Write new source code to a script. The change is NOT applied immediately — it is staged as a diff in the review queue. The user can accept or reject individual hunks in the Linkedsword plugin. If auto-accept is enabled, changes apply immediately without staging. Args: - path (string): Script path...
AI agents use set_script_source 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 or modifies script source code within Roblox Studio, which is a reversible write operation. While the default behavior stages changes for review (reducing immediate risk), the auto-accept mode enables direct code execution without human review, creating potential for malicious script injection or unintended logic changes.
From the tool's definition Tool description states 'Write new source code to a script' and 'The change is NOT applied immediately — it is staged as a diff in the review queue.' The args include 'source (string): Complete new source code' which is written to the script via the path…
Attacks that exploit this kind of access
Write new source code to a script. The change is NOT applied immediately — it is staged as a diff in the review queue. The user can accept or reject individual hunks in the Linkedsword plugin. If auto-accept is enabled, changes apply immediately without staging. Args: - path (string): Script path - source (string): Complete new source code Returns: Diff summary showing what changed, with hunk count and line additions/removals. If any hunks are rejected, the rejection context will be included in subsequent tool responses. 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 set_script_source: 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.
set_script_source 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 set_script_source 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 set_script_source. 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.
set_script_source 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 →