# io.github.lordolami/poldex (npm · @poldex/mcp-server)

MCP server exposing PolDex commercial insurance extraction tools to AI agents.

- Trust score: 53/100 (low)
- Change this week: +14
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@poldex/mcp-server`: 53/100 (this document), [markdown](https://verifymcp.io/servers/lordolami-poldex/poldex-mcp-server.md), [page](https://verifymcp.io/servers/lordolami-poldex/poldex-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@poldex/mcp-server`
- Version: `0.0.3`
- 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 (96 of 100), 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 (96 of 100), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 6/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (UNLICENSED) isn't a recognized OSI-approved license.
  - Actively maintained (last published 95 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 57/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 443 tokens (~49/item across 9 items; 9 tools + 0 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**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 67% 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 lordolami-poldex -- npx -y @poldex/mcp-server
```

### Codex

```bash
codex mcp add lordolami-poldex -- npx -y @poldex/mcp-server
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add lordolami-poldex --command npx --arg -y --arg @poldex/mcp-server
```

### Hermes

```yaml
mcp_servers:
  lordolami-poldex:
    command: "npx"
    args: ["-y", "@poldex/mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "lordolami-poldex": {
      "command": "npx",
      "args": [
        "-y",
        "@poldex/mcp-server"
      ]
    }
  }
}
```

## 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 53, +53)

- [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] License: unverified → fail
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: UNLICENSED

### 2026-08-01 (score 0, −21)

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

### 2026-07-31 (score 21, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 39)

First indexed and scored.

## MCP tools (9)

### `list_schemas` (~18 tokens)

List commercial insurance extraction schemas PolDex supports.

### `get_schema` (~36 tokens)

Get a machine-readable PolDex schema contract with fields, example output, and proof documents.

Input parameters:

- `schema_id` (string, required): Schema identifier.

### `get_credits` (~25 tokens)

Return available, held, and total PolDex credits for the configured API key.

### `estimate_extraction` (~83 tokens)

Estimate pages, credits, and output names before running extraction. This does not spend credits.

Input parameters:

- `file_paths` (array): Local file paths readable by this MCP server.
- `schema` (string): Commercial insurance schema to use.
- `text_items` (array): Inline document text items.
- `url_items` (array): Remote document URLs for PolDex to fetch.

### `extract_batch` (~111 tokens)

Run extraction for text, URLs, or local files. This can hold and capture credits, so confirm_cost must be true.

Input parameters:

- `confirm_cost` (boolean, required): Must be true to confirm the agent is allowed to spend PolDex credits.
- `file_paths` (array): Local file paths readable by this MCP server.
- `schema` (string): Commercial insurance schema to use.
- `text_items` (array): Inline document text items.
- `url_items` (array): Remote document URLs for PolDex to fetch.

### `get_batch` (~31 tokens)

Fetch processor batch status, item states, credit settlement, and result links.

Input parameters:

- `batch_id` (string, required)

### `get_job` (~27 tokens)

Fetch a PolDex async extraction job by job_id.

Input parameters:

- `job_id` (string, required)

### `list_connector_events` (~45 tokens)

List completed or failed connector events for polling agents and automation tools.

Input parameters:

- `limit` (integer)
- `since` (string): Cursor or ISO timestamp returned by a prior call.

### `download_artifact` (~67 tokens)

Download a batch artifact to a local path. Use only for artifacts returned by PolDex batch status.

Input parameters:

- `artifact` (string, required)
- `batch_id` (string, required)
- `output_path` (string, required): Local path where the artifact should be written.
- `overwrite` (boolean)

## Diagnostics

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

## Score history

- 2026-08-03: 53
- 2026-08-02: 53
- 2026-08-01: 0
- 2026-07-31: 21
- 2026-07-30: 39
- 2026-07-28: 39
- 2026-07-27: 39

## Links

- npm package: https://www.npmjs.com/package/@poldex/mcp-server
- Socket report: https://socket.dev/npm/package/@poldex/mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/lordolami-poldex/poldex-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/lordolami-poldex/poldex-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/lordolami-poldex/poldex-mcp-server