Skip to main content
Glama
Sign In
wraith-mcp

wraith-mcp

by Koreahwan
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

extract

Pull structured data from any webpage by describing what you need in natural language. Provide a URL and a description of the desired data to receive structured output.

Instructions

Extract structured data from a webpage using natural language.

Args: url: Target URL data_description: What to extract, e.g. "all product names and prices in JSON" max_steps: Maximum interaction steps (capped at 50) session_id: Optional session ID to reuse an existing browser session

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": {
      "url": "<url>",
      "data_description": "<data_description>"
    },
    "name": "extract"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
max_stepsNo
session_idNo
data_descriptionYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.2

TDQS

A4.3/5.0
Behavior4/5

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

No annotations exist, so the description carries the burden. It adds useful behavioral details not in the schema: max_steps is 'capped at 50', session_id allows reusing a browser session, and 'interaction steps' implies the tool may take actions on the page. However, it does not disclose whether these actions are read-only or can modify state, or any permission requirements.

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

Conciseness5/5

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

The description is concise and well-structured: a one-sentence purpose followed by a succinct Args list. Every element adds value, and the most important information (purpose) is front-loaded.

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?

The description covers the tool's purpose, all parameters with examples, and key behavioral constraints. It lacks explicit usage guidance relative to siblings, but the presence of an output schema means return-value documentation is unnecessary. Overall, it is a solid, nearly complete description.

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?

Schema description coverage is 0%, but the description fully compensates with a clear Args list explaining each parameter. It provides an example for data_description ('all product names and prices in JSON'), specifies the max_steps cap, and clarifies session_id's purpose for reusing a session.

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 description clearly states 'Extract structured data from a webpage using natural language,' which combines a specific verb ('extract'), resource ('webpage'), and method ('natural language'). This distinguishes it from siblings like get_content or browse by emphasizing structured output and natural-language instructions.

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?

The description implies usage context (when you need structured data from a webpage) but does not explicitly compare to alternatives or state when not to use it. Mention of 'session_id' and 'interaction steps' provides some context, but there is no direct guidance on choosing this over sibling tools like get_content or snapshot.

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