Skip to main content
Glama
Sign In
mcp_ocr

mcp_ocr

by timaliev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

ocr_batch_xiaomi

OCR multiple images in one batch and return consolidated results with Markdown text, HTML tables, LaTeX formulas, and key-information extraction for document parsing.

Instructions

OCR multiple images at once. Returns consolidated results.

Backend: xiaomi. Xiaomi-OCR-0 — local 0.8B document-parsing VLM (transformers; Apple Silicon MPS, CUDA or CPU). Best structure fidelity: Markdown output, HTML tables, LaTeX formulas, key-information extraction. Strong on Cyrillic, English, German and Japanese; Arabic/Korean are weak.

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": {
      "paths": "<paths>"
    },
    "name": "ocr_batch_xiaomi"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNo
modeNoaccurate
pathsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.2

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does disclose the backend model, its size class (0.8B), and local execution across MPS/CUDA/CPU, which sets latency and hardware expectations. It omits operational behavior: how results are ordered or aligned to input paths, whether one failure aborts the batch, and any size or count limits.

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 purpose is stated in the first sentence, and the backend/capability paragraph is dense with decision-relevant facts rather than filler. It is well sized for the amount of information conveyed, though the model-naming prefix is slightly redundant.

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

Completeness3/5

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

A batch tool with no output schema, no annotations, and 0% parameter coverage needs more than this. The description characterizes the backend well, but leaves the mode/lang parameters and the shape of the 'consolidated results' undefined, which is a real gap for a multi-file operation.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate and largely doesn't. The `mode` parameter (default 'accurate') is never explained — no list of valid modes or what changes — and `paths` and `lang` are only indirectly touched via the prose about language strengths.

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

Purpose4/5

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

The description gives a specific verb and scope: 'OCR multiple images at once' and 'Returns consolidated results.' The batch nature plus the `ocr_batch_` name prefix distinguishes it from single-image siblings, though the description never explicitly names those alternatives.

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

Usage Guidelines3/5

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

Selection guidance is implied rather than stated: 'Best structure fidelity' and the language-strength list suggest choosing this over `ocr_batch_paddle` or `ocr_batch_vision` when structure or Cyrillic/German/Japanese matters. There is no explicit when-not or direct comparison to the sibling batch tools.

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

Deploy Server

Other Tools