Skip to main content
Glama

Navigate

browser_navigate

Navigate the delegated tab to an allowed http(s) origin. Required: sessionId and url. Userinfo in the URL (https://user:password@host) is stripped before navigation and redacted to https://***@host in status, sessions, and history. Does not take observationId. If another action is still running, this call waits for it to finish (about 5s) and then navigates. BUSY means that wait ran out — retry with sessionId and url. Navigation pushes a history entry (location.assign on the top window) so browser_back and browser_forward move the tab. Navigation is paced; RATE_LIMITED means wait retryAfterMs. On a sensitive site, navigation returns APPROVAL_REQUIRED with approvalId. A different site returns APPROVAL_REQUIRED immediately with origin and approvalId — do not wait for command timeout. Allow this site going forward adds that origin to allowedOrigins for the rest of the share. Just this once does not add it, so allowedOrigins stays unchanged and a later navigation there asks again. The user can remove an added origin in the extension. After Approve, the completed success includes that same approvalId and approved: true. A navigate that did not need approval does not include approvalId. If a page asks for an HTTP sign-in, navigate returns HTTP_AUTH_REQUIRED and the tab is blocked. Call back (cancels the prompt) or navigate elsewhere. A JavaScript dialog opened by the navigation stays pending and is reported as dialog: { type, message, pending: true }. Navigating again while that dialog is open returns DIALOG_PENDING.

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>",
      "url": "<url>"
    },
    "name": "browser_navigate"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
sessionIdYes
idempotencyKeyNoA key replays the original result only within ~60 seconds of the first call, only for the same Mcp-Session-Id, the same credential (API key or OAuth token), the same browser session, and the same tool. After the window, or under a different session/credential/tool, the call executes and bills normally. Reusing a key with different arguments returns IDEMPOTENCY_KEY_REUSED and is not executed or billed. Refusals (e.g. NO_HISTORY_ENTRY) are not cached, so the same key re-executes once state changes. A key passed in _meta is ignored.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

This description provides rich behavioral context that is entirely absent from the annotations. It covers critical behaviors such as URL redaction logic, how history is pushed (`location.assign`), internal timeouts (BUSY state), and various non-standard return states (HTTP_AUTH_REQUIRED, DIALOG_PENDING).

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

Conciseness3/5

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

While the tool is highly complex, the definition is excessively long. Many paragraphs repeat or expand on information that is inherently part of the state machine (like the exact sequence of approval logic). It sacrifices brevity for necessary completeness.

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

Completeness5/5

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

Given the high complexity and numerous edge cases (authentication, rate limiting, allowed origins, history mutation), the description is exceptionally complete and covers all state transitions the agent might encounter.

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

Parameters5/5

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

With only 33% schema description coverage, the description is vital. It elaborates extensively on the complex mechanics of the optional 'idempotencyKey' (replay window, caching of refusals) and clarifies the operational requirements for 'sessionId' and 'url' (e.g., stripping user info and needing an allowed origin).

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

Purpose5/5

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

The purpose is stated unambiguously: 'Navigate the delegated tab to an allowed http(s) origin.' It clearly defines the action (navigate) and the target (allowed origin), distinguishing it from sibling tools like browser_back or browser_forward which manipulate history.

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

Usage Guidelines5/5

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

The description offers extensive usage guidance beyond a simple execution: it mandates that the URL must be an allowed origin, specifies how rate limiting affects usage (wait and retryAfterMs), and details the two distinct paths for sensitive sites vs. other sites regarding approvals.

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.