AI agents use import_build to create or update resources in Melo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Melo environment.
The tool performs a write operation by importing and materializing a saved build into the active Studio project. While not destructive (the operation is reversible by undoing or deleting the imported content), it modifies the state of the development environment.
From the tool's definition Tool 'import_build' loads a saved build from the library into Studio, which creates or modifies the development environment by introducing external build data into the current workspace.
Attacks that exploit this kind of access
Load a saved build from the library into Studio. Args: - name (string): Build name to import - parent (string, optional): Parent path (default:. It is categorised as a Write tool in the Melo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Melo MCP server in PolicyLayer and add a rule for import_build: 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 Melo. Nothing to install.
import_build is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the import_build 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 import_build. 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.
import_build is provided by the Melo MCP server (yannyhl/linkedsword-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 →