get_model_graph
AI agents call get_model_graph to retrieve information from Orionbelt Semantic Layer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix and model name indicate this tool retrieves or queries a graph structure related to semantic models. No side effects, modifications, or execution indicators are present. Although the description is uninformative, the pattern matches Read operations (retrieve/fetch) rather than Write, Execute, Destructive, or Financial actions. Confidence is moderately reduced due to the empty description.
From the tool's definition Tool named 'get_model_graph' with a prefix pattern consistent with other Read tools on this server (get_example, get_json_schema, get_model). The description is empty, limiting certainty, but the naming convention and sibling context suggest data retrieval.
Attacks that exploit this kind of access
get_model_graph. It is categorised as a Read tool in the Orionbelt Semantic Layer MCP Server, which means it retrieves data without modifying state.
Register the Orionbelt Semantic Layer MCP server in PolicyLayer and add a rule for get_model_graph: 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 Orionbelt Semantic Layer. Nothing to install.
get_model_graph 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 get_model_graph 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 get_model_graph. 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.
get_model_graph is provided by the Orionbelt Semantic Layer MCP server (ralfbecher/orionbelt-semantic-layer-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →