A lightweight local framework for building language-model agents with tool use, streaming responses, skills, and file tools. It runs as a Python package.

Use it to build or run local AI-agent workflows that need tool calls, streamed results, reusable skills, or file access.

It provides a basic structure for creating agents that can call tools, send incremental output, use reusable instructions, and work with files.

omd — MCP server by omd-local

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add mcp/omd-local/markdown-everything/omd

Clone the repo

git clone --depth 1 https://github.com/omd-local/markdown-everything

Made for: Claude Code, Codex, Cursor.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

omd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

listed in the official MCP registry · 8 lines

What it actually says

{ "omd": { "command": "uvx", "args": [ "omd" ] } }

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 8 lines scan A 3b724b966afd

Subscribe to this mod's changes

omd is an MCP server published in the GitHub repository omd-local/markdown-everything (1 stars, last pushed 16d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI Languages knowledge-management local-first markdown mcp obsidian ocr

omd

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other mcp servers, from other repositories

big-brain

knowledge-inbox

vulcanus

chamber

enzyme

consilience