# Nexatron (pypi · nexatron-mcp)

Ask business questions across your enterprise data in plain English, with Nexatron.

- Trust score: 64/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `api.nexatron.io`: 38/100, [markdown](https://verifymcp.io/servers/io-nexatron-mcp/api-v1-mcp.md), [page](https://verifymcp.io/servers/io-nexatron-mcp/api-v1-mcp)
- pypi · `nexatron-mcp`: 64/100 (this document), [markdown](https://verifymcp.io/servers/io-nexatron-mcp/nexatron-mcp.md), [page](https://verifymcp.io/servers/io-nexatron-mcp/nexatron-mcp)

## Channel facts

- Registry: `pypi`
- Package: `nexatron-mcp`
- Version: `1.0.2`
- 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 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 31 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 635 tokens (~48/item across 13 items; 12 tools + 1 resources), lean.
  - 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**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **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 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (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

### How do I install the Nexatron MCP server?

Nexatron runs locally as a PyPI package, launched with uvx nexatron-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add io-nexatron-mcp -- uvx nexatron-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "io-nexatron-mcp": {
      "command": "uvx",
      "args": [
        "nexatron-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-nexatron-mcp": {
      "command": "uvx",
      "args": [
        "nexatron-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add io-nexatron-mcp -- uvx nexatron-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-nexatron-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "nexatron-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-nexatron-mcp --command uvx --arg nexatron-mcp
```

### Hermes

```yaml
mcp_servers:
  io-nexatron-mcp:
    command: "uvx"
    args: ["nexatron-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "io-nexatron-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "nexatron-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-nexatron-mcp -t stdio -c uvx -a nexatron-mcp
```

### Other

```json
{
  "mcpServers": {
    "io-nexatron-mcp": {
      "command": "uvx",
      "args": [
        "nexatron-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.

### 2026-11-05 (score 64, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-04 (score 49)

First indexed and scored.

## MCP tools (12)

### `query` (~95 tokens)

Query

Ask a question about your data in plain English.

Nexatron translates your question into SQL, executes it against your
data sources, and returns the answer with results.

Examples:
\- "Show me total revenue by region for Q4"
\- "Which customers churned in the last 30 days?"
\- "Compare this month's sales to last month"
\- "Top 10 products by units sold"

Input parameters:

- `question` (string, required)

Output parameters:

- `result` (string)

### `list_connections` (~38 tokens)

List Connections

List all data source connections.

Shows connection name, type (PostgreSQL, Snowflake, BigQuery, etc.),
and current health status.

Output parameters:

- `result` (string)

### `get_schema` (~44 tokens)

Get Schema

Get the database schema for a connection.

Shows all tables and their columns with data types.
Use list_connections first to get the connection_id.

Input parameters:

- `connection_id` (string, required)

Output parameters:

- `result` (string)

### `test_connection` (~36 tokens)

Test Connection

Test connectivity to a data source.

Verifies that Nexatron can reach the database and returns latency.

Input parameters:

- `connection_id` (string, required)

Output parameters:

- `result` (string)

### `detect_schema_drift` (~51 tokens)

Detect Schema Drift

Detect schema changes (drift) for a connection.

Compares the current database schema to the last discovered schema
and reports added/removed columns and type changes.

Input parameters:

- `connection_id` (string, required)

Output parameters:

- `result` (string)

### `list_metrics` (~37 tokens)

List Metrics

List all metrics in the semantic layer.

Shows metric name, SQL expression, type, and certification status.
Certified metrics have verified, governed definitions.

Output parameters:

- `result` (string)

### `list_views` (~33 tokens)

List Views

List logical views in the semantic layer.

Logical views are virtual tables that combine physical tables
with business context and computed columns.

Output parameters:

- `result` (string)

### `search_knowledge_base` (~115 tokens)

Search Knowledge Base

Search across knowledge bases using natural language.

Finds relevant document chunks from uploaded PDFs, docs, and notes.
Useful for finding business context, definitions, or policies.
top_k is 1-100. A chunk longer than max_chars (default 500) is shown up to
that length and labelled as an excerpt with both lengths, its chunk_id and
its document_id. max_chars=null returns full chunks.

Input parameters:

- `max_chars`
- `query` (string, required)
- `top_k` (integer)

Output parameters:

- `result` (string)

### `list_conversations` (~30 tokens)

List Conversations

List recent query conversations.

Shows your recent natural language queries and timestamps.

Input parameters:

- `limit` (integer)

Output parameters:

- `result` (string)

### `get_report` (~35 tokens)

Get Report

Get a saved report by ID.

Returns the report title, description, type, and definition.

Input parameters:

- `report_id` (string, required)

Output parameters:

- `result` (string)

### `get_credit_balance` (~26 tokens)

Get Credit Balance

Check your remaining query credits.

Shows current balance, period dates, and usage status.

Output parameters:

- `result` (string)

### `whoami` (~27 tokens)

Whoami

Show your Nexatron user info and tenant.

Returns your email, roles, and organization name.

Output parameters:

- `result` (string)

## Diagnostics

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

## Score history

- 2026-11-05: 64
- 2026-11-04: 49

## Common questions

### What is the Nexatron MCP server?

Nexatron is an MCP server listed in the public MCP registry as io.nexatron/mcp. Ask business questions across your enterprise data in plain English, with Nexatron. This page covers its PyPI package (nexatron-mcp).

### Is the Nexatron MCP server safe to use?

Nexatron scores 64 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. 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 Nexatron MCP server expose?

Nexatron exposes 12 tools: query, list_connections, get_schema, test_connection, detect_schema_drift, and 7 more. Their descriptions and schemas cost roughly 567 tokens of context every time the server is loaded.

### Is the Nexatron MCP server still maintained?

Nexatron is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Nexatron MCP server under?

Nexatron declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/nexatron-mcp/
- Socket report: https://socket.dev/pypi/package/nexatron-mcp
- Website: https://nexatron.io/
- Changelog RSS feed: https://verifymcp.io/servers/io-nexatron-mcp/nexatron-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-nexatron-mcp/nexatron-mcp.json
- HTML version of this page: https://verifymcp.io/servers/io-nexatron-mcp/nexatron-mcp