status
Reports whether this session can drive a game right now, and what to do if not. Distinguishes the three states that matter: the hub process (always up if this answers), extensionConnected (a browser attached to it), and tabsAvailable (tabs the user ticked with "Use this tab for MCP"). target is t...
This record as markdown: /tools/pixi-inspector-mcp/status.md
What status does on Pixi Inspector
AI agents call status to retrieve information from Pixi Inspector without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why status is rated Low
Even though status only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs status safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Pixi Inspector, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For status, this is the rule to start with:
status is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Pixi Inspector, apply this rule, and every status call is checked against it from then on.
Questions about status
Reports whether this session can drive a game right now, and what to do if not. Distinguishes the three states that matter: the hub process (always up if this answers), extensionConnected (a browser attached to it), and tabsAvailable (tabs the user ticked with "Use this tab for MCP"). target is the tab THIS session is pinned to — null until one is chosen, and carrying attached: false while a pinned tab is momentarily not reporting (a reload or a re-attaching browser: retry, do not re-ask the user) or when the user unticked it (it is then also in inactiveTabs: do not retry, ask whether to tick it again or choose another tab); candidates lists every drivable tab across every attached browser with its engine, and inactiveTabs lists live tabs the user has not ticked, and silentTabs counts tabs that ARE ticked but whose in-page agent is not answering — those need a tab RELOAD, not enabling. silentTargets lists their target ids when the browser reports them: browser.reload (or browser.navigate) with one of those as target works without a page agent and recovers the tab; every other tool keeps failing NO_TARGET on it. Top-level paired means at least one attached browser is paired; browsers[].paired is the per-browser value, and it alone decides whether an ext.* call in that browser is allowed. An upgrade field means the background hub answering you predates this connector (it survives package upgrades) — do what its action says, including re-checking the config of this client, before trusting anything else here. remedy always names the fix for the current state — relay the human, GUI-only steps to the user; act on the rest yourself. Needs no browser and is the right first call to diagnose any failure; it usually returns immediately, but can take a few seconds when it has to start the background hub or wait for a browser to finish (re)attaching. It is categorised as a Read tool in the Pixi Inspector MCP Server, which means it retrieves data without modifying state.
Register the Pixi Inspector MCP server in PolicyLayer and add a rule for status: 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 Pixi Inspector. Nothing to install.
status 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 status 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 status. 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.
status is provided by the Pixi Inspector MCP server (pixi-inspector-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Pixi Inspector, and thousands of servers like it.
This server
Across the catalogue