Save a selection of instances as a versioned JSON snapshot in the build library. Args: - path (string): Instance path to export - name (string): Name for the build entry - description (string, optional): Description Returns: { buildId, name, instanceCount }
AI agents use export_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.
This tool creates new build snapshots and stores them persistently in a version-controlled library. It is reversible (snapshots can be deleted or replaced), so it does not qualify as Destructive. However, it goes beyond simple metadata—it saves instance hierarchies as JSON snapshots, making it a Write operation that modifies the state of the build library.
From the tool's definition Tool is described as 'Save a selection of instances as a versioned JSON snapshot in the build library' — it creates and stores a new versioned build entry in persistent storage (the build library). This is a data creation/write operation.
Attacks that exploit this kind of access
Save a selection of instances as a versioned JSON snapshot in the build library. Args: - path (string): Instance path to export - name (string): Name for the build entry - description (string, optional): Description Returns: { buildId, name, instanceCount }. 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 export_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.
export_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 export_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 export_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.
export_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 →