SkillFoxx

1C AI development environment MCP

1C AI Development Environment

1C development environment with an MCP server offering 10 tools: 11 BSL analyzers, JSON DSL to XML, dependency graph, and EPF build without 1C

  • 18 ★ on the repository
  • Last commit
  • MIT
MCP server

Broad access

Why this level

  • build_epf and code generators create and modify configuration and extension files on disk
  • cfe_patch_method generates interceptor methods in extensions, changing configuration logic
All reasons and checks
Russian stack

pradushkoai/1c-ai-dev-envAuthor:Pradushkoai

Install

Manual install

git clone https://github.com/Pradushkoai/1c-ai-dev-env.git && cd 1c-ai-dev-env && pip install -e ".[dev,mcp]"

Optionally run bash install.sh to install BSL Language Server.

Access and checks

How we review

Broad accessThe tool can change data, run commands or handle secrets.

  • build_epf and code generators create and modify configuration and extension files on disk
  • cfe_patch_method generates interceptor methods in extensions, changing configuration logic

This is third-party code. Review the repository files before installing.

What it does

The project parses 1C configuration XML exports and builds five indexes: metadata (35 object types), a directory of platform BSL methods, SKD schemas, form structure, and a dependency graph using networkx. On top of these indexes operate 11 BSL analyzers with over 150 rules (security, code standards, transactions, queries, complexity metrics, architecture), five JSON DSL to XML compilers for metadata, forms, SKD, layouts, and roles, plus extension operations (object borrowing, interceptor method generation, extension diff). Separately, EpfFactory assembles external .epf processing from scratch without running 1C, using templates and v8unpack. All features are accessible via CLI (19 commands) and through a dedicated MCP server with 10 tools for Cursor, Claude Desktop, VS Code, and JetBrains. The project is in Beta with explicit stability markings for each subsystem and 1595 passing tests.

Who it is for. For 1C developers who want a full analytical and code-generating environment around an agent, not just a reference or search tool.

Good fit when

  • You need security and BSL code standards audit across dozens of rules at once
  • You need to generate metadata, forms, SKD, or roles from JSON descriptions without manual XML editing
  • You need a metadata dependency graph to find dead code or cycles

Not a fit when

  • You need only stable minimal functionality: some subsystems (EDT parser, RAG with Ollama, SaaS/Enterprise) are marked experimental or frozen
  • You lack Python 3.10+ and, for the full analyzer set, Java 17+ for BSL Language Server
  • You need to work with a live 1C database rather than XML configuration exports

Example request

Check the module ОбщегоНазначения.bsl with all seven analyzers and show only new errors compared to the baseline

MCP

Transport
stdio
Authentication
not required

Limitations

The project declares Beta status, not production-ready, with a clear stability matrix by subsystem: EpfFactory, SARIF reporter, OpenSpec, and Session manager are Beta; EDT parser and RAG with Ollama are Experimental; SaaS/Enterprise/Plugin are frozen and moved to experimental/. EPF build uses a workaround via v8unpack instead of the official API. The full set of over 150 analysis rules requires BSL Language Server installed on Java.

How to disable. Remove the 1c-ai server from the client's mcp.json and stop it with docker compose down if Docker was used.

FAQ

Can I use it without BSL Language Server?

Yes, install.sh for it is optional, but without it analysis via analyze_bsl with 187 diagnostics is unavailable.

How to know which subsystems are safe for production use?

Refer to the Stability Matrix table in the README: Stable subsystems have passed tests, Beta and Experimental require caution.

Discussion

No questions or reviews yet.

All 1C:Enterprise tools
Russian stack

A local read-only MCP server suite for 1C: a Rust code indexer, metadata skills, a prompt gallery and platform help search, with evidence-backed answers

MCP serverExtended access
Russian stack

A set of skills, rules and MCP servers for 1C Enterprise 8.3 development where the agent works from real code and docs, not from memory

SkillBroad access35
Russian stack

Ten MCP servers for 1C development: platform reference, targeted object dump and load, COM, storage, file search and BSL Language Server

MCP serverBroad access1

1C configuration graph MCP server

1C Configuration MCP Server

Russian stack

An MCP server builds a metadata and call graph from a 1C configuration's XML and BSL export, with optional semantic search via an external embedder and Qdrant

MCP serverExtended access4
Russian stack

An MCP server that exposes the cloud 1C:Napparnik (1C.ai) assistant and a local BSL Language Server to agents in Cursor and other IDEs

MCP serverExtended access22
Russian stack

An MCP server for Claude Code: full-text search over multiple 1C XML+BSL configuration exports in a local SQLite FTS5 database

MCP serverExtended access

README in short

The README lists 11 BSL analyzers with rule counts, metadata parsing components, five DSL compilers, CFE extension operations, infrastructure tools (SARIF, OpenSpec, Session manager, EpfFactory), a clear stability matrix per subsystem, installation via pip or Docker, a full list of 19 CLI commands by category, MCP setup for Cursor, Claude Desktop, VS Code, and JetBrains with a table of 13 tool categories, and the project directory architecture. It separately advises reading AGENTS.md before working with the AI agent.

README badge

Report a problem