DitriXNew/EDT-MCP

MCP for 1C:EDT

What it solves

This project provides a bridge between 1C:EDT (the development environment for 1C:Enterprise business applications) and modern AI assistants. It allows AI tools like Claude, GitHub Copilot, and Cursor to directly interact with an EDT workspace, enabling them to read code, inspect metadata, run tests, and perform refactoring tasks as if they were a human developer.

How it works

It implements the Model Context Protocol (MCP), a standard that allows AI models to connect to local data sources and tools. The plugin runs as a server within the EDT environment, exposing a wide array of tools—such as module reading, form inspection, and project management—over an HTTP/SSE connection. AI assistants can then call these tools to perform actions like searching code, running database updates, or analyzing errors, with the ability to interrupt long-running operations via a status bar interface.

Who it’s for

This is designed for 1C:Enterprise developers who use 1C:EDT and want to integrate AI-powered coding assistants into their daily workflow to automate repetitive tasks, perform code reviews, or debug complex business applications.

Highlights

  • Comprehensive Tooling: Exposes over 100 tools categorized into groups like BSL Code, Debugging, Refactoring, and Application Management.
  • Visual Inspection: Supports form inspection by providing PNG screenshots and layout snapshots of the WYSIWYG editor.
  • Interactive Control: Includes a status bar for real-time monitoring and the ability to send signals (e.g., cancel, retry, ask expert) to the AI agent during long operations.
  • Flexible Configuration: Offers granular control over which tools are exposed, including preset modes like "Code Review" or "Development" and progressive disclosure to keep the AI's tool list manageable.
  • Compatibility: Supports 1C:EDT 2026.1 and 2026.2, with easy installation via the Eclipse p2 director or the EDT update site.

Related

  • Project
    vinilana/jev-gateway

    A local LLM gateway for coding agents that uses the fast Jev decision model to optimize tool selection, reducing cost and latency for the primary reasoning model.

  • Project
    gendigitalinc/sage

    Sage is a security plug‑in for AI coding assistants (Claude Code, Cursor, VS Code, OpenClaw, OpenCode). It intercepts tool calls—shell commands, URL fetches, file writes, package installs—and runs multiple threat checks (cloud URL reputation, 300+ local YAML heuristics, a prompt‑injection ML model, supply‑chain analysis, and Windows AMSI). If a request looks unsafe, Sage blocks it and logs the decision. Installation is done via the respective assistant’s marketplace or npm, and the project is open‑source under Apache 2.0.

  • Project
    MangoFisher/TestBrain

    TestBrain is an AI-powered testing platform that automates test case generation, review, and code analysis by leveraging LLMs and a vector-based knowledge base to assist testing teams.

  • Project
    block/trailblaze

    Trailblaze is a CLI tool that allows AI coding agents to control iOS, Android, and web applications, turning agent-led sessions into deterministic, replayable automated tests.