Poll captured output logs from the running play session. Call repeatedly to get new output. Args: - since (number, optional): Only return logs after this timestamp Returns: { logs: Array<{ type, message, timestamp }>, isRunning: boolean }
AI agents call get_playtest_output 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 pure read operation that queries existing playtest logs without side effects. It does not create, modify, delete, or execute any operations—only retrieves diagnostic output. The optional 'since' parameter filters results but does not change the underlying data. Severity is low because log data is typically non-sensitive operational information and misuse would not cause system damage or compromise.
From the tool's definition Tool retrieves captured output logs from a running play session via polling. The description explicitly states it 'polls' and 'gets' output with no mention of modification, deletion, or execution.
Attacks that exploit this kind of access
Poll captured output logs from the running play session. Call repeatedly to get new output. Args: - since (number, optional): Only return logs after this timestamp Returns: { logs: Array<{ type, message, timestamp }>, isRunning: boolean }. 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_playtest_output: 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_playtest_output 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_playtest_output 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_playtest_output. 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_playtest_output 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 →