mcp-webextrator

webextrator_extract

Need structured data from a web page? Extract content by rendering the URL, returning clean JSON for products, articles, or general pages.

Instructions

Extract structured content from a web page using the WebExtrator API.

Navigates to the specified URL, renders the page, and extracts structured data
such as product details, article content, or general page information.

Use this when:
- You need to extract structured data from a web page
- You want product details, article content, or general page data
- You need LLM-enhanced semantic normalization of extracted content

Returns:
    By default, the extracted structured content inline. With async=true, a JSON envelope with a `task_id` — poll `webextrator_get_task` until it reports `finished_at`, then read the extracted content from its `response`.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	The URL of the web page to extract content from. Required.
`async`	No	Whether to process the request asynchronously.
`delay`	No	Extra delay in seconds after page load before extracting.
`headers`	No	Extra HTTP headers to include with the page request.
`timeout`	No	Total timeout in seconds for page load. Default is 30.
`enable_llm`	No	Enable LLM-based semantic normalization for richer structured output. Default is false.
`user_agent`	No	Override the User-Agent header for the page request.
`wait_until`	No	Page load wait condition before extracting. Options: 'load', 'domcontentloaded', 'networkidle', 'commit'. Default is 'networkidle'.
`callback_url`	No	Callback URL for async processing. If provided, the task runs asynchronously and results are sent to this URL when complete.
`expected_type`	No	Hint about expected page type. Options: 'product', 'article', 'general'. Helps the extractor optimize for the content structure.
`block_resources`	No	Resource types to block during page load to speed up rendering. Options: 'image', 'font', 'media', 'stylesheet', 'xhr', 'fetch'.
`wait_for_selector`	No	CSS selector to wait for before extracting content.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed5 schema fields changedv0.1.7Aug 28, 2026

addedInput schema / properties / async

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Whether to process the request asynchronously.",
+  "title": "Async"
+}

removedInput schema / properties / bypass_cache

Removed value: -{
-  "anyOf": [
-    {
-      "type": "boolean"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Skip the Redis result cache for this request (still writes the fresh result back). Default is false.",
-  "title": "Bypass Cache"
-}

removedInput schema / properties / cache_ttl_seconds

Removed value: -{
-  "anyOf": [
-    {
-      "type": "number"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Override the global cache TTL (seconds) for this entry. 0 means do not cache this response. Default is 3600.",
-  "title": "Cache Ttl Seconds"
-}

removedInput schema / properties / cookies

Removed value: -{
-  "anyOf": [
-    {
-      "items": {
-        "additionalProperties": true,
-        "type": "object"
-      },
-      "type": "array"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Cookies to install before navigation. Each cookie is an object with at least 'name' and 'value', plus optional 'domain', 'path', 'expires', 'httpOnly', 'secure', 'sameSite'. Useful for authenticated pages.",
-  "title": "Cookies"
-}

removedInput schema / properties / mode

Removed value: -{
-  "anyOf": [
-    {
-      "enum": [
-        "sync",
-        "async"
-      ],
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Processing mode. Defaults to API sync behavior. Pass 'async' to return immediately with a task_id to poll via webextrator_get_task.",
-  "title": "Mode"
-}

Changed1 schema field changedv0.1.5Aug 17, 2026

changedInput schema / properties / mode / description

Previous value: -"Processing mode. Defaults to 'async': returns immediately with a task_id to poll via webextrator_get_task. Pass 'sync' to wait for the result inline (may time out on slow pages)."New value: +"Processing mode. Defaults to API sync behavior. Pass 'async' to return immediately with a task_id to poll via webextrator_get_task."

Changed1 schema field changedv0.1.3Jul 28, 2026

changedInput schema / properties / mode / description

Previous value: -"Processing mode. 'sync' (default) waits for the result; 'async' returns immediately with a task_id to poll via the Tasks API."New value: +"Processing mode. Defaults to 'async': returns immediately with a task_id to poll via webextrator_get_task. Pass 'sync' to wait for the result inline (may time out on slow pages)."

Changed4 schema fields changedv0.1.2Jul 5, 2026

addedInput schema / properties / bypass_cache

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Skip the Redis result cache for this request (still writes the fresh result back). Default is false.",
+  "title": "Bypass Cache"
+}

addedInput schema / properties / cache_ttl_seconds

Added value: +{
+  "anyOf": [
+    {
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Override the global cache TTL (seconds) for this entry. 0 means do not cache this response. Default is 3600.",
+  "title": "Cache Ttl Seconds"
+}

addedInput schema / properties / cookies

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Cookies to install before navigation. Each cookie is an object with at least 'name' and 'value', plus optional 'domain', 'path', 'expires', 'httpOnly', 'secure', 'sameSite'. Useful for authenticated pages.",
+  "title": "Cookies"
+}

addedInput schema / properties / mode

Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "sync",
+        "async"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Processing mode. 'sync' (default) waits for the result; 'async' returns immediately with a task_id to poll via the Tasks API.",
+  "title": "Mode"
+}

First observedv0.1.0Jun 28, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries the full burden. It transparently reveals the core behaviors: navigation, rendering, extraction, sync vs. async returns, and LLM enhancement. It even describes the async envelope structure and how to retrieve results. While it doesn't discuss error handling or rate limits, for a read-only extraction tool this is adequate disclosure.

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 well-structured with a short purpose statement, a 'Use this when' bullet list, and a 'Returns' section. It front-loads the core purpose and includes necessary workflow details without extra fluff. It's slightly longer than minimal, but every section earns its place.

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?

Given the tool's complexity (12 parameters, async support, callback URLs), the description covers the key workflow: how to run synchronously vs. asynchronously, how to poll for async results, and the supported content types. It also notes LLM enhancement. Missing details like error handling or specific exceptions are minor given the available output schema and the clear description of the primary flow.

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 coverage is 100%, so the description doesn't need to restate parameters. It adds context for async (via callback_url and async flag), LLM normalization (enable_llm), and the wait_until options, but doesn't go into depth on each parameter. This aligns with the baseline of 3—the schema handles most semantics, and the description clarifies the most important behavior details.

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 the tool's action ('Extract structured content from a web page') and names the specific resources (product details, article content, general page info). It distinguishes itself from siblings like webextrator_render by focusing on structured extraction rather than rendering.

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

Usage Guidelines4/5

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

The 'Use this when' section explicitly lists scenarios, and the description explains the async flow with webextrator_get_task for polling results. It doesn't explicitly contrast with alternative tools (e.g., when to use webextrator_render instead), but the primary use cases are clear enough for an agent to select this tool correctly.

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

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/AceDataCloud/WebExtratorMCP'

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