How do I install and run extract-mcp?

Install via npm with `npx @averra/extract-mcp@0.1.5`. It runs over stdio transport, so configure it in your MCP client to spawn the process and communicate via standard input/output.

What metadata does the server extract from URLs?

The registry indicates metadata extraction is included, but specific fields are not detailed in the available documentation. Check the server's output schema or contact the maintainer for the full metadata spec.

Does extract-mcp cache results to avoid repeated requests?

Yes, caching is built in. This reduces redundant API calls and speeds up repeated requests to the same URL, which is especially useful in batch AI processing workflows.

Is there a cost or rate limit for using this server?

Pricing and rate limits are not documented in the available registry metadata. Check the Averra documentation or GitHub repository for billing details and usage constraints.

MCP ServerSTDIOOfficialv0.1.5

Averra Extract MCP Server

Extract clean markdown from any URL with built-in metadata extraction and caching, designed for AI pipelines that need reliable web content processing without manual parsing.

dev.averra/extract

Try MCP with AI models View source

Hosted URL

Local install

Transport

STDIO

Auth

No auth required

What the Averra Extract MCP server does

How models use it and what it is built for.

Extract clean markdown from any URL with built-in metadata extraction and caching, designed for AI pipelines that need reliable web content processing without manual parsing.

Connect to Averra Extract

Local install — runs as a subprocess.

npx @averra/extract-mcp@0.1.5

Resources

Where to find authoritative docs and source for Averra Extract.

Source repository

Example prompts for Averra Extract

Paste any of these into Agent Studio after connecting Averra Extract.

Convert this blog post URL to markdown and extract the publication date
Fetch the article at example.com/post and return structured markdown with metadata
What metadata does the extract API return for a given URL
Show me how caching works in the extract-mcp server

Averra Extract MCP server — FAQ

Common questions about connecting and running Averra Extract.

What does the extract MCP server do?
It converts URLs to clean markdown with metadata extraction and built-in caching, optimized for AI pipelines that need reliable web content processing. It handles the parsing and formatting so your AI can focus on content analysis.
How do I install and run extract-mcp?
Install via npm with `npx @averra/extract-mcp@0.1.5`. It runs over stdio transport, so configure it in your MCP client to spawn the process and communicate via standard input/output.
What metadata does the server extract from URLs?
The registry indicates metadata extraction is included, but specific fields are not detailed in the available documentation. Check the server's output schema or contact the maintainer for the full metadata spec.
Does extract-mcp cache results to avoid repeated requests?
Yes, caching is built in. This reduces redundant API calls and speeds up repeated requests to the same URL, which is especially useful in batch AI processing workflows.
Is there a cost or rate limit for using this server?
Pricing and rate limits are not documented in the available registry metadata. Check the Averra documentation or GitHub repository for billing details and usage constraints.

Skip the local setup — run MCP in your browser

MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.

Open Agent Studio