AI agents call parallel_search 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 tool retrieves data through concurrent search operations without modifying, deleting, or executing code. It is a read-only operation that queries information and returns results, fitting the Read category with low severity due to minimal blast radius if misused by an AI agent.
From the tool's definition Tool performs 'search queries' and 'return[s] compact summaries' with no mention of modification, deletion, or execution capabilities. The batching mechanism addresses performance constraints, not side effects.
Attacks that exploit this kind of access
Run up to 5 search queries concurrently and return compact summaries. Fan-out is internally batched 3-at-a-time to avoid Studio heartbeat timeouts. Each query routes to one of: -. 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 parallel_search: 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.
parallel_search 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 parallel_search 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 parallel_search. 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.
parallel_search 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 →