1C metadata search MCP
mcp1c_metadata
A Docker service that indexes a JSON export of 1C configuration metadata and gives an agent fast object search by name and synonym
Low risk
We rate an entry low when it mostly gives the agent instructions and reference material.
Why this level
- The service only searches a pre-exported JSON, there is no live base access or write capability
- The Docker container publishes a port externally, so network access should be restricted
Install
Manual install
docker run --rm -it -p 8007:8000 -v "C:\ERP\Report":/app/metadata_src -e MCP_PORT=8000 -e MCP_PATH=/mcp smirnov0ser/mcp1c_metadata:latestQuick start from the ready Docker Hub image, from the README.
Security check
How we reviewLow riskWe rate an entry low when it mostly gives the agent instructions and reference material.
- The service only searches a pre-exported JSON, there is no live base access or write capability
- The Docker container publishes a port externally, so network access should be restricted
This is third-party code. Review the repository files before installing.
What it does
The service reads JSON metadata files produced by the ВыгрузитьМетаданныевJson.epf processor and builds a short index for fast lookups. The single metadatasearch tool finds an object by its full name, such as Справочники.Номенклатура, with a result limit, and can work with several configurations at once by selecting one via the config parameter. Types are automatically normalized to singular form, and the Ссылка suffix is trimmed. The service runs in Docker with ports and volumes for source metadata, the index and logs, or locally through pip and venv on Python 3.12.
Who it is for. For 1C developers who need fast metadata object search by name for AI agents in the browser or an IDE.
Good fit when
- You need to quickly find a metadata object's full name by title or synonym
- You work with several 1C configurations at once and need a shared search service
- You want a lightweight Docker service without installing extensions into the 1C base itself
Not a fit when
- You need live access to base data rather than a static JSON metadata export
- You cannot regularly refresh the export through the ВыгрузитьМетаданныевJson.epf processor
Example request
Find the full metadata object name for the user settings registerMCP
- Transport
- http
- Authentication
- not required
Environment variables
INPUT_METADATA_DIR- Path to the source metadata JSON files, defaults to /app/metadata_src.
MCP_PORT- The MCP server's port inside the container, defaults to 8000.
Limitations
No pushes for over a year, and no license is specified. The service works with a pre-exported JSON, not a live base, so freshness depends on how often the export is refreshed. The tool's find_usages parameter is reserved but not yet used.
How to disable. Stop and remove the mcp1c_metadata container, and remove the server from your MCP client config.
FAQ
How do I get the JSON export for the service?
Through the ВыгрузитьМетаданныевJson.epf processor bundled with the repository.
Can several configurations be indexed at once?
Yes, the service builds an index over several JSON files and lets you pick one with the config parameter.
Related
MCP serversA skills library that gives coding agents a development process: brainstorming, planning, TDD, subagents and code review
Skills for real engineers by Matt Pocock
Skills For Real Engineers
Small composable skills for engineering with agents: plan grilling, TDD, bug diagnosis, code review and architecture
GitHub toolkit for spec-driven development: the specify CLI adds agent commands and skills to a project, from principles to implementation
Reference MCP servers
Model Context Protocol servers
Official reference MCP servers: Filesystem, Fetch, Git, Memory, Sequential Thinking, Time and Everything
README in short
The README describes the service's purpose, where it is used (the MCP SuperAssistant browser extension, Cursor, Void), a Docker quick start with an example command and environment variables, a non-Docker local run, the metadata directory layout, the single metadatasearch tool with its parameters, and a recommended prompt instruction for the agent.