# ocr-software.com OCR (pypi · ocr-software-mcp)

Read PDFs and images with ocr-software.com: page count, job, text, Markdown, JSON, hOCR.

- Trust score: 67/100 (medium)
- Change this week: −12
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- pypi · `ocr-software-mcp`: 67/100 (this document), [markdown](https://verifymcp.io/servers/ocr-software-ocr-software-mcp/ocr-software-mcp.md), [page](https://verifymcp.io/servers/ocr-software-ocr-software-mcp/ocr-software-mcp)

## Channel facts

- Registry: `pypi`
- Package: `ocr-software-mcp`
- Version: `0.3.1`
- 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 2026-11-21.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 0 of 29 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to ocr-software/ocr-software-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 6 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 62/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1453 tokens (~207/item across 7 items; 7 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the ocr-software.com OCR MCP server?

ocr-software.com OCR runs locally as a PyPI package, launched with uvx ocr-software-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 ocr-software-ocr-software-mcp -- uvx ocr-software-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "ocr-software-ocr-software-mcp": {
      "command": "uvx",
      "args": [
        "ocr-software-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ocr-software-ocr-software-mcp": {
      "command": "uvx",
      "args": [
        "ocr-software-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ocr-software-ocr-software-mcp -- uvx ocr-software-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ocr-software-ocr-software-mcp --command uvx --arg ocr-software-mcp
```

### Hermes

```yaml
mcp_servers:
  ocr-software-ocr-software-mcp:
    command: "uvx"
    args: ["ocr-software-mcp"]
```

### Netclaw

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

### Vellum

```bash
assistant mcp add ocr-software-ocr-software-mcp -t stdio -c uvx -a ocr-software-mcp
```

### Other

```json
{
  "mcpServers": {
    "ocr-software-ocr-software-mcp": {
      "command": "uvx",
      "args": [
        "ocr-software-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.

### 2026-11-20 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 66, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-18 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 80, +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.

### 2026-11-14 (score 79, +19)

- [security improvement] Malware scan: unverified → pass
- [functional regression] Schema quality: 178 → 207
- [functional improvement] Tool coverage: 0% → 100%
- [functional improvement] Stability: unverified → 0.03
- [functional] Package version: 0.1.0 → 0.3.1
- [functional] Package version: 0.1.0 → 0.2.3
- [functional] Package version: 0.1.0 → 0.2.2

### 2026-11-13 (score 60)

First indexed and scored.

## MCP tools (7)

### `list_pipelines` (~128 tokens)

List what the service offers (no key needed): per pipeline one line (summary: what it delivers, price per page in euros,
when to choose another one), formats and features, and default_pipeline: the fastest and cheapest available one, used when no pipeline is named. Show the available ones
to the human with the default; you are asked to let the human pick and not to choose a pipeline yourself. detail=true adds
descriptions, capabilities, measurements and hardware (long, rarely needed).

Input parameters:

- `detail` (boolean): true adds descriptions, capabilities, measurements and hardware (long)

### `quote` (~165 tokens)

Dry run: nothing runs, nothing is billed. Returns quote_id, the page count and say_to_human, one sentence with the
price: you are asked to show it to the human word for word and get a yes before submit_job. pipeline is name@version from list_pipelines; if the
human named none, leave it out: the default (fastest and cheapest available) is used and the sentence names it.
The quote_id is for one document, one pipeline and one job.

Input parameters:

- `dpi`: render resolution for PDF pages; leave out for the default
- `file_path` (string, required): absolute path of one PDF, PNG, JPEG or TIFF file
- `pipeline`: name@version from list_pipelines; leave out if the human named none

### `submit_job` (~234 tokens)

Start the job of a quote (document, pipeline and price are bound to the quote_id; the budget is the quoted price).
You are asked to set human_confirmed=true only after the human saw say_to_human and really agreed (the server cannot check it); if the client can ask the human itself it asks
when you leave it false. With wait_seconds and format the result is saved like get_result. Without wait_seconds it returns at once: use job_status, keep the job_id.

Input parameters:

- `client_ref`: your own reference, kept with the job
- `format`: json, text, md, hocr or pdf: save the result when done (needs wait_seconds)
- `human_confirmed` (boolean): true only after the human saw say_to_human and agreed
- `out_dir`: folder for the result file; not allowed if the human set OCR_OUT_DIR
- `quote_id` (string, required): from quote; valid for one job, one hour
- `wait_seconds` (integer): 0 to 300: hold until the job is done; 0 returns at once

### `job_status` (~172 tokens)

State and counts of a job. Holds until the job is done or wait_seconds (0 to 300) are over, and reports progress
meanwhile: one call is enough, do not poll in a loop; if state is still running call again. When state is done, check
problem (pages failed or not run) and tell the human. format (json, text, md, hocr, pdf) saves the result when done.

Input parameters:

- `format`: json, text, md, hocr or pdf: save the result when done
- `job_id` (string, required): from submit_job
- `out_dir`: folder for the result file; not allowed if the human set OCR_OUT_DIR
- `wait_seconds` (integer): 0 to 300: hold until the job is done

### `get_result` (~308 tokens)

Result of a finished job. Default: write it to a file and return path, size and
check: words, mean confidence and uncertain words per page, notes such as probably several columns. The content stays
out of the chat. pages ('3', '1-5') returns those pages' text here, search the matching lines with page numbers;
neither writes a file. The file goes to ocr-results next to the document by default; pdf is searchable.
Results expire after about 24 hours.
In the json: confidence is 0 to 1, box is [x0,y0,x1,y1] in pixels of the page image (page width, height). verified (per word) is
true only where a second reader confirmed it (scan-vlm-ctc@2); safe_ok (per page) is always false today. Judge by confidence.

Input parameters:

- `format`: json (default), text, md, hocr or pdf; file output only
- `job_id` (string, required): from submit_job
- `out_dir`: folder for the file; not allowed if the human set OCR_OUT_DIR
- `pages`: like 3 or 1-5 or 2,4,7-9: return the text of these pages here, no file
- `search`: return the lines containing this text with page numbers, no file
- `source_path`: original document, needed for pdf after a restart of this server

### `cancel_job` (~91 tokens)

Stop a running job, or delete the result of a finished one (DELETE /v1/jobs/{id}). You are asked to set human_confirmed=true only
after the human agreed (the server cannot check it). Pages already read stay charged; check job_status afterwards.

Input parameters:

- `human_confirmed` (boolean): true only after the human agreed to cancel
- `job_id` (string, required): from submit_job

### `uncertain_words` (~218 tokens)

Words the OCR read with low confidence (below max_confidence, default 0.9: the words of the gold set that were really
wrong sat at about 0.83) or flagged as differing readings (scan-vlm-ctc), least
sure first: page, word, confidence, other_reading if there is a second one, and box [x0,y0,x1,y1] in pixels of the page
image (page_size: width and height per page). Check these against the image of the page, do not trust them blindly, and tell
the human what you corrected. limit 1 to 100, max_confidence 0 to 1. Needs a finished job.

Input parameters:

- `job_id` (string, required): from submit_job
- `limit` (integer): 1 to 100: most words returned
- `max_confidence` (number): 0 to 1: list words below this confidence
- `pages`: like 3 or 1-5: only these pages

## Diagnostics

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

## Score history

- 2026-11-21: 67
- 2026-11-20: 67
- 2026-11-19: 66
- 2026-11-18: 81
- 2026-11-17: 80
- 2026-11-16: 80
- 2026-11-15: 80
- 2026-11-14: 79
- 2026-11-13: 60

## Common questions

### What is the ocr-software.com OCR MCP server?

ocr-software.com OCR is an MCP server listed in the public MCP registry as io.github.ocr-software/ocr-software-mcp. Read PDFs and images with ocr-software.com: page count, job, text, Markdown, JSON, hOCR. This page covers its PyPI package (ocr-software-mcp).

### Is the ocr-software.com OCR MCP server safe to use?

ocr-software.com OCR scores 67 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 ocr-software.com OCR MCP server expose?

ocr-software.com OCR exposes 7 tools: list_pipelines, quote, submit_job, job_status, get_result, and 2 more. Their descriptions and schemas cost roughly 1,316 tokens of context every time the server is loaded.

### Is the ocr-software.com OCR MCP server still maintained?

ocr-software.com OCR 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 ocr-software.com OCR MCP server under?

ocr-software.com OCR declares the MIT 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 ocr-software.com OCR MCP server?

VerifyMCP ran 15 checks on ocr-software.com OCR, 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 ocr-software.com OCR: 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/ocr-software-mcp/
- Socket report: https://socket.dev/pypi/package/ocr-software-mcp
- Repository: https://github.com/ocr-software/ocr-software-mcp
- Website: https://ocr-software.com/
- Changelog RSS feed: https://verifymcp.io/servers/ocr-software-ocr-software-mcp/ocr-software-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ocr-software-ocr-software-mcp/ocr-software-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ocr-software-ocr-software-mcp/ocr-software-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ocr-software-ocr-software-mcp/ocr-software-mcp
