Skip to main content
Glama
Octen-Team

octen-mcp

Official
by Octen-Team

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OCTEN_API_KEYYesYour Octen API key. Get one at https://octen.ai
OCTEN_API_URLNoOverride base URL for the Octen API (e.g., for staging or self-hosted)https://api.octen.ai

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
searchA

Search the live web with Octen and return ranked results (title, url, snippet). Set topic to news for news-focused results. Pass highlight to get a ranked snippet per result, or full_content to pull the cleaned page body inline (heavier — costs more context). Narrow with domain / text include-exclude filters and a time window (published/crawled start_time/end_time, or a relative time_range). Set include_images / include_videos to return media URLs per result.

news_searchA

Search recent news with Octen and return ranked articles (title, url, snippet). This is web search locked to topic: news — use it for current events, headlines, and timely reporting. Same options as search (domain / text filters, time window, highlight / full_content, media) except topic, which is fixed to news.

broad_searchA

Broad multi-angle web search with Octen. Best for questions that span several subtopics where a single search only reaches a few: comparisons across many sources (pricing, products, vendors), surveys and deeper research, and any multi-angle question. Pass the user's full question as query AS-IS — Octen expands it into related sub-queries and searches them concurrently, returning results grouped per sub-query (not deduplicated). Do NOT pre-split the question or call this repeatedly; raise max_queries for broader coverage instead. For a single focused lookup, use search. Per-sub-query options (count, topic, domain / text filters, time window, highlight / full_content, media) are the same as search and apply to every sub-query.

extractA

Fetch one or more URLs and return LLM-ready content from Octen. By default (no query) it returns each page's full content — this is what you want in almost all cases. Only pass query when the user explicitly asks to fetch relevance-ranked snippets for a specific topic; doing so returns highlights INSTEAD of the full body, so the content will be partial. Every result also includes a category (topical) and page_structure (typology) classification, unique to Octen. Bare hosts like 'octen.ai' are auto-normalized to https. Cached when fresh.

image_searchA

In Beta. Contact us to request beta access. Search the live web for images with Octen and return ranked results (title, source page, dimensions, thumbnail, description, summary). Pass a text query, and optionally an image_url to search by reference image. Set topic to design for UI design references — each result then carries a structured style summary and an html_snippet for building/restyling frontends. Use this when the user wants to find pictures, photos, diagrams, or visual references — not for general text web search.

video_searchA

In Beta. Contact us to request beta access. Search the live web for videos with Octen and return ranked results (title, source page, cover image, duration, matching segment, authors, description). Pass a text query. Use this when the user wants to find videos, clips, or footage — not for general text web search.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

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/Octen-Team/octen-mcp'

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