Skip to main content
Glama
Sign In
deenesjakoruzh
PennyOCR

PennyOCR

by imiraoui
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

PennyOCR MCP server

Un servidor remoto de Model Context Protocol que le da a cualquier agente ojos para leer documento: PDFs e imágenes por URL → markdown (conservando las tablas) o texto plano, con informe exacto de costes y límites de gasto estrictos.

Alojado en https://mcp.pennyocr.com — nada que instalar:

{
  "mcpServers": {
    "pennyocr": {
      "url": "https://mcp.pennyocr.com",
      "headers": { "Authorization": "Bearer pk_live_..." }
    }
  }
}

Las claves son gratuitas (100 páginas/mes) en pennyocr.com/dashboard. Clientes que no puedan establecer cabeceras: https://mcp.pennyocr.com/?key=pk_live_...

Herramientas

Herramienta

Entrada

Salida

read_document

{url, pages?, output?, max_pages?, max_cost_usd?}

{content, pages, cost_usd, citations[]}

estimate_cost

{url, pages?}

número de páginas + coste exacto — gratis

Los límites de gasto deniegan antes, de cualquier procesamiento, mostrando las cifras — de modo que los agentes autónomos puedan razonar sobre el gasto («200 páginas, 0,15 $ — adelante») y nunca puedan superado un saldo prepagado.

Related MCP server: shuck-file

Transporte

Streamable HTTP (JSON-RPC 2.0 sobre POST), sin estado. Este repositorio es el servidor completo: un único Cloudflare Worker (worker.js) que hce de proxy de la API de PennyOCR.

Precios: 0,75 USD por cada 1.000 páginas · * pennyocr.com/pricing.txt · Incorporación de agentes: pennyocr.com/llms.txt

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues

Resources

Related MCP Connectors

Related MCP Servers

  • document-parser

    agenson-tools
    A
    license
    Not graded
    quality
    C
    maintenance
    Provides AI agents with comprehensive document parsing capabilities including PDF text extraction, OCR, HTML-to-markdown conversion, table extraction, and summarization, optimized for agent workflows.
    57 npm
    MIT

  • shuck-file

    Shan-Zhu
    A
    license
    Not graded
    quality
    D
    maintenance
    Provides AI agents with document conversion to Markdown, intelligently routing small and large files, and enabling targeted extraction via sections, search, and token budgets.
    21 PyPI
    6
    MIT

  • doc2md

    skyzhao1223
    A
    license
    A
    quality
    B
    maintenance
    Converts documents to clean Markdown for AI agents from a URL or base64 — no API key, built for remote hosting. Supports PDF (tables preserved as Markdown/CSV/JSON), DOCX, PPTX, XLSX, EPUB, HTML and CSV; scanned PDFs and images go through offline OCR. Includes full-text search, page-range reading, metadata inspection, PDF split/merge and image export, with SSRF-protected fetching, 30 MB limits and
    10
    AGPL 3.0