Skip to content
AgentSearch logo

AgentSearch

Provides web search, URL extraction, and JavaScript rendering APIs for AI agents via Pocket Network.

At a glanceswept 2026-10-10

840 installs/mo

Emerging

For
AI agents and RAG pipelines needing live web search and content extraction
Price
Price not read
Activity
Actively maintainedrelease 8 days ago · site updated 6 days ago
Company
Domain since 2026domain registered
Runs as
API
Used for
  • search the live web and get fresh results as JSON
  • extract clean text and markdown from URLs for RAG
The companyeach fact with its source · read 2026-10-10
  • Domain since2026domain registered
How a program reaches itfound, not claimed · read 2026-10-10
  • MCP serverio.github.agentsearchhq-coder/agentsearch-mcppublished by agentsearchhq-coder on GitHub
  • Statenot asked yet
  • MCP docsagentsearchhq.com/blog/mcp-web-search-for-ai-agentsthe vendor's page ↗

MCP server details →

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.

Alternatives in Developer toolsby use, among tools still maintained

Figure and bar: visits/mo, estimate · year: online since

Compare AgentSearch with

Pick up to two.

All Developer tools tools →

Questions this page answers
  • What is AgentSearch?

    Provides web search, URL extraction, and JavaScript rendering APIs for AI agents via Pocket Network. It is listed in the Atlas under Developer tools.

  • Who is AgentSearch for?

    AI agents and RAG pipelines needing live web search and content extraction

  • Do people use AgentSearch?

    Emerging: 840 installs/mo (npm).

  • Is AgentSearch still maintained?

    Actively maintained: release 8 days ago · site updated 6 days ago.

  • What are alternatives to AgentSearch?

    In Developer tools, by use: Browserbase, TinyFish, The Content Repurpose Revolution, GlobalGPT, Airbyte, Olostep.

Not quite it? Describe the job

beta

Five tools from the Atlas that fit it, each judged against what you wrote.

How we read a tool

No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.

  • Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
  • Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
  • Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
  • The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.

How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.