AI agents call find_references_to_object to retrieve information from 1C MCP Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'find_references' naming pattern indicates a retrieval/search function that scans for relationships or dependencies in a 1C:Enterprise database. This is a non-mutating Read operation.
From the tool's definition Tool name is 'find_references_to_object' with empty description. The name strongly suggests a search/query operation that retrieves references without modifying data.
Documented attack patterns abuse exactly the kind of access find_references_to_object gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and 1C MCP Toolkit, and nothing reaches the server without passing your rules. This is the rule we recommend for find_references_to_object:
{
"version": "1",
"default": "deny",
"tools": {
"find_references_to_object": {}
}
}find_references_to_object is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
find_references_to_object. It is categorised as a Read tool in the 1C MCP Toolkit MCP Server, which means it retrieves data without modifying state.
Register the 1C MCP Toolkit MCP server in PolicyLayer and add a rule for find_references_to_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 MCP Toolkit. Nothing to install.
find_references_to_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 find_references_to_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 find_references_to_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.
find_references_to_object is provided by the 1C MCP Toolkit MCP server (roctup/1c-mcp-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 1C MCP Toolkit tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
13 1C MCP Toolkit tools catalogued and risk-classified — across an index of 42,500+ MCP servers.