describe_object
Показывает поля (реквизиты) объекта 1С и их типы, включая табличные части, чтобы правильно строить select, filter и expand.
This record as markdown: /tools/1c-claude-connector/describe-object.md
What describe_object does on 1c Claude Connector
AI agents call describe_object to retrieve information from 1c Claude Connector without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why describe_object is rated Low
Retrieves metadata about 1С object structure without modifying or executing operations.
From the tool's definition Shows fields and types for query building; read-only OData connector
Attacks that exploit this kind of access
The rule that runs describe_object safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 1c Claude Connector, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For describe_object, this is the rule to start with:
describe_object is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect 1c Claude Connector, apply this rule, and every describe_object call is checked against it from then on.
Questions about describe_object
Показывает поля (реквизиты) объекта 1С и их типы, включая табличные части, чтобы правильно строить select, filter и expand. It is categorised as a Read tool in the 1c Claude Connector MCP Server, which means it retrieves data without modifying state.
Register the 1c Claude Connector MCP server in PolicyLayer and add a rule for describe_object: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches 1c Claude Connector. Nothing to install.
describe_object is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the describe_object rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for describe_object. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
describe_object is provided by the 1c Claude Connector MCP server (glxaoc/1c-claude-connector). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 1c Claude Connector, and thousands of servers like it.
This server
Across the catalogue