Skip to main content
Glama

Get session status

browser_get_status
Read-onlyIdempotent

Get control mode and tab status for a session. If this connector is signed into a different Browse Bridge account than the extension on the same browser, the result is ACCOUNT_MISMATCH. Includes the current url, offOrigin when that url is outside allowedOrigins, sensitiveMode, and deviceOnline. sensitiveMode is true when Sensitive site is on: click, type, key, select, and navigation wait for Approve (APPROVAL_REQUIRED), which is not CHALLENGE_DETECTED. The switch stays on for this browser until the user turns it off, including the next tab they Enable, and sensitiveMode matches that switch. When the device heartbeat is stale, controlMode is disconnected and statusUx is SESSION_OFFLINE, not HUMAN_HAS_CONTROL. Includes remaining monthly quota (actionsRemaining, screenshotsRemaining), quotaExceeded, and quotaResetAt (ISO). dialogHook is { installed, error?, rawError? }. error and rawError are the Chrome scripting error, not a rewritten content-script message. statusUx and blocked keep a stable code; rawError is the Chrome string when it differs from the friendly message. statusUx names CHALLENGE_DETECTED, ORIGIN_NOT_ALLOWED, SESSION_OFFLINE, or HUMAN_HAS_CONTROL when the human must take over. CONTENT_SCRIPT_UNAVAILABLE is returned from tools if the agent is not on the tab. EXTENSION_RECONNECT_NEEDED means click Reconnect in the side panel, then retry. While a JavaScript dialog is open, dialog is { type, message, pending: true } and blocked.code stays JS_DIALOG_OPEN. A native HTTP sign-in prompt is HTTP_AUTH_REQUIRED in blocked and statusUx, with dialog null. The user answers or cancels it. Browse Bridge does not enter the username or password. Navigate, back, forward, and reload can leave that prompt. A timeout while that dialog is open is DIALOG_PENDING, not CONTENT_SCRIPT_UNAVAILABLE. In Agent mode, alert/confirm/prompt stay pending until browser_handle_dialog. They are not dismissed when they open. QUOTA_EXCEEDED names which quota (actions or screenshots) and resetAt. extensionVersion is the connected extension, sent on the WebSocket handshake and the first auth frame. meetsExtensionMinimum and meetsLatestExtension compare it with extensionMinVersion and latestExtensionVersion.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "sessionId": "<sessionId>"
    },
    "name": "browser_get_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
sessionIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.2/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare read-only/idempotent/non-destructive; the description adds extensive behavioral context beyond that: account mismatch handling, sensitiveMode approval flow, stale heartbeat behavior, quota states, dialog handling, error code meanings, and extension version comparisons. No annotation contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It opens with a clear purpose sentence but then becomes a dense wall of status-code semantics. Many details are useful, but the length is excessive for a status tool and the lack of grouping or bullets makes it hard to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does a thorough job explaining return fields and status codes. However, it omits any guidance on the sole input parameter and when to use the tool, leaving a clear completeness gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The sole required parameter, sessionId, has 0% schema description coverage, and the description never explains where to obtain it, its format, or its role beyond the vague phrase 'for a session.' This leaves the input semantics largely undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Get') and resource ('control mode and tab status for a session'), so the core purpose is clear. It does not explicitly differentiate itself from siblings like browser_list_sessions or browser_observe, which keeps it from a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to call this tool versus alternatives. The description explains many result conditions (ACCOUNT_MISMATCH, sensitiveMode, SESSION_OFFLINE) but never says when an agent should use this instead of browser_list_sessions or browser_observe.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.