AI agents call get_tagged to retrieve information from Melo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward data retrieval tool that queries existing tags and returns matching instances. It has no side effects, does not execute code, modify data, or trigger external operations. The blast radius of misuse is minimal—an AI agent could only discover information about tagged instances in the workspace, which is non-destructive reconnaissance.
From the tool's definition Tool name 'get_tagged' and description 'Find all instances with a specific CollectionService tag' indicate a query operation that retrieves data without modification. Returns array of instance metadata (name, path, className).
Attacks that exploit this kind of access
Find all instances with a specific CollectionService tag. Args: - tag (string): Tag name Returns: Array of { name, path, className } for tagged instances. It is categorised as a Read tool in the Melo MCP Server, which means it retrieves data without modifying state.
Register the Melo MCP server in PolicyLayer and add a rule for get_tagged: 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.
get_tagged 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_tagged 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_tagged. 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_tagged 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 →