Ext Ops Panel
Open dashboard
Comparison

CodeCortex Context Engine vs mdflow — Context OS for AI Coding Agents

CodeCortex Context Engine is an MCP server published by BehnamJalaliCo. Marketplaces we read that list it: 1 (Official MCP Registry). mdflow — Context OS for AI Coding Agents is an MCP server published by yubinbin32-ops. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-19. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
MarketplaceCodeCortex Context Enginemdflow — Context OS for AI Coding Agents
Official MCP Registry Listed
Version: 0.1.0a10
Downloads/month (PyPI): 470
Downloads/week (PyPI): 58
Forks (GitHub): 2
Stars (GitHub): 8
Not marked · First seen
Listed
Version: 0.3.7
Forks (GitHub): 0
Stars (GitHub): 14
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

CodeCortex Context Engine vs mdflow — Context OS for AI Coding Agents
FactCodeCortex Context Enginemdflow — Context OS for AI Coding Agents
Marketplaces that list it11
Stars (GitHub) (differs)8 (worse)14 (better)
Forks (GitHub) (differs)2 (better)0 (worse)
Last releaseNot publishedNot published
Where it runs (differs)On your machine (codecortex-context-engine)On your machine (ghcr.io/yubinbin32-ops/mdflow:0.3.7)
Transportstdiostdio
Tools it declaresNot publishedNot published
Environment variables it asks for (differs)Not published1, secrets among them: 0
LicenceNot statedNot stated
Repository (differs)github.com/behnamjalalico/codecortexgithub.com/yubinbin32-ops/mdflow-canvas
Changes in the last 7 days00
First seen2026-10-112026-10-11

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

CodeCortex Context Engine

In its own words, on Official MCP Registry:

Context intelligence for AI coding agents: navigation, impact, memory, guarded edits.

mdflow — Context OS for AI Coding Agents

In its own words, on Official MCP Registry:

Context OS for AI coding agents: task-scoped AST context, verified mutation, and rollback.

How to run each

CodeCortex Context Engine As a local MCP server: PyPI package

Claude Code
claude mcp add --transport stdio codecortex-context-engine -- uvx codecortex-context-engine mcp --path .

mdflow — Context OS for AI Coding Agents As a local MCP server: Docker image

Claude Code
claude mcp add --transport stdio mdflow -- docker run -i --rm ghcr.io/yubinbin32-ops/mdflow:0.3.7

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

The marketplaces of CodeCortex Context Engine publish no settings it asks for, so we do not compare settings.

What it can do: CodeCortex Context Engine · What it can do: mdflow — Context OS for AI Coding Agents · Compare two other plugins

Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built