PluginBench
MCP Server

ContextOS — Powered Exoskeleton for AI Coding MCP Server

io.github.yubinbin32-ops/contextos

RepositoryRegistry
How to choose

What this kind of tool is for

  • Automate a build, test, or deployment step you repeat by hand.
  • Review or refactor code in an existing repository without leaving your agent.
  • Bridge an internal service or CLI into the agent toolset.

How to compare servers like this

Scope of control:
Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
Environment fit:
Match the runtime it expects (Node, Python, a container) to what you actually run.
Maintenance signal:
Check the last-commit date — dev tooling that lags upstream breaks first.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the ContextOS — Powered Exoskeleton for AI Coding MCP server?

Powered exoskeleton for AI coding: auto-governs context via MCP to cut 90%+ context waste.

How to install ContextOS — Powered Exoskeleton for AI Coding

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • CONTEXTOS_PROJECT_ROOT

    Absolute path of the mounted project directory containing .contextos.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "contextos": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/yubinbin32-ops/contextos:2.7.1"
      ],
      "env": {
        "CONTEXTOS_PROJECT_ROOT": "<YOUR_CONTEXTOS_PROJECT_ROOT>"
      }
    }
  }
}

Related MCP servers

Context OS for AI coding agents: task-scoped AST slices, verified mutations, and rollback with compact receipts.

11
JavaScript
MIT
View repository →
RERepo Memory logo

Repo Memory

Maintained

Shared, git-tracked working memory for AI agents on the same codebase.

1
Python
MIT
View repository →

Auditable memory for coding agents: evidence chains, supersession history, keyless embedded SQLite

0
TypeScript
MIT
View repository →

MCP server for Drone CI/CD: 45 tools for builds, repos, secrets, users and templates

1
Go
View repository →
AIAI-First Scraper logo

Three MCP tools: fetch_page, fetch_pages_batch, search_web. Ad-free Markdown for AI agents.

2
Python
MIT
View repository →

Double-entry bookkeeping MCP server — import bank CSVs, categorize, reconcile, tax reports.

0
TypeScript
MIT
View repository →