Server facts
anysearch-mcp
Project
- Author
- anysearch-ai
- Repository
- github.com/anysearch-ai/anysearch-mcp
- License
- Not specified
- Category
- Search & Web Data
Tech
- Runtime / language
- Not specified
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 1,943
- Last commit
- Data as of
Tags
- anysearch
- mcp
Overview
AnySearch supports both broad web research and lookups shaped by a particular field. The search tool accepts general queries, while specialized requests begin with get_sub_domains to identify routing options and structured parameters. Agents can use those results for searches involving finance, academic papers, legal cases, or security issues, including identifiers such as stock tickers, DOIs, and CVEs. General searches skip that discovery step, and filters can limit results by content type or freshness.
For separate research questions, batch_search runs up to 5 queries in parallel and can combine general searches with domain-specific ones. If a query fails, the others can still complete. The extract tool retrieves readable content from a page URL when snippets leave questions unanswered. API keys are optional; anonymous access has lower rate limits. Connections use native Streamable HTTP or proxies for SSE and stdio clients. Queries, extraction URLs, and API keys are sent to the AnySearch service.
anysearch-mcp setup notes
- anysearch-mcp records stdio only; confirm a network transport upstream before planning remote access.
- anysearch-mcp has no recorded license; confirm reuse terms in its repository.