Skip to main content
Glama
omd-local

omd-mcp

by omd-local

convert_to_markdown

Convert URLs, local files, directories, PDFs, Office docs, images, audio, and web pages into Markdown for local AI context workflows.

Instructions

Ingest a user-selected URL, file path, or directory into untrusted Markdown for local AI context workflows. Core routes include PDF/DOCX/PPTX/XLSX/HTML/CSV/ZIP via markitdown, PNG/JPG/JPEG via OCR, audio via local transcription, generic web pages, and directories as batches. Advanced public/local-only routes include social posts, WeChat articles, XHS/Douyin, reels, and podcasts when their source access requirements are met.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
uriYesURL, absolute file path, or directory path
langNoTesseract language(s) for image OCR (default eng; Chinese + English example: chi_sim+eng).eng
outputNoOptional output .md/.Rmd path. If omitted, returns content inline.
reel_optionsNoExtra args forwarded to reel_to_markdown.py for video URLs (safe conversion flags only, e.g. ['--polish', '--ocr']).
output_formatNoOutput format: Markdown (.md) or RMarkdown (.Rmd). Defaults to md; explicit .md/.Rmd output paths are inferred when omitted.md

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.1/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. It does add useful context — output is 'untrusted Markdown', directories become batches, and advanced routes have access requirements — but it omits permissions/auth needs, failure modes, rate limits, and side effects for a tool that touches local files and network sources.

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

Conciseness3/5

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

The purpose is front-loaded in the first sentence, which is good, but the two following sentences are dense, enumerative run-ons of format acronyms that are hard to parse and partially redundant with the schema.

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?

With no output schema, the description must cover returns, and it does state that content is returned inline when 'output' is omitted. Still, for a tool touching many file types and network routes with no annotations, the disclosure of behavior and failure conditions is thinner than ideal.

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 description coverage is 100%, so the baseline is 3. The route list loosely maps to parameters (OCR/PNG-JPG to lang, reels to reel_options, output formats), but it adds no syntax or format detail beyond what the schema already documents.

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?

Clear specific verb+resource: ingest a URL/file path/directory and convert it into Markdown, with the supported input families enumerated. It does not explicitly distinguish itself from siblings like inspect_source or list_supported_formats, though its conversion scope is evident from the route list.

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?

It frames the use case ('for local AI context workflows') and notes that advanced routes are 'public/local-only ... when their source access requirements are met', implying prerequisites. However, there is no explicit when-to-use-this vs an alternative, and no guidance on choosing between this and sibling tools.

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