Headless Code Editor MCP Server

Created By
oakenaia year ago
Headless Editor MCP Server for intelligent code editing
Overview

what is Headless Code Editor MCP Server?

Headless Code Editor MCP Server is a robust, language-agnostic code editor that utilizes the Language Server Protocol (LSP) and Model Context Protocol (MCP) for enhanced code intelligence and AI-assisted code manipulation.

how to use Headless Code Editor MCP Server?

To use the server, install dependencies, build the project, and start the server with the desired workspace directory. Additionally, you can create a new editing session, apply code edits, and validate the current code state through MCP tools available via its API.

key features of Headless Code Editor MCP Server?

  • Language Server Protocol support for coding languages
  • Secure file system operations with strict access controls
  • State management for session-based editing
  • In-depth analysis for TypeScript/JavaScript code
  • React component detection and manipulation
  • Comprehensive logging and error tracking

use cases of Headless Code Editor MCP Server?

  1. AI-assisted code editing for TypeScript/JavaScript projects.
  2. Automating React component manipulation.
  3. Enhancing security during code transactions with strict file access controls.

FAQ from Headless Code Editor MCP Server?

  • What languages does the editor support currently?

The server currently supports TypeScript and JavaScript with future expansions planned for Python and Java.

  • Can I use it for team development?

Yes! The server is designed for session-based editing, which can facilitate collaboration.

  • Is there any documentation available for new users?

Yes, the project includes detailed documentation covering architecture, design principles, and integration instructions.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
oakenai
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago