Koskamo

Auto-Reader OCR MCP

An official MCP server for the Auto-Reader OCR API that enables AI agents to perform multilingual OCR, document extraction, and translation. It supports Arabic-first and manga-aware Japanese processing, automatic language detection, and structured data extraction from invoices and receipts. The server handles API key provisioning, usage tracking, and offers features like semantic chunking and word-level bounding boxes.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Auto-Reader OCR MCP logo, by Auto-ReaderVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by Auto-Reader
MCP endpoint (Streamable HTTP)
https://api.auto-reader.com/mcp
Vendor documentation

What its tools do

7 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

7 of 7 have a description · 0 of 7 declare behavior hints · 7 of 7 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to auto-reader.com ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Perform multilingual OCR on images and documents
  • Extract structured data from invoices and receipts
  • Translate text between supported languages
  • Detect language and script of input documents

Source and maintenance

Vendor evidenceRegistry 1.0.3
Maintenance checked

Protocol and capabilities

Server
auto-reader-ocr 1.0.0
MCP protocol negotiated in check
2025-06-18
Tools
7 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Auto-Reader OCR extracts text from images (GPU OCR) and translates it across 13+ languages. It is Arabic-first (Arabic/Persian/Urdu accuracy is its strength), manga-aware for vertical Japanese, and auto-detects the script/language when you pass lang="auto". No account setup is needed: any tool that requires a key will auto-provision a free trial key on first use and return it to you — pass that key as the api_key argument on later calls, or set an Authorization: Bearer header. Use create_api_key with an email for the larger free tier, and get_usage to watch your remaining credits. When a call reports being out of credits, the error carries a prefilled checkout link to hand to your human.

Tools

7 advertised

extract_document
Advertised by the server during the last successful anonymous check.

Extract STRUCTURED FIELDS from a document image: invoices, receipts, ID cards — or any custom JSON schema you supply. Every field returns {value, confidence, box} where the confidence and box come from the OCR geometry (never model guesswork); absent fields are null. preset="zatca" additionally decodes the Saudi ZATCA e-invoice QR (TLV) and cross-validates it against the printed fields — use it for Saudi tax invoices. Arabic-first accuracy. 5 credits/page (zatca 7).

extract_document input schema
{
  "type": "object",
  "required": [
    "image_base64"
  ],
  "properties": {
    "lang": {
      "type": "string",
      "default": "auto",
      "description": "Language hint; default auto."
    },
    "preset": {
      "enum": [
        "invoice",
        "receipt",
        "id",
        "zatca"
      ],
      "type": "string",
      "description": "Built-in schema. Use zatca for Saudi e-invoices (adds QR validation)."
    },
    "schema": {
      "type": "object",
      "description": "Custom extraction schema instead of a preset: an object whose keys are the fields you want, values describing them, e.g. {\"policy_number\": \"string|null\"}."
    },
    "api_key": {
      "type": "string",
      "description": "Optional Auto-Reader OCR key (nsk_live_...). If omitted, a free trial key is auto-provisioned and returned to you in the result."
    },
    "image_base64": {
      "type": "string",
      "description": "The document image as base64 (data: URI prefix accepted)."
    }
  }
}
ocr_image
Advertised by the server during the last successful anonymous check.

Extract text from an image with GPU OCR. Best-in-class Arabic (plus Persian/Urdu) accuracy, manga-aware vertical Japanese, and strong English, French, Spanish, German, Chinese, Korean, Russian, Italian and Portuguese — 13+ languages. Automatic language and script detection with lang="auto". Returns reading-order layout text (right-to-left aware, paragraph-gapped) that is ready to feed an LLM or show a human, plus the detected language, the engine used, and the number of text blocks found. Provide the image as base64. Use the mode hint (document | receipt | manga | scene) to tune detection.

ocr_image input schema
{
  "type": "object",
  "required": [
    "image_base64"
  ],
  "properties": {
    "lang": {
      "type": "string",
      "default": "auto",
      "description": "Language/script hint. Default \"auto\" detects it. Codes: ar, fa, ur, en, fr, es, de, ja, zh, ko, ru, it, pt."
    },
    "mode": {
      "enum": [
        "document",
        "receipt",
        "manga",
        "scene"
      ],
      "type": "string",
      "default": "document",
      "description": "Content hint that tunes detection and prompts. Default \"document\"."
    },
    "api_key": {
      "type": "string",
      "description": "Optional Auto-Reader OCR key (nsk_live_...). If omitted, a free trial key is auto-provisioned and returned to you in the result."
    },
    "quality": {
      "enum": [
        "standard",
        "high"
      ],
      "type": "string",
      "default": "standard",
      "description": "\"standard\" (default) lets a confidence gate decide whether the vision model re-reads the page. \"high\" always re-reads it — use when accuracy matters more than cost or latency (costs 2 extra credits and adds a few seconds). You are charged the extra ONLY when it actually applies: check quality_applied in the result, and notice tells you why if it is false (receipt mode, a manga-engine page, an out-of-scope language, or the vision read failing its quality guards)."
    },
    "image_base64": {
      "type": "string",
      "description": "The image encoded as base64 (a data: URI prefix is accepted and stripped)."
    }
  }
}
read_manga
Advertised by the server during the last successful anonymous check.

OCR a comic/manga page, routed by LANGUAGE (not the blanket "manga = Japanese" assumption). Japanese goes to the manga specialist reader that reads vertical, hand-lettered speech bubbles in right-to-left order; Korean manhwa, Chinese manhua and other scripts use their own OCR pack; low-confidence pages escalate to the vision model. Returns text blocks in reading order plus the detected language, the engine used, and whether the page is vertical. Provide the image as base64. Pass lang explicitly (ko/zh/...) for the best non-Japanese result; default "auto" detects it.

read_manga input schema
{
  "type": "object",
  "required": [
    "image_base64"
  ],
  "properties": {
    "lang": {
      "type": "string",
      "default": "auto",
      "description": "Language hint. Default \"auto\". Codes: ja (manga specialist), ko, zh, ar, en, fr, es, de, ru, it, pt."
    },
    "api_key": {
      "type": "string",
      "description": "Optional Auto-Reader OCR key (nsk_live_...). If omitted, a free trial key is auto-provisioned and returned to you in the result."
    },
    "image_base64": {
      "type": "string",
      "description": "The manga/comic page as base64 (a data: URI prefix is accepted and stripped)."
    }
  }
}
translate_text
Advertised by the server during the last successful anonymous check.

Translate text between 13+ languages with an LLM. Arabic-first quality, with formality control (formal/informal) and optional context to disambiguate meaning. Handles both short dictionary-style word lookups and full documents. Returns the translation and, when available, alternative phrasings.

translate_text input schema
{
  "type": "object",
  "required": [
    "text",
    "target_lang"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "The text to translate."
    },
    "api_key": {
      "type": "string",
      "description": "Optional key (nsk_live_...). Auto-provisioned if omitted."
    },
    "context": {
      "type": "string",
      "description": "Optional background text that improves accuracy (it is not translated)."
    },
    "formality": {
      "enum": [
        "formal",
        "informal"
      ],
      "type": "string",
      "description": "Optional register for the output."
    },
    "target_lang": {
      "type": "string",
      "description": "Target language, as a name or code (e.g. English, Arabic, ar, ja, fr)."
    }
  }
}
ocr_and_translate
Advertised by the server during the last successful anonymous check.

One call: OCR an image, then translate every line into target_lang. Arabic-first OCR and manga-aware Japanese with right-to-left-aware layout, followed by LLM translation. Automatic source-language detection. Provide the image as base64. Ideal for reading foreign documents, signs, manga, or receipts end-to-end in a single step.

ocr_and_translate input schema
{
  "type": "object",
  "required": [
    "image_base64",
    "target_lang"
  ],
  "properties": {
    "api_key": {
      "type": "string",
      "description": "Optional key (nsk_live_...). Auto-provisioned if omitted."
    },
    "target_lang": {
      "type": "string",
      "description": "Language to translate into, as a name or code (e.g. English, ar, ja)."
    },
    "image_base64": {
      "type": "string",
      "description": "The image encoded as base64 (a data: URI prefix is accepted and stripped)."
    }
  }
}
get_usage
Advertised by the server during the last successful anonymous check.

Check your Auto-Reader OCR key: tier, remaining daily free credits, prepaid credit balance, subscription allowance, and per-minute rate limit. Use it to throttle yourself before hitting a limit.

get_usage input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "api_key": {
      "type": "string",
      "description": "Optional key (nsk_live_...). Auto-provisioned if omitted."
    }
  }
}
create_api_key
Advertised by the server during the last successful anonymous check.

Provision a new Auto-Reader OCR API key instantly, with no human steps. Pass an optional email to unlock the larger free tier (about 100 credits/day, vs about 50/day for an email-less trial key). Store the returned key and pass it as api_key on future calls.

create_api_key input schema
{
  "type": "object",
  "required": [],
  "properties": {
    "email": {
      "type": "string",
      "description": "Optional email to attach for the larger free tier and a verification link."
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (2 of 2 answered).

  1. 2026-11-06: 1 of 1 checks answered
  2. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
177 ms
95th percentile latency
177 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 177 ms · metadata changed · 7 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http auto-reader-ocr-mcp https://api.auto-reader.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add auto-reader-ocr-mcp --url https://api.auto-reader.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable auto-reader-ocr-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "auto-reader-ocr-mcp": {
      "url": "https://api.auto-reader.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "auto-reader-ocr-mcp": {
      "type": "streamableHttp",
      "url": "https://api.auto-reader.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start auto-reader-ocr-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "auto-reader-ocr-mcp": {
      "type": "http",
      "url": "https://api.auto-reader.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http auto-reader-ocr-mcp https://api.auto-reader.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://api.auto-reader.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "auto-reader-ocr-mcp": {
      "serverUrl": "https://api.auto-reader.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Auto-Reader OCR MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run Auto-Reader OCR MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing