Skip to main content
Glama

AI OCR: scanned PDF or image to Markdown

doc_ocr
Read-only

AI OCR of a scanned PDF (up to 10 pages, 5 MB) or a PNG, JPEG or WebP image (up to 7.5 MB) at a public URL: printed text, tables, headings, lists, checkboxes and legible handwriting transcribed to Markdown page by page, with page count, file type, size and image dimensions. For scans, photos, screenshots, receipts and forms without a text layer. AI-generated by Anthropic Claude under a fixed Kit Rx prompt; transcription can misread characters. URL fetch is SSRF-guarded. Price: $0.02 per successful call, paid in USDC with x402 v2; failed calls and calls that match nothing are not charged. AI-generated answer; a call with no arguments returns the stored example answer without a model call.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "doc_ocr"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYeshttp or https URL of a PDF (at most 10 pages and 5 MB) or a PNG, JPEG or WebP image (at most 7.5 MB and 8000 x 8000 px). Default ports only; credentials, IP addresses, localhost and private or single-label names are rejected.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds substantial behavior beyond the readOnly and openWorld annotations: page and size limits, supported formats, output fields, AI misread risk, SSRF protection, per-call pricing, failed-call billing, and no-argument example behavior. This is exactly the kind of operational context an agent needs before paying for a call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose, then limits, output, caveats and billing. It is dense but nearly every sentence earns its place; the no-argument example behavior is useful though slightly buried at the end.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the burden of explaining return content and does so by naming Markdown transcription, page count, file type, size and image dimensions. It also covers accuracy, billing and failure behavior, making it complete for a single-URL OCR tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the URL constraints, supported formats and rejected address types are already fully documented in the schema. The description does not add material meaning about the url parameter beyond what the schema provides, so the baseline score applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: AI OCR of scanned PDFs or images into Markdown. It also scopes the input types and output content page by page, which lets an agent distinguish this from text-layer Markdown conversion tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear when-to-use guidance: scans, photos, screenshots, receipts and forms without a text layer. It does not explicitly name an alternative tool for digital PDFs, so the agent must infer that doc_markdown-like siblings are for text-layer documents.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources