Context OS for AI coding agents: task-scoped AST context, verified mutation, and rollback.
Mdflow — Context OS for AI Coding Agents is an MCP integration. Context OS for AI coding agents: task-scoped AST context, verified mutation, and rollback.
The published oci package is ghcr.io/yubinbin32-ops/mdflow:0.3.7. Its declared MCP transport is stdio.
The package declares MDFLOW_PROJECT_ROOT: Absolute path of the mounted project directory containing .mdflow..
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project repository. This profile uses version 0.3.7 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related developer tools MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| MDFLOW_PROJECT_ROOT | Absolute path of the mounted project directory containing .mdflow. | Optional |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Local-first memory for coding agents; stores decisions, bugs, and context across sessions.
PDF native MCP server: generate, validate, sign PAdES, embed, extract. AI-powered.
Local-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP.
MCP access to cluster-wide L4 and L7 network traffic, packets, APIs, and complete payloads.