ocr-software.com OCR
PYPI · OCR-SOFTWARE-MCP
Read PDFs and images with ocr-software.com: page count, job, text, Markdown, JSON, hOCR.
Available components
Last scanned (15 hours ago)
Scores higher than 60% of PyPI servers
Category Documents and Files
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. How we score → Why this is hard to score →
Supply Chain Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 0 of 29 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to ocr-software/ocr-software-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 6 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability62
- AI-judged instruction clarity (good).Pass
- 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. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
- Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (15)
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Nov 26 +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.
- 19 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 18 Nov 26 +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.
- 15 Nov 26 +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.
- 14 Nov 26 +19
- Malware scan: unverified → pass ▲ security
- Schema quality: 178 → 207 ▼ functional
- Tool coverage: 0% → 100% ▲ functional
- 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 functional
- 13 Nov 26 60
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed pypi/ocr-software-mcp@0.3.1
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | ocr-software/ocr-software-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/ocr-software/ocr-software-mcp/.github/workflows/publish.yml@refs/tags/v0.3.1 |
| Rekor log index | 3875217755 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:fd0a4128f486f90c87520e547c3522fb1b29a199346e87a3a7e8776bc580ff0b |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 29 packages
| Packages resolved | 29 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
cancel_job ~91
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.
| Name | Type | Req | Description |
|---|---|---|---|
| human_confirmed | boolean | – | true only after the human agreed to cancel |
| job_id | string | yes | from submit_job |
No output schema declared.
No examples provided.
get_result ~308
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.
| Name | Type | Req | Description |
|---|---|---|---|
| format | – | – | json (default), text, md, hocr or pdf; file output only |
| job_id | string | yes | 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 |
No output schema declared.
No examples provided.
job_status ~172
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.
| Name | Type | Req | Description |
|---|---|---|---|
| format | – | – | json, text, md, hocr or pdf: save the result when done |
| job_id | string | yes | 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 |
No output schema declared.
No examples provided.
list_pipelines ~128
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).
| Name | Type | Req | Description |
|---|---|---|---|
| detail | boolean | – | true adds descriptions, capabilities, measurements and hardware (long) |
No output schema declared.
No examples provided.
quote ~165
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.
| Name | Type | Req | Description |
|---|---|---|---|
| dpi | – | – | render resolution for PDF pages; leave out for the default |
| file_path | string | yes | absolute path of one PDF, PNG, JPEG or TIFF file |
| pipeline | – | – | name@version from list_pipelines; leave out if the human named none |
No output schema declared.
No examples provided.
submit_job ~234
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | yes | from quote; valid for one job, one hour |
| wait_seconds | integer | – | 0 to 300: hold until the job is done; 0 returns at once |
No output schema declared.
No examples provided.
uncertain_words ~218
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.
| Name | Type | Req | Description |
|---|---|---|---|
| job_id | string | yes | 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 |
No output schema declared.
No examples provided.
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.
pypi · ocr-software-mcp
claude mcp add ocr-software-ocr-software-mcp -- uvx ocr-software-mcp
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.