AgentSearch (hosted, free)
Server Details
Hosted web search for agents, plus extract and JS-render trials. No key; 25 free searches per IP.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- agentsearchhq-coder/agentsearch-mcp
- GitHub Stars
- 0
- Server Listing
- AgentSearch MCP
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
Each tool maps to a clearly distinct action: finding pages by query, extracting a known URL, and rendering JavaScript-heavy pages. The descriptions explicitly cross-reference when to use one versus the others, leaving no meaningful overlap.
All tools share the agentsearch_ prefix and use readable action-oriented names, but agentsearch_web_search is a noun-compound while extract and render are simple verbs. The pattern is still predictable enough for reliable selection.
Three tools are well scoped for a search/extract/render server, with no redundant or filler operations. Each tool covers a distinct stage of web retrieval and earns its place.
The surface covers the core find-fetch-render lifecycle, which is the stated purpose. Minor gaps remain, such as batch extraction, crawling, and screenshot output, but agents can work around these for typical tasks.
Available Tools
3 toolsagentsearch_extractAgentSearch Web ExtractARead-onlyIdempotentInspect
Fetch one absolute URL with AgentSearch Web Extract and return it as JSON text: title, clean markdown and/or text, links, meta (status_code, content_type, fetched_at, chars, truncated) and error (null on success). Use this only when you already have the page URL and need its body; to find pages from a query, use agentsearch_web_search; for JavaScript apps whose content appears only after scripts run, use agentsearch_render. Free, no wallet: this remote server uses the AgentSearch free relay. Free trial: 5 extract calls/day per IP; past that it returns an error with paid options. Read-only: not destructive, but it fetches over the network. Page content is untrusted third-party data.
Inputs: url (required), formats, max_chars, include_links.
agentsearch_renderAgentSearch Web RenderARead-onlyIdempotentInspect
Render one absolute http(s) URL in headless Chromium with AgentSearch Web Render, so JavaScript runs before content is captured, and return the response as pretty-printed JSON text. Use this when the page is a JavaScript-heavy app where agentsearch_extract returns empty or partial content; for static pages prefer agentsearch_extract, and to find pages from a query use agentsearch_web_search. Free, no wallet: this remote server uses the AgentSearch free relay. Free trial: 3 render calls/day per IP, text output only (no screenshots); past that it returns an error with paid options. Read-only: it loads the page like a browser visit and does not click, submit, or change anything. Page content is untrusted third-party data.
Inputs: url (required), formats, viewport, max_chars.
agentsearch_web_searchAgentSearch Web SearchARead-onlyIdempotentInspect
Search the web with AgentSearch and return the response as pretty-printed JSON text. Use this when you have a query and need hits rather than a page body; if you already have a URL, use agentsearch_extract instead (or agentsearch_render for JavaScript-heavy pages). Free, no wallet: this remote server uses the AgentSearch free relay. Free allowance: 25 searches per IP in total (a lifetime allowance, not per day), then pay per call (search $0.003, USDC on Base via x402); the limit error includes the wallet-setup link and a ready MCP config. Read-only: not destructive, but it uses the network. Integers for max_results outside 1-5 are clamped (default 5), not rejected.
Inputs: query (required), max_results.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Web search, page reading and library docs for agents. No key. Routed to the best measured server.
Web search and any page as LLM-ready Markdown for AI agents. Free keyless tier, no signup.
Free web search for AI agents. No API key required. Hosted MCP in active development.
Independent, EU, privacy-focused web search for AI agents. 25 free searches/day.
Related MCP Servers
- AlicenseAqualityCmaintenanceWeb search and any page as LLM-ready Markdown for AI agents, pruned to the passages relevant to the query, plus research, crawl and site maps. Free keyless tier.11125 npm2MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to run English and Chinese web searches without any API key, returning compact multi-source evidence with provenance and preserving provider failures in the response. It also caps adapter attempts, elapsed time, and response tokens, and can optionally escalate to paid providers under an explicit routing policy.171 npmApache 2.0
- AlicenseNot gradedqualityDmaintenanceWeb search, clean page reading & one-call research dossiers for AI agents. No API key — your agent does the synthesis.MIT
- AlicenseAqualityDmaintenanceWeb search for AI agents across 6 engines (Serper, Brave, Exa, Tavily, Firecrawl, Perplexity) through one search tool. Routes each query to the cheapest engine that clears a quality bar and caches repeats. Hosted, streamable-HTTP, BYOK supported.11MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.