omd-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OMD_MCP_ALLOWED_ROOTS | No | MCP restricts local paths and private-network URLs by default; use narrow OMD_MCP_ALLOWED_ROOTS only for folders you intend the client to access. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| convert_to_markdownB | 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. |
| inspect_sourceA | Inspect how OMD would route a URL, share blob, file path, or directory without converting it. Optionally includes local readiness from doctor checks. |
| capture_to_vaultB | Capture one source into an Obsidian-compatible local vault as Markdown plus an .omd.json manifest. Uses conservative agent defaults: path allowlist checks, no cookie/browser auth flags, no generated memory cards, and untrusted source labeling. |
| search_memoryA | Search Markdown notes under an allowed local vault root. Returns relative paths, deterministic lexical scores, and bounded untrusted evidence snippets. |
| list_supported_formatsB | List the input forms |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Most tools have clearly distinct purposes: convert, inspect, capture, search, and list formats. However, convert_to_markdown and capture_to_vault both convert a source to Markdown, which could cause slight confusion on when to use which, though descriptions differentiate by output destination and defaults.
All tools follow a consistent snake_case verb_noun pattern (convert_to_markdown, inspect_source, capture_to_vault, search_memory, list_supported_formats). No deviations in case or style.
Five tools cover the core operations: conversion, inspection, vault capture, search, and format listing. This is well-scoped for a markdown ingestion and vault tool without redundancy.
The surface covers ingestion, inspection, vault capture, and search, but lacks a way to retrieve full note content (search returns only bounded snippets) and no note update/delete operations. These are minor gaps for its stated purpose.