Open the JD login page in a persistent browser session and return a QR screenshot path.
AI agents invoke login_jd to trigger actions in Parcel Pilot MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool launches a browser session and navigates to an external login page, constituting execution of a browser action with external side effects. It is not merely reading data — it opens a persistent browser session that could be reused for further actions. Severity is medium because it initiates authentication to a third-party platform (JD), which could expose credentials or session tokens if misused.
From the tool's definition Open the JD login page in a persistent browser session
Attacks that exploit this kind of access
Open the JD login page in a persistent browser session and return a QR screenshot path. It is categorised as a Execute tool in the Parcel Pilot MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Parcel Pilot MCP server in PolicyLayer and add a rule for login_jd: 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 Parcel Pilot MCP. Nothing to install.
login_jd is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the login_jd 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 login_jd. 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.
login_jd is provided by the Parcel Pilot MCP server (jieyangxchen/parcel-pilot-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 →