obscura mcp. Its browser tools act on pages the agent already has a URL for. Set OBSCURA_WEB_SEARCH=keenable and the server also lists a web_search tool backed by Keenable, so the agent can find pages first. It works without an API key.
→ Web search in Obscura’s MCP server guide
Install
Theweb_search tool ships in Obscura 0.2.7 and later. Download the latest release binary, for example on Linux x86_64:
Turn on web search
Add the variable to the server’s environment in your MCP client config. For Claude Desktop, editclaude_desktop_config.json:
web_search next to Obscura’s browser tools. In Claude Code, pass the variable with -e:
The web_search tool
The tool returns one JSON object per line, each with
title, url and snippet. A response larger than 1 MiB after decompression returns a tool error. Each call goes from Obscura’s own HTTP client to api.keenable.ai, through the proxy you configured for Obscura.
Without a key, searches run on the shared public tier at lower rate limits. Add
KEENABLE_API_KEY to the server’s env block to use your organization’s limits. See API keys.Related pages
hyperresearch
Use Keenable as the web provider in hyperresearch, the deep-research pipeline, for search and page fetch. No key or extra install, 0.13.1 and later.
career-ops
Find job postings on employers’ own ATS pages from career-ops with the Keenable plugin: a search command and a portals.yml provider. No key needed.
Qwen-MM-Plugins
Use Keenable for web_search and web_extractor in the Qwen-MM-Plugins search plugin with QWEN_MM_SEARCH_BACKEND=keenable. Works without an API key.
Fetch quickstart
Turn any URL into clean markdown your model can read, or get only the part a prompt asks for. Try it with no API key. Code, cost per call and gotchas.