# ReadAnyDoc (pypi · readanydoc)

Parse PDFs, scans and Office files to Markdown; extract typed fields with page citations.

- Trust score: 64/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- pypi · `readanydoc`: 64/100 (this document), [markdown](https://verifymcp.io/servers/arpitpatel25-readanydoc/readanydoc.md), [page](https://verifymcp.io/servers/arpitpatel25-readanydoc/readanydoc)

## Channel facts

- Registry: `pypi`
- Package: `readanydoc`
- Version: `0.4.6`
- 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 2026-11-21.

- **Supply Chain Security**: 49/100
  - Malware scan not yet available for this package.
  - 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.
  - 5 of 51 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to arpitpatel25/ReadAnyDoc).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 0 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 58/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 749 tokens (~187/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 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).

## Install

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

ReadAnyDoc runs locally as a PyPI package, launched with uvx --from 'readanydoc[engine]==0.4.6' readanydoc mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add arpitpatel25-readanydoc -- uvx --from 'readanydoc[engine]==0.4.6' readanydoc mcp
```

### Cursor

```json
{
  "mcpServers": {
    "arpitpatel25-readanydoc": {
      "command": "uvx",
      "args": [
        "--from",
        "readanydoc[engine]==0.4.6",
        "readanydoc",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "arpitpatel25-readanydoc": {
      "command": "uvx",
      "args": [
        "--from",
        "readanydoc[engine]==0.4.6",
        "readanydoc",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add arpitpatel25-readanydoc -- uvx --from 'readanydoc[engine]==0.4.6' readanydoc mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "arpitpatel25-readanydoc": {
      "type": "local",
      "command": [
        "uvx",
        "--from",
        "readanydoc[engine]==0.4.6",
        "readanydoc",
        "mcp"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  arpitpatel25-readanydoc:
    command: "uvx"
    args: ["--from", "readanydoc[engine]==0.4.6", "readanydoc", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "arpitpatel25-readanydoc": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "--from",
        "readanydoc[engine]==0.4.6",
        "readanydoc",
        "mcp"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "arpitpatel25-readanydoc": {
      "command": "uvx",
      "args": [
        "--from",
        "readanydoc[engine]==0.4.6",
        "readanydoc",
        "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.

### 2026-11-21 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-20 (score 63, 0)

- [functional] Package version: 0.4.4 → 0.4.6

### 2026-11-19 (score 63, +1)

- [functional regression] Schema quality: 392 → 749
- [functional improvement] Schema quality: 196 → 170
- [functional] Package version: 0.3.0 → 0.4.4
- [functional] Package version: 0.3.0 → 0.4.3
- [functional] Package version: 0.3.0 → 0.4.2

### 2026-11-18 (score 62, −1)

- [functional regression] Schema quality: pass → fail
- [functional] Package version: 0.1.8 → 0.3.0
- [functional] Package version: 0.1.8 → 0.2.0

### 2026-11-17 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 62, 0)

- [security improvement] Malware scan: unverified → pass
- [functional improvement] Stability: unverified → 0.03
- [functional] Package version: 0.1.6 → 0.1.8

### 2026-11-15 (score 62)

First indexed and scored.

## MCP tools (4)

### `parse_document` (~96 tokens)

Parse a local document (PDF, image, DOCX, XLSX, PPTX ...) into Markdown.

path: file on this computer. mode: "engine" (default, most accurate) or "model-only" (one model read per
page, faster). pages: 1-based page numbers to read; all pages when omitted.

Input parameters:

- `mode` (string)
- `pages`
- `path` (string, required)

### `extract_fields` (~278 tokens)

Extract structured values from a local document into a JSON Schema, with citations.

schema: a JSON Schema object (type "object" with properties). instructions: optional guidance for the
extraction. array_extract: true for long lists or tables that span many pages. review: also list values to
check (found by code, no extra cost). alternatives: also return other values the document gives for a field
(a special term or an amendment that changes a price). part_tokens: largest document part per call, in tokens
(default 30,000). parse_first: false to skip parsing (the model reads the file itself: about half the cost and
faster, less accurate, fewer citations). fill_required: which required fields always get a value: "choices"
(default, yes/no and enum fields), true (numbers and text too: the model may guess, each guess is flagged in
to_check as filled_because_required), a list of field paths, or false (nothing forced).

Input parameters:

- `alternatives` (boolean)
- `array_extract` (boolean)
- `fill_required`
- `instructions`
- `mode` (string)
- `parse_first` (boolean)
- `part_tokens`
- `path` (string, required)
- `review` (boolean)
- `schema` (object, required)

### `list_test_sets` (~55 tokens)

The public test sets (invoices, receipts, financial reports, contracts, research papers, resumes, result
tables, long reports), with what each tests, its size and its licence, and the systems that can be compared.

### `run_test` (~177 tokens)

Compare systems on a public test set (set_id) or on the user's own documents (folder + schema_path, and
answers_folder with <file stem>.json answer keys if they have them). Scored by code against the answer key.

With confirm=false (the default) nothing is spent: it returns the plan (documents, pages, rough cost per
system, systems that cannot run and why). Ask the user, then call again with confirm=true to run it. Returns
the scores per system and the path of an HTML report with a citation viewer for every document.

Input parameters:

- `answers_folder`
- `budget_usd`
- `confirm` (boolean)
- `folder`
- `limit`
- `out`
- `schema_path`
- `set_id`
- `systems`

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/arpitpatel25-readanydoc/readanydoc#diagnostics

## Score history

- 2026-11-21: 64
- 2026-11-20: 63
- 2026-11-19: 63
- 2026-11-18: 62
- 2026-11-17: 63
- 2026-11-16: 62
- 2026-11-15: 62

## Common questions

### What is the ReadAnyDoc MCP server?

ReadAnyDoc is an MCP server listed in the public MCP registry as io.github.arpitpatel25/readanydoc. Parse PDFs, scans and Office files to Markdown; extract typed fields with page citations. This page covers its PyPI package (readanydoc).

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

ReadAnyDoc scores 64 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. 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 ReadAnyDoc MCP server expose?

ReadAnyDoc exposes 4 tools: parse_document, extract_fields, list_test_sets, run_test. Their descriptions and schemas cost roughly 606 tokens of context every time the server is loaded.

### Is the ReadAnyDoc MCP server still maintained?

ReadAnyDoc is still listed as active in the MCP registry. We last reached this channel on 21 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 ReadAnyDoc MCP server under?

ReadAnyDoc declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the ReadAnyDoc MCP server?

VerifyMCP ran 15 checks on ReadAnyDoc, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about ReadAnyDoc: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/readanydoc/
- Socket report: https://socket.dev/pypi/package/readanydoc
- Repository: https://github.com/arpitpatel25/ReadAnyDoc
- Website: https://arpitpatel25.github.io/ReadAnyDoc/
- Changelog RSS feed: https://verifymcp.io/servers/arpitpatel25-readanydoc/readanydoc.xml
- Changelog JSON feed: https://verifymcp.io/servers/arpitpatel25-readanydoc/readanydoc/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/arpitpatel25-readanydoc/readanydoc.json
- HTML version of this page: https://verifymcp.io/servers/arpitpatel25-readanydoc/readanydoc
