get_join_graph
AI agents call get_join_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.
Based on the 'get_' prefix and the context of a semantic layer server that explores governed models and schema, this tool most likely retrieves join relationship information without modifying data. The empty description lowers confidence slightly, but the pattern of similar tools (get_example, get_json_schema, get_model, get_model_diagram) all being read operations supports this classification.
From the tool's definition Tool name 'get_join_graph' suggests retrieval of relationship/schema metadata. No description provided to confirm, but naming convention aligns with Read category tools (get_*, describe_*) found on this semantic layer server.
Attacks that exploit this kind of access
get_join_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_join_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_join_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_join_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_join_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_join_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 →