octen-mcp
OfficialExtract any URL into clean, LLM-ready markdown with built-in page classification and relevance filtering.
Fetch web content: Convert 1–20 URLs per call into clean markdown or plain text, auto-normalizing bare hosts (e.g.,
octen.ai→https://octen.ai).Classify pages by topic: Each result includes a
categoryfield (e.g.,Finance,Health,Computers & Technology / AI) to filter out-of-vertical content before processing.Classify pages by structure: Each result includes a
page_structurefield (e.g.,Content Page / Article,Homepage,Index Page,No Main Content) to skip login walls, paywalls, JS shells, and navigation-only pages without spending LLM tokens.Summarize with highlights: Pass a
queryparameter to return only the most relevant ranked snippets per page instead of the full body — reducing token usage and improving signal.Handle failures gracefully: Failed URLs (404s, 5xx errors, DNS failures) return structured
status: failedresponses with descriptiveerror_messagefields.Control caching: Set
max_age_seconds(minimum 300s, default 24h) to force fresh fetches for time-sensitive pages like news or prices.Include media assets: Optionally retrieve image, video, audio, and favicon URLs found on each page.
Set per-URL timeout: Adjust extraction timeout from 1–60 seconds per URL.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@octen-mcpFetch octen.ai and summarize the main product features"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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:
search/news_search: search the live web with domain, text, language, and time filters.broad_search: decompose a query into multiple sub-queries, search them concurrently, and return results grouped per sub-query for broad coverage.extract: turn one or more URLs into clean, LLM-ready content.image_search(In Beta — contact us for beta access): search the web for images by text query, optionally with a reference image.video_search(In Beta — contact us for beta access): search the web for videos by text query.
What makes Octen useful for agents is that extract returns more than page text. Each successful result also includes:
category: what the page is aboutpage_structure: what kind of page it ishighlights: ranked snippets when you pass aquery
That lets an agent skip login walls, nav pages, and off-topic URLs before spending tokens on the full body.
Why Octen MCP
Fast
Web search averages 62ms. Fast enough for multi-step MCP workflows.
Accurate
Powered by SOTA text and VL embedding models. Better sources, fewer hallucinations.
Fresh
Live web data with minute-level updates. Useful for news, prices, and fast-moving pages.
Efficient
Clean highlights, optional full_content, and page labels keep model context relevant.
Related MCP server: Averra Extract MCP
Quick start
You need an OCTEN_API_KEY from octen.ai.
For most MCP clients, the config is:
{
"mcpServers": {
"octen": {
"command": "npx",
"args": ["-y", "octen-mcp"],
"env": {
"OCTEN_API_KEY": "your-key-here"
}
}
}
}Install command by client
Agent | One-line install |
Claude Code |
|
Codex |
|
Gemini CLI |
|
VS Code |
|
Cursor | Add to Cursor (then edit the key), or use the JSON above in |
Claude Desktop | No CLI — add the JSON above to the config file (see below) |
Config file locations
For clients without a CLI installer, drop the JSON config above into:
Claude Desktop:
~/Library/Application\ Support/Claude/claude_desktop_config.jsonCursor:
~/.cursor/mcp.jsonVS Code workspace:
.vscode/mcp.json(useserversinstead ofmcpServers)Windsurf / Cline / other clients: paste it into that client's MCP settings
Tools
Tool | What it does | Best for |
| Search the live web with domain, text, language (ISO 639-1), time, and content controls | a single focused web search |
| Same engine as | current events and timely reporting |
| Decompose a query into up to | research-style, multi-angle coverage |
| Fetch 1-20 URLs and return clean content, labels, and optional highlights | summarization, RAG, fact lookup |
| In Beta — contact us for beta access. Search the web for images by text query (optional reference | finding pictures, photos, visual references |
| In Beta — contact us for beta access. Search the web for videos by text query | finding videos, clips, footage |
Reference docs:
Keep the tools always on (optional)
In clients with MCP tool search enabled (the Claude Code default), tools are
deferred — the model runs a ToolSearch step to load them on demand. If you'd
rather have the Octen tools resident from the first turn (no discovery step), set
alwaysLoad on the server in your .mcp.json (Claude Code v2.1.121+):
{
"mcpServers": {
"octen": {
"command": "npx",
"args": ["-y", "octen-mcp"],
"env": { "OCTEN_API_KEY": "your-key-here" },
"alwaysLoad": true
}
}
}Each always-loaded tool uses context on every turn, and alwaysLoad blocks startup
until the server connects (capped at the ~5s connect timeout), so reserve it for tools
you hit constantly. To keep the cost down, mark just the highest-traffic tools — e.g.
search and broad_search — with "anthropic/alwaysLoad": true in each tool's _meta,
leaving the rest deferred.
Why agents like this
Most extract tools stop at "here is the page body." Octen helps one step earlier:
Skip bad pages early:
page_structure.primary == "No Main Content"tells the agent it hit a login wall, empty shell, or similar non-content page.Filter by topic early:
categoryhelps a pipeline ignore pages outside the target vertical before embedding or summarizing.Use less context:
queryreturnshighlightswhen the user wants a specific fact instead of the full page.
For the full decision tree and integration patterns, see docs/best-practices.md.
Example prompts
Fetch octen.ai and summarize the main product features.Search for recent MCP news from the last week.Fetch these URLs and only summarize the ones whose category is Finance.Search site:docs.anthropic.com prompt caching and return only the relevant highlights.
Environment variables
Variable | Required | Default |
| yes | — |
| no |
|
Local development
git clone https://github.com/Octen-Team/octen-mcp.git
cd octen-mcp
npm install
npm run build
OCTEN_API_KEY=<key> npm run inspectMore docs
Best practices for agent integration: docs/best-practices.md
Search API reference: docs.octen.ai/api-reference/search
Extract API reference: docs.octen.ai/api-reference/extract
License
MIT © Octen
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityCmaintenanceFetch URLs and return clean, LLM-ready markdown with metadata and layered prompt injection defense. Configurable timeouts, word limits, JS rendering, and link extraction. All-in-one MCP server + CLI.Last updated11MIT
- AlicenseAqualityDmaintenanceMCP server for Averra Extract — lets AI agents like Claude, Cursor, and ChatGPT convert any webpage into clean, LLM-ready Markdown.Last updated587MIT
- AlicenseAqualityBmaintenanceWeb extraction MCP server for AI agents. Extract structured data from any URL with built-in Cloudflare bypass, JavaScript rendering, and intelligent parsing. Returns clean markdown or JSON.Last updated57942MIT
- Alicense-qualityCmaintenanceMCP Server for Web2MD — convert webpage URLs to clean Markdown from Claude Desktop, Cursor, or any MCP-compatible agent.Last updated15MIT
Related MCP Connectors
Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.
Converts any URL to clean, LLM-ready Markdown using real Chrome browsers
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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