SkillFoxx

1C:Enterprise MCP server over OData

1C:Enterprise MCP Server for AI Assistants

A dependency-free Python MCP server: in-memory 1C metadata search, reading and writing data via the OData REST API, and parsing data composition schema queries

  • 0 ★ on the repository
  • Last commit
MCP server

Broad access

Why this level

  • The odata_create and odata_update tools write new records and change existing ones in the live 1C database
  • Database admin credentials are passed via the MCP server's environment variables
All reasons and checks
Russian stack

flakeman/fervent-hawkingAuthor:flakeman

A similar tool with a larger community: 1C OData MCP with a JSON cache, 4 ★ on the repository

Install

Manual install

git clone https://github.com/flakeman/fervent-hawking.git

Clone the repo, then register the server in the MCP client's configuration.

Access and checks

How we review

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

  • The odata_create and odata_update tools write new records and change existing ones in the live 1C database
  • Database admin credentials are passed via the MCP server's environment variables

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

What it does

The server combines two ways to access a 1C configuration: an in-memory compact metadata index for instant keyword search over catalogs, documents and registers, and static search over an unpacked configuration XML export. Separately, it gives tools for live data via OData: reading with a filter and sort, creating a record, and updating one by GUID. The extract_xml_query tool pulls the 1C query text straight out of a data composition schema template XML file. A SKILL.md file teaches the model to write queries following database optimization rules, for example filtering inside virtual table parameters instead of a WHERE clause. The server is written using only the Python standard library, with no external dependencies.

Who it is for. For 1C developers who use Codex, Gemini CLI, Cursor or Windsurf and want to give an agent access to configuration metadata and live database data via OData.

Good fit when

  • You need fast keyword search over configuration objects without hitting the database
  • You need to read, create or update 1C records via OData directly from the assistant chat
  • You need to pull a data composition schema query text out of an XML template without opening the Configurator

Not a fit when

  • OData is not published on the database's web server: the odata_* tools will not work without it
  • You are not ready to give the agent the ability to create and modify records via odata_create and odata_update

Example request

Find all catalogs and registers with the word Запасы and show the first 10 СписаниеЗапасов documents via OData

MCP

Transport
stdio
Authentication
API key

Environment variables

1C_ODATA_URL required
The address of the published OData service for the 1C database.
1C_ODATA_USER required
The user for OData authorization.
1C_ODATA_PASSWORD required, secret
The OData user's password.
1C_INDEX_FILE required
Path to the compiled compact metadata index.

Limitations

The compact metadata index has to be built ahead of time with build_1c_index.py and refreshed manually after configuration changes. OData must be separately enabled and published on the database's web server, with steps in a dedicated guide. The example config stores the database admin login and password in plain text in the MCP server's environment variables.

How to disable. Remove the 1c-helper entry from your client's mcp_config.json.

FAQ

Do I need to install Python packages?

No, the server uses only the standard library (urllib, json), so no pip packages are required.

Can the assistant change data in the database?

Yes, the odata_create and odata_update tools create and change 1C records directly, so this access should be granted deliberately.

Discussion

No questions or reviews yet.

All 1C:Enterprise tools

1C OData MCP with a JSON cache

MCP сервер для работы с OData 1C

Russian stack

A Python MCP server over 1C OData: reads and changes catalogs and documents, saving everything to JSON files for local analysis without repeat queries

MCP serverBroad access4

1C OData MCP server

1C OData MCP Server

Russian stack

A small Python MCP server that wraps standard 1C Управление предприятием OData read operations into three tools

MCP serverBroad access
Russian stack

A Python proxy between an MCP client and a 1C HTTP service: reads metadata, object structure and predefined data, with optional OAuth2

MCP serverExtended access9
Russian stack

MCP server for 1C:Enterprise databases over standard OData: catalogs, documents, registers and accounting with no configuration extension

MCP serverBroad access13
Russian stack

An npx MCP server that gives Claude read access to a 1C database via standard OData, no Excel exports or hand-built URLs

MCP serverExtended access

README in short

The README describes the integration for Codex and other MCP clients: hybrid metadata search, data access via OData, data composition schema query parsing, and a SKILL.md rules file for query optimization. It gives the repo layout, three install steps (cloning, registering the server in the client config, enabling OData in 1C), a table of six tools with parameters, and example natural-language requests to the assistant. It separately mentions a document with efficiency metrics.

README badge

Report a problem