# AnySearch

Unified real-time search MCP server supporting general web search, vertical domain search, parallel batch search, and full-page URL content extraction.

Repository: https://github.com/anysearch-ai/anysearch-mcp-server
Canonical: https://ross.abutalabs.com/products/anysearch
Homepage: https://www.anysearch.com
License: Apache-2.0
License Family: permissive
Topics: anysearch, hermes, mcp, mcp-server, openclaw, qclaw
Last push: 2026-08-24T03:24:27+00:00
Link (homepage): https://www.anysearch.com

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 8
- inputs: {"age_days": 125, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1838, forks 183 (observed 2026-08-28T04:05:42.814359+00:00)

## What it is
AnySearch is a unified real-time search engine service for AI agents, distributed as an agent skill package and an MCP server. It provides general web search, vertical domain search, parallel batch search, and full-page content extraction via an API with optional key registration.

## Use cases
- give my AI agent real-time web search
- search the web from Claude Code or Cursor
- extract full page content for an LLM
- run parallel batch searches from an agent
- add an MCP search server to my agent setup
- vertical domain search for AI agents

## When to choose
- you need live web search integrated into AI agents like Claude Code, Cursor, or OpenClaw
- you want an MCP-compatible search tool with content extraction
- you need batch/parallel search queries from an agent

## When to avoid
- you need a self-hosted search engine with full control over indexing
- you want search without any external API dependency or rate limits
- you need a traditional SEO or analytics search tool

## Facets
- artifact type: service
- maturity: active
- function: search-engine, web-scraping, mcp, agent-framework, http-client
- domain: artificial-intelligence, developer-tools
- platform: python, cli, cross-platform
- tags: ai-agent-skills, real-time-search, mcp-server, web-search-api, content-extraction, claude-skills, ai-agents, search

## Member repositories
- anysearch-ai/anysearch-mcp-server (main) score 58
- anysearch-ai/anysearch-skill (plugin) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:42.814359+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:50:47.514181+00:00, confidence not recorded.
  - readme: https://github.com/anysearch-ai/anysearch-mcp-server (fetched 2026-08-28T04:05:42.814359+00:00, sha 82761d1d1ef6)
  - homepage: https://www.anysearch.com (fetched 2026-08-29T08:46:43.379927+00:00, sha 4aa033fe5419)
- Data as of 2026-08-30T08:39:29.467469+00:00.