# DocQA MCP (npm · docqa-mcp)

AI document verification: catch hallucinations, arithmetic errors, and field mismatches.

- Trust score: 63/100 (medium)
- Change this week: +23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `docqa-mcp`: 63/100 (this document), [markdown](https://verifymcp.io/servers/com-agentsconsultants-api-docqa/docqa-mcp.md), [page](https://verifymcp.io/servers/com-agentsconsultants-api-docqa/docqa-mcp)

## Channel facts

- Registry: `npm`
- Package: `docqa-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 2026-08-03.

- **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**: 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 123 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 514 tokens (~102/item across 5 items; 5 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 com-agentsconsultants-api-docqa -- npx -y docqa-mcp
```

### Codex

```bash
codex mcp add com-agentsconsultants-api-docqa -- npx -y docqa-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-agentsconsultants-api-docqa": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "docqa-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-agentsconsultants-api-docqa --command npx --arg -y --arg docqa-mcp
```

### Hermes

```yaml
mcp_servers:
  com-agentsconsultants-api-docqa:
    command: "npx"
    args: ["-y", "docqa-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "com-agentsconsultants-api-docqa": {
      "command": "npx",
      "args": [
        "-y",
        "docqa-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.

### 2026-08-02 (score 63, +63)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional] Licence: MIT

### 2026-07-31 (score 0, −40)

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

### 2026-07-27 (score 40)

First indexed and scored.

## MCP tools (5)

### `docqa-verify` (~254 tokens)

Verify AI extraction results against an original document. Detects hallucinated values, arithmetic errors, and field mismatches. Returns a confidence score and detailed report.

Input parameters:

- `callerTool` (string): Name of the tool that produced the extraction (e.g. 'tesseract', 'azure-form-recognizer'). DocQA will use a different method for independent verification.
- `document` (string): Base64-encoded original document (PDF or image). Required for standard tier cross-extraction. Omit for basic pattern/arithmetic checks only.
- `extraction` (object, required): Key-value pairs of extracted fields to verify. Example: { invoice_number: 'INV-001', total: '$1,200.00', date: '03/15/2024' }
- `language` (string): OCR language code for re-extraction (default: eng)
- `mode` (string): gate: returns simple { pass, confidence, failReasons }. full (default): returns complete verification report.
- `tier` (string): basic ($0.05): pattern + arithmetic checks only. standard ($0.50): full cross-extraction with OCR/PDF re-parse. Auto-detected from presence of 'document'.

### `docqa-sample` (~45 tokens)

Fetch a sample DocQA verification report to understand the output format. Free, no API key needed for this tool. Use this to preview DocQA output before submitting real documents.

### `pdf-extract` (~60 tokens)

Extract structured text and tables from a PDF document. Returns text content, page count, detected tables, and metadata.

Input parameters:

- `file` (string, required): Base64-encoded PDF file content
- `filename` (string): Original filename (optional, for logging)

### `ocr` (~77 tokens)

Extract text from an image using Tesseract OCR. Supports PNG, JPG, TIFF, BMP, WebP. Returns recognized text and confidence score.

Input parameters:

- `file` (string, required): Base64-encoded image file content
- `filename` (string): Original filename (optional)
- `language` (string): OCR language code (default: eng)

### `convert` (~78 tokens)

Convert a document between formats. Input formats: pdf, md, json, txt. Output formats: txt, md, json.

Input parameters:

- `file` (string, required): Base64-encoded source document
- `filename` (string): Original filename with extension (optional)
- `from` (string, required): Source format
- `to` (string, required): Target output format

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-agentsconsultants-api-docqa/docqa-mcp#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 63
- 2026-08-01: 0
- 2026-07-31: 0
- 2026-07-30: 40
- 2026-07-28: 40
- 2026-07-27: 40

## Links

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