Source-only multi-provider web search, extraction, evidence receipts, and onboarding for MCP clients
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"web-search-plus-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# 🔍 web-search-plus-mcp <p align="center"> <img src="docs/assets/web-search-plus-logo.png" alt="Web Search Plus" width="180"> </p> [](https://pypi.org/project/web-search-plus-mcp/) [](https://www.python.org/downloads/) [](https://modelcontextprotocol.io/) [](https://github.com/robbyczgw-cla/web-search-plus-mcp/actions/workflows/ci.yml) [](./LICENSE) [](https://glama.ai/mcp/servers/robbyczgw-cla/web-search-plus-mcp) **Give your AI app better web search and clean page reading.** `web-search-plus-mcp` works with Claude Desktop, Cursor, NanoBot, Hermes, and other MCP apps. It searches across the services you choose, returns the original sources, and can try another service when one fails. `web-search-plus-mcp 5.1.2` carries the engine fixes of Hermes Web Search Plus 5.1.2 (released 2026-10-18). ### What's new in 5.1.2 5.1.1 was never released, so this covers everything since 5.0.1. No provider request starts after the request deadline, `web_extract` returns exactly one result per requested URL in request order, and each result now carries `requested_url`, the URL you passed in (`url` is where the page was fetched). A rate limit, out-of-credit or auth error partway through a batch keeps the pages already fetched and marks the rest `not tried: …` instead of failing the whole batch, and URLs past the per-call limit of 10 get their own `not tried` row instead of disappearing. The per-request budget no longer depends on SQLite, half-open circuit probes release their lease, and the search cache is keyed by the credentials that produce…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.