The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Extract listing page.
MCP (Model Context Protocol) server for Averra Extract — lets AI agents like Claude, Cursor, and ChatGPT convert any webpage into clean, LLM-ready Markdown.
Listed in the official MCP registry as dev.averra/extract. MCP clients that support registry-based install can reference that identifier directly; for clients that need manual configuration, see the install sections below.
Exposes the Averra Extract API as 5 MCP tools:
| Tool | Description |
|---|---|
averra_extract_url | Convert any URL to clean Markdown with metadata |
averra_check_usage | Check monthly quota and remaining requests |
averra_create_api_key | Create a new API key |
averra_list_api_keys | List all API keys on the account |
averra_revoke_api_key | Revoke an API key by ID |
Sign up at averra.dev — the free plan includes 50 requests/month.
Add this to your claude_desktop_config.json:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Restart Claude Desktop. The 5 tools will appear in your session.
Add to ~/.cursor/mcp.json (or use the Cursor MCP settings UI):
Any stdio-based MCP client works. Point it at npx -y @averra/extract-mcp with AVERRA_EXTRACT_API_KEY in the environment.
| Env var | Required | Default | Description |
|---|---|---|---|
AVERRA_EXTRACT_API_KEY | yes | — | Your Extract API key (starts with sk_live_) |
AVERRA_EXTRACT_BASE_URL | no | https://averra.dev | Override API host |
TRANSPORT | no | stdio | stdio (local) or http (hosted) |
PORT | no | 3000 | Port when TRANSPORT=http |
Once installed, try:
MIT