
Octen Mcp
Wraps the Octen Extract API so Claude can pull live web pages as clean markdown with three filters most extract tools skip: category labels (tech, health, finance), page structure flags (article, homepage, login wall, no main content), and query driven highlights instead of full body dumps. The big win is filtering upstream. When your RAG pipeline fetches 100 URLs, maybe 20 are index pages or paywalls that cost you LLM tokens to discover they're useless. Octen flags them at fetch time via page_structure so you skip the embedding step entirely. Pass a query parameter and you get ranked snippets per page instead of paying to process full content. Supports batches of up to 20 URLs, configurable cache TTL, and optional image or video URL extraction.
- GitHub stars
- 10
- tools
- 9
- auth
- Secret needed
- transport
- STDIO
- env vars
- 2
- last updated
- May 20, 2026
Tools
9 toolsPublic tool metadata for what this MCP can expose to an agent.
searchSearch the live web with domain, text, language (ISO 639-1), time, and content controls
Search the live web with domain, text, language (ISO 639-1), time, and content controls
No parameter schema in public metadata yet.
news_searchRecent news as ranked articles plus subjects — the coverage grouped into storylines with summaries
Recent news as ranked articles plus subjects — the coverage grouped into storylines with summaries
No parameter schema in public metadata yet.
business_searchCompany and person cards (profile, financials, key people, career, recent activity) plus the ranked sources
Company and person cards (profile, financials, key people, career, recent activity) plus the ranked sources
No parameter schema in public metadata yet.
place_searchPlace cards (address, coordinates, phone, hours, status, rating) around a point or in a named area; web pages about them are opt-in
Place cards (address, coordinates, phone, hours, status, rating) around a point or in a named area; web pages about them are opt-in
No parameter schema in public metadata yet.
pulse_searchPredicted destinations — titles and URLs in ~10ms, or page content in standard mode. No filters, no freshness
Predicted destinations — titles and URLs in ~10ms, or page content in standard mode. No filters, no freshness
No parameter schema in public metadata yet.
broad_searchDecompose a query into up to max_queries sub-queries, search concurrently, return grouped results
Decompose a query into up to max_queries sub-queries, search concurrently, return grouped results
No parameter schema in public metadata yet.
extractFetch 1-20 URLs and return clean content, labels, and optional highlights
Fetch 1-20 URLs and return clean content, labels, and optional highlights
No parameter schema in public metadata yet.
image_searchSearch the web for images by text query (optional reference image_url)
Search the web for images by text query (optional reference image_url)
No parameter schema in public metadata yet.
video_searchIn Beta — contact us for beta access. Search the web for videos by text query
In Beta — contact us for beta access. Search the web for videos by text query
No parameter schema in public metadata yet.
Sponsors
Configuration
OCTEN_API_KEY*secretOcten API key. Get one at https://octen.ai (self-serve).
OCTEN_API_URLdefault: https://api.octen.aiOverride the Octen API base URL. Default: https://api.octen.ai.
Readme
octen-mcp
MCP server for Octen. Plug it into Claude, Cursor, VS Code, Windsurf, or any MCP client to give your agent live web search and URL extraction.
Core capabilities:
Details
- Repository
- github.com/octen-team/octen-mcp
- Categories
- AI & LLM Tools, Documents & Knowledge
- Package
octen-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active