ocr-software.com OCR
ocr-software/ocr-software-mcp
Read PDFs and images with ocr-software.com: page count, job, text, Markdown, JSON, hOCR.
- tools
- 6
- auth
- Secret needed
- transport
- STDIO
- env vars
- 4
- last updated
- Nov 14, 2026
Tools
6 toolsPublic tool metadata for what this MCP can expose to an agent.
list_pipelinesShort list: per pipeline one summary line (what it delivers, price per page in euros, when to choose another one), formats and features, and default_pipeline, from GET /v1/catalog (no key needed); detail=true gives the full catalog.
Short list: per pipeline one summary line (what it delivers, price per page in euros, when to choose another one), formats and features, and default_pipeline, from GET /v1/catalog (no key needed); detail=true gives the full catalog.
No parameter schema in public metadata yet.
quoteDry run of POST /v1/jobs. Returns a quote_id and say_to_human, a plain sentence with the page count and the amounts in euros. Nothing runs, nothing is billed.
Dry run of POST /v1/jobs. Returns a quote_id and say_to_human, a plain sentence with the page count and the amounts in euros. Nothing runs, nothing is billed.
No parameter schema in public metadata yet.
submit_jobStarts the job from the quote_id; the budget comes from the quote, so the agent never handles it. Sends an Idempotency-Key, so a retry never creates a second job or a second charge.
Starts the job from the quote_id; the budget comes from the quote, so the agent never handles it. Sends an Idempotency-Key, so a retry never creates a second job or a second charge.
No parameter schema in public metadata yet.
job_statusWaits up to wait_seconds (default 45) until the job is done, with progress messages, in one call.
Waits up to wait_seconds (default 45) until the job is done, with progress messages, in one call.
No parameter schema in public metadata yet.
get_resultFetches json, text, md, hocr or pdf (searchable PDF, needs the original document), writes it to a file and returns the path, the size and a quick check.
Fetches json, text, md, hocr or pdf (searchable PDF, needs the original document), writes it to a file and returns the path, the size and a quick check.
No parameter schema in public metadata yet.
uncertain_wordsThe words the OCR is least sure about: page, word, confidence, the other reading where the pipeline has two, the box in pixels and the page size.
The words the OCR is least sure about: page, word, confidence, the other reading where the pipeline has two, the box in pixels and the page size.
No parameter schema in public metadata yet.
Sponsors
Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthly
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any language
Agent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any languageConfiguration
OCR_KEY*secretAPI key, starts with ocr_. Never shown to the model.
OCR_BASE_URLdefault: https://api.ocr-software.comAddress of the service; for your own server e.g. http://127.0.0.1:8080.
OCR_OUT_DIRFolder where results are written. Default: ocr-results next to the document, else ~/Documents/ocr-results.
OCR_ALLOWED_DIROptional: read documents only from below this folder.
Readme
OCR MCP server for ocr-software.com: let Claude, Cursor and other agents read PDFs and scans
Give your AI agent a way to read documents: this MCP server sends PDF, PNG, JPEG and TIFF files to the ocr-software.com OCR API and writes the result (JSON with word boxes, text, Markdown or hOCR) to a file. The API is hosted in Helsinki, EU (Hetzner). It also works against the package on your own server, which takes the same calls: set OCR_BASE_URL to its address (install guide).
Details
- Repository
- github.com/ocr-software/ocr-software-mcp
- Website
- ocr-software.com
- Categories
- Documents & Knowledge, Data & Analytics
- Package
ocr-software-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
