onec-odata-mcp
Bridges AI agents to 1C:Enterprise via OData, enabling natural language queries of business entities like counterparties and invoices with read-only access.
README
onec-odata-mcp
MCP server bridging AI agents to 1C:Enterprise (1С:Предприятие) via OData.
Give an AI assistant (Claude Desktop, Cursor, any MCP client) read-only access to a 1C database. Instead of exporting spreadsheets or hand-writing OData URLs, the agent queries 1C entities — counterparties, documents, invoices, catalogs — in natural language and gets structured data back. Works with any 1C configuration that exposes the standard OData endpoint (Accounting, ERP, Trade Management, and custom configs).
Quick start
npm install
npm run build
Configure via environment variables (recommended for MCP clients):
ONEC_BASE_URL=https://1c.example.com/your_db/odata/standard.odata
ONEC_USERNAME=odata_user
ONEC_PASSWORD=odata_password
# optional:
ONEC_DATABASE=your_db
ONEC_METADATA_CACHE_TTL_MS=3600000
Register the server in your MCP client (e.g. Claude Desktop claude_desktop_config.json):
{
"mcpServers": {
"onec-odata": {
"command": "npx",
"args": ["-y", "onec-odata-mcp"],
"env": {
"ONEC_BASE_URL": "https://1c.example.com/your_db/odata/standard.odata",
"ONEC_USERNAME": "odata_user",
"ONEC_PASSWORD": "your_password"
}
}
}
}
Alternatively, place a JSON file at ~/.onec-odata/onec-config.json with { "baseUrl", "username", "password" } and point ONEC_CONFIG_PATH at it.
Tools
| Tool | Description |
|---|---|
odata_config |
Check configuration status and setup instructions |
odata_list_entities |
List all available OData entities |
odata_metadata |
Get entity types and sets from $metadata (cached, 1h TTL) |
odata_explain_entity |
Describe an entity's fields, types, keys, navigation properties |
odata_build_query |
Build a validated $filter/$select/$orderby from structured intent |
odata_query |
Query an entity with raw OData params (filter/select/top/expand) |
odata_count |
Count records in an entity, optionally filtered |
odata_financial_summary |
Auto-detect common financial entities and report their counts |
Example
Ask the agent: "How many sales orders were posted this month?"
It calls odata_build_query → odata_count on the sales-order entity with a date filter. No OData syntax knowledge required — the server validates fields against live $metadata and rejects unknown/secret fields.
Requirements
- Node.js ≥ 18
- 1C:Enterprise with the OData endpoint published (web publishing →
standard.odata)
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.