find_composables
AI agents call find_composables 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 tool appears designed to locate or list reusable composable components within the semantic layer. Even in the worst case where it could retrieve sensitive metadata, the operation itself is read-only with no modification, execution, or destructive capability.
From the tool's definition Tool name 'find_composables' suggests a search or discovery operation within a semantic layer context. The description is empty, but contextually, this appears to be a retrieval/exploration function similar to sibling tools like 'find_artefacts' and…
Attacks that exploit this kind of access
find_composables. 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 find_composables: 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.
find_composables 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_composables 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_composables. 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_composables 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 →