no-api-search
Used as one of the fallback search engines via ddgs when DuckDuckGo search is challenged, contributing results that are merged into the web_search output.
Provides web search through DuckDuckGo's HTML search page, returning numbered results with titles, URLs, and snippets; falls back to aggregated results from other engines when DuckDuckGo presents a bot challenge.
Used as one of the fallback search engines via ddgs when DuckDuckGo search is challenged, contributing results that are merged into the web_search output.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
no-api-search
Free web search and page reading for local AI agents: clean markdown from web pages, including JavaScript pages, PDFs and many bot-walled sites, with no API key.
On 30 public pages (docs, news, GitHub, papers, JavaScript apps, bot-walled sites), fetch_url returned the page for 27 and curl for 21. Where both did, fetch_url used 9.6% of curl's tokens on average: MDN's HTTP status page is 63,258 tokens with curl and 2,833 with fetch_url. A fetch_url call took 4.7 s on average, curl 0.35 s.
Install
Requires uv.
pi
pi install git:github.com/tctsung/no-api-searchopencode: add to ~/.config/opencode/opencode.json
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"web": {
"type": "local",
"command": ["uvx", "--from", "git+https://github.com/tctsung/no-api-search", "no-api-search", "mcp"]
}
}
}Codex
codex mcp add web -- uvx --from git+https://github.com/tctsung/no-api-search no-api-search mcpThe agent starts the server when a session starts and stops it when the session ends; there is no daemon and no open port. The first start takes about 4 s while uv builds an isolated environment (5 packages, 33 MB), later starts under 1 s. Nothing is installed into your Python.
Related MCP server: read-website-fast
Tools
Function | Arguments | Returns |
|
| Numbered results: title, URL, snippet |
|
| Page as markdown, link URLs removed; when truncated, a note with the next |
CLI
Same argument names as the tools:
uv tool install git+https://github.com/tctsung/no-api-search
no-api-search search "python dataclasses" --max_results 5
no-api-search fetch https://arxiv.org/pdf/1706.03762 --offset 20000 --max_chars 20000How it works
web_search sends one request to DuckDuckGo's HTML page. If DuckDuckGo answers with a bot challenge, the query goes to ddgs, which searches up to seven other engines (Brave, Yahoo, Mojeek and others) and merges their results.
fetch_url asks Jina Reader for the page; Jina loads it in a browser, so JavaScript runs and PDFs become text. If Jina returns an error, a 403/404/CAPTCHA warning or a placeholder page, markdown.new tries next, which gets through some bot walls. If both fail, ddgs fetches the page directly from your machine, without JavaScript. Each step runs only when the previous one fails, so a typical call makes one request.
Limits
Queries go to DuckDuckGo, or to the engines ddgs uses. Fetched URLs go to
r.jina.ai, thenmarkdown.new. Do not search for or fetch confidential content.Keyless quotas: Jina 20 requests per minute, markdown.new 500 per day per IP.
Search engines challenge datacenter and corporate IP ranges more often than residential ones.
opencode 1.19.6 sends SIGTERM to every process you own when
opencode mcp listoropencode modelsstops a stdio MCP server. This happens with any server, not only this one. Do not run those two commands until opencode fixes it.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Web search and any page as LLM-ready Markdown for AI agents. Free keyless tier, no signup.
Fetch pages as markdown, search web and news, extract structured data. For AI agents.
Scrape, map, crawl, search and monitor the web. Runs locally with no API key, cites every source.
Web search, Google SERP, page extraction to markdown and cited answers for AI agents.
Related MCP Servers
- AlicenseAqualityBmaintenanceGives AI agents local web search and page reading with no API keys, layering a SearXNG-backed search cache with browser-based fallbacks and returning clean page text from HTML, PDF, JSON, and archived snapshots. Fetches run in Docker alongside the search engine with SSRF protection, egress filtering, and untrusted-content marking so agents can safely retrieve live web data.2MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and LLM pipelines to fetch webpages and crawl sites locally, stripping noise and converting content to clean, token-efficient Markdown with preserved links, caching, and polite crawling.-
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to run web searches across configured providers and crawl individual pages or entire sites into deduplicated Markdown or JSON, including options for authenticated pages and CLI/API access.-
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to fetch and crawl websites locally, extract main content, preserve links, and convert pages to clean Markdown with minimal token footprint.MIT