mcpbeat Sign in

ContextOS — Powered Exoskeleton for AI Coding MCP Server

local only

ContextOS — Powered Exoskeleton for AI Coding runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 21 Sep 2026.

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

Installs / week
not published
11
Stars
0 open issues
21 Sep 2026
Last commit
from GitHub
MIT
License
JavaScript

What the code does

We read the source, 7 h ago · rules 3dff92dd89df

A tool parameter reaches a dangerous call

A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.

A tool parameter reaches a file or shell call contextos_doctor.projectRoot → packages/mcp/src/v2-server.mjs:415, contextos_doctor.projectRoot → packages/mcp/src/v2-server.mjs:617, contextos.projectRoot → packages/mcp/src/v2-server.mjs:58 и ещё 4
          projectConfig = JSON.parse(fs.readFileSync(projJsonPath, 'utf8'));
Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

      try { execFileSync(codexBin, ['plugin', 'remove', 'contextos@personal', '--json'], { stdio: 'ignore' }); } catch (_) {}
Builds a file path from a variable packages/orchestrator/src/observer.mjs:29
    const stat = fs.statSync(path.join(projectRoot, filePath));

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

A tool parameter here reaches a dangerous call

That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.

Three servers free · no card

Alternatives to ContextOS — Powered Exoskeleton for AI Coding

same job, measured the same way
Cgraphy
by pmgarg

Code knowledge graph over MCP: token-budgeted context for AI coding agents.

63 installs/wk local only
Cerebras Code MCP
by kevint-cerebras

Model Context Protocol (MCP) server for Cerebras to make coding faster in AI-first IDEs

56 installs/wk local only
Ainative Browser MCP
by ainative-studio

AI-powered browser automation MCP — 6 tools for web interaction, extraction, and validation.

120 installs/wk local only
Google Sheets MCP
by henilcalagiya

Powerful tools for automating Google Sheets using Model Context Protocol (MCP)

115 installs/wk local only
Autoplans MCP
by mohamedgb00714

AI-powered project planning tools for Autoplans.dev with 14+ MCP tools

34 installs/wk local only
Revit MCP
by shuotao

MCP Server for Revit integration - AI-Powered Revit Control

51 installs/wk local only
Coverctl
by felixgeelhaar

Go code coverage analysis tool with MCP server for AI-powered coverage workflows

local only
Coverctl
by klarlabs-studio

Go code coverage analysis tool with MCP server for AI-powered coverage workflows

local only

ContextOS — Powered Exoskeleton for AI Coding — questions

Answers built from our own checks of this server.

Why is there no uptime for ContextOS — Powered Exoskeleton for AI Coding?
ContextOS — Powered Exoskeleton for AI Coding runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone.
Is ContextOS — Powered Exoskeleton for AI Coding open source?
Yes — it is published under the MIT licence, written in JavaScript and 11 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.