens)

Begin a Trail Split purchase. Returns a Stripe Checkout link. Call list_plans first if the user has not chosen a plan.

Input parameters:

- `email` (string): Email address for the receipt and licence.
- `plan` (string, required): Plan id: "pro" or "team". Use list_plans to see the options.

### `list_plans` (~23 tokens)

List the available Trail Split plans, prices and what each one includes.

### `billing_portal` (~29 tokens)

Open the Stripe billing portal to change plan, update the card, or cancel the Trail Split subscription.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/farssaadeldin7-ux-trail-split/trail-split#diagnostics

## Score history

- 2026-10-23: 36
- 2026-10-22: 36
- 2026-10-21: 36

## Common questions

### What is the io.github.farssaadeldin7-ux/trail-split MCP server?

io.github.farssaadeldin7-ux/trail-split is an MCP server listed in the public MCP registry as io.github.farssaadeldin7-ux/trail-split. Plan shared gear, food, weight and cost across a group trip so nothing is carried twice and... This page covers its MCPB bundle (https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/trail-split.mcpb).

### Is the io.github.farssaadeldin7-ux/trail-split MCP server safe to use?

io.github.farssaadeldin7-ux/trail-split scores 36 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.farssaadeldin7-ux/trail-split MCP server expose?

io.github.farssaadeldin7-ux/trail-split exposes 12 tools: gear_taxonomy, spof_systems, planning_figures, size_consumables, weight_ledger, and 7 more. Their descriptions and schemas cost roughly 1,402 tokens of context every time the server is loaded.

## Links

- Repository: https://github.com/farssaadeldin7-ux/claude-plugin-suite
- Changelog RSS feed: https://verifymcp.io/servers/farssaadeldin7-ux-trail-split/trail-split.xml
- Changelog JSON feed: https://verifymcp.io/servers/farssaadeldin7-ux-trail-split/trail-split.json
- HTML version of this page: https://verifymcp.io/servers/farssaadeldin7-ux-trail-split/trail-split