# services.gera/mcp-gera-nexus (npm · @gera-services/mcp-gera-nexus)

Search Gera marketplaces and create consent-first booking intents. No payment taken by server.

- Trust score: 62/100 (medium)
- Change this week: −10
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- npm · `@gera-services/mcp-gera-nexus`: 62/100 (this document), [markdown](https://verifymcp.io/servers/services-gera-mcp-gera-nexus/gera-services-mcp-gera-nexus.md), [page](https://verifymcp.io/servers/services-gera-mcp-gera-nexus/gera-services-mcp-gera-nexus)

## Channel facts

- Registry: `npm`
- Package: `@gera-services/mcp-gera-nexus`
- Version: `1.0.1`
- 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 2026-08-04.

- **Supply Chain Security**: 83/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known medium-severity CVE affects hono 4.12.33, reached via @modelcontextprotocol/sdk > hono. A fixed version is available.
  - 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**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 41 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 994 tokens (~198/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - 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 services-gera-mcp-gera-nexus -- npx -y @gera-services/mcp-gera-nexus
```

### Codex

```bash
codex mcp add services-gera-mcp-gera-nexus -- npx -y @gera-services/mcp-gera-nexus
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add services-gera-mcp-gera-nexus --command npx --arg -y --arg @gera-services/mcp-gera-nexus
```

### Hermes

```yaml
mcp_servers:
  services-gera-mcp-gera-nexus:
    command: "npx"
    args: ["-y", "@gera-services/mcp-gera-nexus"]
```

### Other

```json
{
  "mcpServers": {
    "services-gera-mcp-gera-nexus": {
      "command": "npx",
      "args": [
        "-y",
        "@gera-services/mcp-gera-nexus"
      ]
    }
  }
}
```

## 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.

### 2026-08-04 (score 62, +3)

- [security regression] CVE-2026-69207 affects this package: medium
- [security regression] Known CVEs: partial → fail
- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 59, +44)

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

### 2026-08-01 (score 15, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 0, −33)

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

### 2026-07-30 (score 33, −39)

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

### 2026-07-27 (score 72, +53)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Schema quality: fail
- [functional] Licence: MIT

### 2026-07-26 (score 19)

First indexed and scored.

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

## MCP tools (5)

### `search_home_services` (~178 tokens)

Search GeraHome home-service providers

Find home-service providers (plumbers, electricians, cleaners, handymen, etc.) on GeraHome. Tries the live GeraHome production API first; if unreachable or empty, falls back to real crawled provider records bundled with this server (currently Yerevan, sourced from List.am/Spyur). Read-only — finds providers; it does not book anything. The result's "data_source" field tells you whether rows are live or bundled seed. Pass these provider ids to create_booking_intent to start a consent-first booking.

Input parameters:

- `category` (string): Service category, e.g. "plumber", "electrician", "cleaner".
- `city` (string): City to search in, e.g. "Yerevan".
- `limit` (integer): Max providers to return (default 10).

### `search_jobs` (~167 tokens)

Search GeraJobs job postings

Search jobs on GeraJobs by keyword and location. Tries the live GeraJobs production API first; if unreachable or empty, returns real recruitment-agency / job-board supply partners bundled with this server (clearly labelled — these are where vacancies come from, not individual postings). Read-only. The "data_source" field tells you which you got. To apply, use create_booking_intent with action_kind="job_application" — that creates a consent-first application lead, not a submitted application.

Input parameters:

- `limit` (integer): Max results to return (default 10).
- `location` (string): Location filter, e.g. "London", "GB", "remote".
- `query` (string): Keyword, e.g. "software engineer", "nurse", "driver".

### `search_restaurants` (~187 tokens)

Search restaurants (live UK FHRS data)

Find restaurants for GeraEats, with their current UK Food Hygiene Ratings. Backed by the live Food Standards Agency FHRS open API (api.ratings.food.gov.uk) — genuinely live UK restaurant data, no auth. Filter by city/name and minimum hygiene rating (0-5). Read-only. To place an order, use create_booking_intent with action_kind="restaurant_order" — a consent-first order lead, not a paid order.

Input parameters:

- `city` (string): UK city/town/area to search, e.g. "Bristol", "Manchester".
- `limit` (integer): Max restaurants to return (default 10).
- `min_rating` (integer): Minimum food hygiene rating (0-5). E.g. 4 = only well-rated places.
- `name` (string): Restaurant name to search for, e.g. "Dishoom".

### `create_booking_intent` (~349 tokens)

Create a consent-first booking/action INTENT (no payment)

Create a structured, human-confirmable INTENT to act on a Gera marketplace on the user's behalf — a home-service booking, a job application, or a restaurant order. IMPORTANT — this is the consent gate: it does NOT take payment, does NOT commit a provider, and does NOT execute the transaction. It records what the user wants, assigns a tracking intent_id, writes an audit entry, and returns a confirmation_url (a deep-link) the HUMAN opens to review and complete the action on the real Gera surface. Present the intent and the confirmation link to the user; tell them plainly that nothing has been booked or paid yet and that they must confirm. Use get_action_status to check an intent later. Never tell the user a booking/order/application is "done" from this tool — it is a lead awaiting their confirmation.

Input parameters:

- `action_kind` (string, required): Which marketplace action to create an intent for.
- `consent_acknowledged` (boolean, required): Must be true: confirms the agent has told the user this creates a lead for THEM to confirm, not an executed/paid transaction.
- `contact_name` (string): Name the user wants to book under (kept in the intent for the human to confirm).
- `notes` (string): Free-text details: the task, the order items, the role applied for, etc.
- `provider_id` (string): Id of the chosen provider/job/restaurant from a search_* tool result.
- `provider_name` (string): Human-readable name of the chosen provider/job/restaurant.
- `requested_for` (string): When the user wants it, e.g. "2026-06-20 morning", "ASAP".

### `get_action_status` (~113 tokens)

Look up a booking/action intent status

Look up the status of an intent created earlier by create_booking_intent, by its intent_id. Returns the current status (pending_human_confirmation | expired | unknown) and the audit trail. Note: intents are tracked per running server session — an id from a different session returns "unknown". This server does NOT poll the marketplace for downstream completion; confirmation/payment happens on the Gera surface via the confirmation_url, outside this tool.

Input parameters:

- `intent_id` (string, required): The intent_id returned by create_booking_intent.

## Diagnostics

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

## Score history

- 2026-08-04: 62
- 2026-08-03: 59
- 2026-08-02: 59
- 2026-08-01: 15
- 2026-07-31: 0
- 2026-07-30: 33
- 2026-07-28: 72
- 2026-07-27: 72
- 2026-07-26: 19

## Links

- npm package: https://www.npmjs.com/package/@gera-services/mcp-gera-nexus
- Socket report: https://socket.dev/npm/package/@gera-services/mcp-gera-nexus
- Website: https://geranexus.com/
- Changelog RSS feed: https://verifymcp.io/servers/services-gera-mcp-gera-nexus/gera-services-mcp-gera-nexus/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/services-gera-mcp-gera-nexus/gera-services-mcp-gera-nexus/changelog.json
- HTML version of this page: https://verifymcp.io/servers/services-gera-mcp-gera-nexus/gera-services-mcp-gera-nexus