Skip to main content
Glama

browse

Automate browser interactions on web pages by performing clicks, form fills, and scrolling actions to gather data or complete tasks programmatically.

Instructions

Interactive browser actions on a URL. Perform clicks, form fills, scrolling, and more. Costs 5 credits.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesURL to browse
actionsYesArray of browser action objects (click, type, scroll, etc.)

Implementation Reference

  • Main tool registration for 'browse' - includes the handler function that executes the tool logic: async ({ url, actions }) => jsonResult(await apiPost("/browse", { url, actions })). The tool takes a URL and array of browser action objects, makes a POST request to the /browse API endpoint, and returns the result as formatted JSON.
    server.tool(
      "browse",
      "Interactive browser actions on a URL. Perform clicks, form fills, scrolling, and more. Costs 5 credits.",
      {
        url: z.string().describe("URL to browse"),
        actions: z.array(z.record(z.unknown())).describe("Array of browser action objects (click, type, scroll, etc.)"),
      },
      async ({ url, actions }) => jsonResult(await apiPost("/browse", { url, actions }))
    );
  • Input schema definition for the browse tool using Zod: url (string) and actions (array of records containing unknown values). Defines the structure for browser action objects like click, type, scroll, etc.
    url: z.string().describe("URL to browse"),
    actions: z.array(z.record(z.unknown())).describe("Array of browser action objects (click, type, scroll, etc.)"),
  • Helper function apiPost() that makes POST requests to the SearchClaw API. Used by the browse tool handler to send the URL and actions to the /browse endpoint. Includes timeout handling and error management.
    async function apiPost(path: string, body: Record<string, unknown>) {
      const controller = new AbortController();
      const timeout = setTimeout(() => controller.abort(), 30000);
      try {
        const response = await fetch(`${API_BASE}${path}`, {
          method: "POST",
          headers: { ...headers, "Content-Type": "application/json" },
          body: JSON.stringify(body),
          signal: controller.signal,
        });
        if (!response.ok) {
          const text = await response.text();
          throw new Error(`SearchClaw API error ${response.status}: ${text}`);
        }
        return response.json();
      } finally {
        clearTimeout(timeout);
      }
    }
  • Helper function jsonResult() that formats the API response as MCP tool output. Converts the data to formatted JSON text and wraps it in the required MCP content structure.
    function jsonResult(data: unknown) {
      return { content: [{ type: "text" as const, text: JSON.stringify(data, null, 2) }] };
    }
Behavior3/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context beyond the schema by mentioning the cost ('Costs 5 credits'), which implies resource consumption and potential rate limits. However, it lacks details on permissions, error handling, or what 'interactive' entails (e.g., whether it simulates user behavior or requires authentication). The description doesn't contradict annotations, as none are given.

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

Conciseness4/5

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

The description is appropriately sized with two sentences that efficiently convey core functionality and cost. The first sentence front-loads the main purpose ('Interactive browser actions on a URL'), and the second adds critical behavioral context ('Costs 5 credits'). There is no wasted text, though it could be slightly more structured by explicitly listing key use cases.

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?

Given the tool's moderate complexity (interactive browser actions with 2 parameters) and no output schema, the description is partially complete. It covers the basic purpose and cost but lacks details on return values, error conditions, or examples of action objects. With no annotations to supplement, the agent might struggle with implementation specifics, though the schema provides parameter definitions.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents both parameters ('url' and 'actions') adequately. The description adds minimal value beyond the schema by implying that actions include 'clicks, form fills, scrolling, and more', but this is redundant with the schema's description of 'Array of browser action objects'. No additional syntax, format, or constraints are provided, meeting the baseline for high schema coverage.

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?

The description clearly states the tool's purpose with specific verbs ('Perform clicks, form fills, scrolling, and more') and identifies the resource ('Interactive browser actions on a URL'). It distinguishes from sibling tools like 'crawl' or 'screenshot' by emphasizing interactive actions rather than passive retrieval or capture. However, it doesn't explicitly differentiate from all siblings, such as 'extract' which might also involve browser interaction.

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?

The description provides no guidance on when to use this tool versus alternatives. It mentions 'Costs 5 credits' which hints at resource considerations but doesn't specify use cases, prerequisites, or exclusions. For example, it doesn't clarify when to choose 'browse' over 'crawl' for data extraction or 'screenshot' for visual capture, leaving the agent with minimal contextual direction.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/CSteenkamp/searchclaw-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server