Skip to main content
Glama
Sign In
BrowserSolver MCP Server

BrowserSolver MCP Server

Official
by browsersolver
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Website Crawler

website_crawler
Read-only

Retrieves public HTML via plain HTTP without launching a browser, so you can pull page content when the first response already includes what you need.

Instructions

Website Crawler. Fast HTTP pull of public HTML with no browser session. Ideal when the first response already contains the content you need. Credit cost: 1 credit per call.

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": {
      "query": "<query>"
    },
    "name": "website_crawler"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesPublic URL to retrieve with the Crawler tier (plain HTTP, no JavaScript). Include http:// or https://.
fieldsNoComma-separated list of fields to keep in the response, with dot notation for nested fields (e.g. name,location.city). Does not change the credit cost.
allow_redirectsNoWhether BrowserSolver should chase HTTP redirects for this fetch. Default: true.
return_page_sourceNoChoose between processed markup and the exact bytes from the origin. Default: false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare read-only, open-world, non-destructive, so the description earns credit for adding what they don't: the cost model (1 credit per call), the absence of JavaScript execution and browser sessions, and the implication that it is the cheap/fast tier. It does not cover rate limits or anti-bot failure behavior, which matters for an open-world fetch tool.

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?

Four short sentences, front-loaded with mechanism then the ideal-use condition then cost. The opening 'Website Crawler.' duplicates the title and earns nothing, but the rest is tight.

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

Completeness4/5

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

For a simple, fully documented read tool with annotations and no output schema, the essentials are present: what it fetches, that it skips JavaScript, and what it costs. The remaining gap is what happens on anti-bot blocks or non-HTML responses, which a sibling comparison would have resolved.

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% and every parameter is documented inline, so the description need only reinforce meaning. It adds the no-JavaScript constraint but nothing about query format, fields projection, or the source-vs-processed toggle beyond what the schema already says. Baseline 3 applies.

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?

After a redundant restatement of the title, it gives a specific mechanism: 'Fast HTTP pull of public HTML with no browser session.' That distinguishes it in spirit from browser-based siblings like website_rendering or website_webunlocker, though none are named explicitly.

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

Usage Guidelines3/5

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

'Ideal when the first response already contains the content you need' implies a usage condition, but it never names the alternatives (website_rendering, website_webunlocker, website_antibot) or states when to avoid this tool, leaving the routing decision to inference.

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

Deploy Server

Other Tools