What languages are supported?
Currently TypeScript and JavaScript are supported. Incomplete tasks indicate plans for Python, Java, and other languages.
@oakenai
Basic information
Headless Editor MCP Server for intelligent code editing
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"headless-editor-mcp": {
"command": "node",
"args": [
"build/index.js",
"/path/to/workspace"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A robust, language-agnostic headless code editor that integrates the Language Server Protocol (LSP) for code intelligence and the Model Context Protocol (MCP) for AI-assisted code manipulation. It targets developers needing secure, session-based code editing with AI integration.
Install dependencies with npm install, build with npm run build, and start the server by passing allowed directories, e.g., node build/index.js /path/to/workspace. Use MCP tools such as start_session, edit_code, validate_code, and close_session to manage editing sessions.
Currently TypeScript and JavaScript are supported. Incomplete tasks indicate plans for Python, Java, and other languages.
The server requires Node.js and npm. It runs as a stdio-based MCP server.
All file system operations are strictly confined to allowed directories specified at startup. Sessions and state are managed in memory.
The server uses the stdio transport for MCP communication, as shown in the example integration.
The server is in alpha stage (v0.0.10) with basic support only for TypeScript/JavaScript and React component analysis. Many features are listed as incomplete.
Agent conductor — AGENTS.md contract parser, SKILL.md registry, CHP decision engine over MCP

AdsMCP is the MCP entry point into the Adgentek Ad Server. Call ads_serve with the conversation context and get back a native ad matched to user intent, or no ad when one does not fit. Publishers earn on a CPM basis. Fre
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Agent-Native Terminal

Give an agent a place to put large output. Instead of returning 40k characters of a build log into the conversation, it posts the file to DocBin and hands back one short URL. Docs render with syntax highlighting and mark
Comments