1C Development Standards MCP
MCP-сервер стандартов разработки 1С:Предприятие 8
An MCP server exposing 1C:Enterprise 8 development standards for agent-driven search and code review
- 3 ★ on the repository
- Last commit
Extended access
Why this level
- Runs a Docker container with an HTTP /mcp endpoint
- Searches ITS standards and checks submitted BSL code without connecting to a 1C database
Install
- Works in
- Services
Manual install
docker pull ghcr.io/1cworkers/mcp-1c-standards:latestRecommended. Local build alternative: git clone then docker build -t mcp-1c-standards .
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs a Docker container with an HTTP /mcp endpoint
- Searches ITS standards and checks submitted BSL code without connecting to a 1C database
This is third-party code. Review the repository files before installing.
What it does
The server gives the agent 1C:Enterprise 8 development standards and methodology sourced from its.1c.ru, bundled into a ready dataset. The agent can look up a standard by task description, such as queries inside a loop, or submit a BSL code snippet for a standards compliance check. The server runs in Docker and exposes an HTTP /mcp endpoint; /health reports the number of loaded standards and categories. You can add your own company standards through the custom-standards file.
Who it is for. For 1C developers and code reviewers who want an agent to check BSL code against 1C standards automatically.
Good fit when
- You need to find an official 1C standard by task description rather than exact document title
- You want an automatic BSL code snippet check against standards before code review
- You have your own company standards to add alongside the official ones
Not a fit when
- You cannot run a Docker container locally or on a server
- You want a full replacement for human code review, not a standards hint
- You need standards for platforms other than 1C:Enterprise 8
Example request
Check this code against 1C standards for queries inside a loop and suggest a fixMCP
- Transport
- http, stdio
- Authentication
- not required
Environment variables
MCP_TRANSPORTrequired- Server transport; http for a long-running container
Limitations
The server ships only as a Docker image or a Dockerfile build, with no separate npm or pip package. The standards set is fixed in data/standards.json at build time and can lag behind the current its.1c.ru version. No license file is present, and the project is small and maintained by a single author.
How to disable. Stop the container with docker stop mcp-1c-standard-review and remove the server from your MCP client config, for example claude mcp remove 1c-standards.
FAQ
Can I run it without Docker?
The README only covers a Docker pull or a local image build, no other install path is documented.
Can I add my own standards?
Yes, custom-standards/example.json in the repository is a template for your own company rules.
Discussion
No questions or reviews yet.
Related
All 1C:Enterprise toolsPublic MCP server ai.v8std.ru searches 1C development standards and explains diagnostics with a link to the v8std.ru rule.
1C AI MCP: 1C:Naparnik API bridge
1C AI MCP
A FastMCP Docker server with 12 tools for BSL code analysis and documentation search through the 1С:Naparnik API (code.1c.ai)
Five independent Docker-based MCP servers: a Neo4j metadata and call graph, static BSL analysis, platform syntax help, a query builder and 1C coding standards
Ten MCP servers for 1C development: platform reference, targeted object dump and load, COM, storage, file search and BSL Language Server
A Docker server with a read-only core and pluggable modules: metadata, code, forms and relations of several 1C configurations through one MCP contract
A single-binary Go MCP server: the agent sees 1C metadata, searches code, runs read-only queries and writes accurate BSL
README in short
The Russian README walks through installing via docker pull or a local build, and connecting Cursor, Claude Code and Codex with commands for each. It shows a curl /health check and a stdio connection example where Docker starts on demand. It gives ready chat phrases for testing: looking up a standard and reviewing a BSL code sample with a query-in-a-loop example.