OCRRouter
Server Details
OCR for agents: PDFs and images to Markdown or JSON, routed across OCR models. Free models included.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
The two tools serve clearly separate phases of the workflow: list_models is read-only discovery of available OCR backends and pricing, while ocr performs the actual extraction. There is no plausible way to confuse one for the other.
Both names are snake_case and short, with list_models following a verb_noun pattern and ocr acting as a bare action verb. The deviation is minor and the names remain immediately readable, but the pair is not a strictly uniform convention.
Two tools is on the thin side for a routing service: the discover-then-execute pair covers the core loop, but there is no room for anything like batch submission, job status, or explicit model comparison without overloading these two.
Discovery plus extraction covers the primary lifecycle, and the ocr tool accepts url or base64 input with selectable models. However obvious operations are absent: no batch or multi-page job handling, no async status for large documents, and no way to inspect or validate a document before processing.
Available Tools
2 toolslist_modelsList OCR modelsARead-onlyInspect
List the OCR models you can route to, with credits per page (0 = free) and whether each is available.
Inputs: no named parameters.
ocrOCR a PDF or imageARead-onlyInspect
Read a PDF or image and return its text as Markdown (tables kept as tables) or JSON blocks. Pass file_url for a public link, or file_base64 for file contents. Models jina/jina-ocr and deepseek/deepseek-ocr are free; auto picks the best model for the document.
Inputs: model, pages, format, file_url, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Document conversion and OCR for AI agents: PDF, Office docs, images to text.
Pay-per-use agent tools: screenshots, web to Markdown, PDF tables, OCR, UK company checks
Convert PDF, Word, Excel and scanned documents to Markdown, tables and RAG chunks. OCR.
Agent-native document parsing: PDF, scans and FR/EU invoices to structured JSON or Markdown.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceGives coding agents on-device OCR that turns images, PDFs and scans into Markdown with tables, plain text or JSON. Also fills a JSON Schema from a document using a local language model, with all processing kept on the machine.67 npm1Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to perform local CPU OCR on scanned PDFs and images, generating searchable PDFs or structured Markdown and inspecting PDFs through four validated tools.1Apache 2.0
- AlicenseAqualityBmaintenanceEnables Claude, Cursor, and other AI agents to read PDFs and scans by submitting documents to an OCR API and saving results as JSON, text, Markdown, or hOCR files. Includes quoting, job status, and human-confirmed budget controls for safe document processing.7490 PyPIMIT

Loupe MCPofficial
AlicenseNot gradedqualityCmaintenanceEnables AI agents to turn PDFs, scans, photos, Office files, and HTML into readable text through signed-URL uploads and batch jobs, using fast page-level OCR or accurate vision-reconciled transcription. Jobs run independently, support page-by-page reading and downloads, and can be deployed securely with Entra authentication.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.