{
  "markdown": "# google-researcher-mcp — DEPRECATED\n\n> **⚠️ This project has been superseded by [`web-researcher-mcp`](https://github.com/zoharbabin/web-researcher-mcp).**\n>\n> A complete rewrite in Go: same tools, but it cites real sources and stays honest — citation verification, retraction flagging, eight search providers behind one interface, and a single signed static binary. No Node.js, no npm.\n\n---\n\n## Migrate in one line\n\nYour **API keys and tool calls don't change** — only how the server is launched. Pick whichever you prefer (no Node required):\n\n```bash\n# macOS / Linux — installs the binary and registers it with Claude Code automatically:\ncurl -fsSL https://raw.githubusercontent.com/zoharbabin/web-researcher-mcp/main/install.sh | sh\n\n# Windows (PowerShell):\npowershell -ExecutionPolicy Bypass -c \"irm https://raw.githubusercontent.com/zoharbabin/web-researcher-mcp/main/install.ps1 | iex\"\n\n# Python users (uv) — run with no install:\nuvx web-researcher-mcp\n```\n\n### Before / after (MCP client config)\n\nThe config keeps the **same shape** — swap the `command`/`args`, keep your env:\n\n```jsonc\n// BEFORE — google-researcher-mcp (npx / Node)\n{\n  \"mcpServers\": {\n    \"google-researcher\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"google-researcher-mcp\"],\n      \"env\": { \"GOOGLE_CUSTOM_SEARCH_API_KEY\": \"…\", \"GOOGLE_CUSTOM_SEARCH_ID\": \"…\" }\n    }\n  }\n}\n\n// AFTER — web-researcher-mcp (installed binary; or use \"uvx\" + args [\"web-researcher-mcp\"])\n{\n  \"mcpServers\": {\n    \"web-researcher\": {\n      \"command\": \"web-researcher-mcp\",\n      \"env\": { \"GOOGLE_CUSTOM_SEARCH_API_KEY\": \"…\", \"GOOGLE_CUSTOM_SEARCH_ID\": \"…\" }\n    }\n  }\n}\n```\n\n> **Don't run both at once** — they register identical tool names. Remove the `google-researcher` entry before adding `web-researcher`.\n\n**→ [Full migration guide](https://github.com/zoharbabin/web-researcher-mcp/blob/main/docs/MIGRATION.md)**\n\nYour existing `GOOGLE_CUSTOM_SEARCH_API_KEY` and `GOOGLE_CUSTOM_SEARCH_ID` work unchanged.\n\n---\n\n## Why the Rewrite?\n\n| Open Issue | Resolution in web-researcher-mcp |\n|------------|----------------------------------|\n| [#108](https://github.com/zoharbabin/google-researcher-mcp/issues/108) — Orphan detection fails via npx | Go binary has native process lifecycle (EOF/SIGPIPE) — no npm wrapper |\n| [#107](https://github.com/zoharbabin/google-researcher-mcp/issues/107) — Google discontinuing 'entire web' search | Eight providers (Brave, Serper, SearXNG, SearchAPI, Tavily, Exa, DuckDuckGo + Google PSE for lenses) with automatic fallback |\n| [#55](https://github.com/zoharbabin/google-researcher-mcp/issues/55) — Support alternative search engines | Multiple engines behind one interface, plus a zero-config DuckDuckGo default |\n| [#72](https://github.com/zoharbabin/google-researcher-mcp/issues/72) — Add Redis caching | Hybrid cache: memory + AES-encrypted disk + optional Redis |\n| [#40](https://github.com/zoharbabin/google-researcher-mcp/issues/40) — Split server.ts into modules | Fully modular Go architecture (one package per concern) |\n\nPlus what's new: **verify_citation** and **audit_bibliography** (catch fabricated/retracted citations), academic / patent / SEC-filing / US-case-law / economic / clinical-trial search, and authority-weighted search lenses.\n\n---\n\n## Links\n\n- **New project**: https://github.com/zoharbabin/web-researcher-mcp\n- **Install (all methods)**: [README → Get started](https://github.com/zoharbabin/web-researcher-mcp#get-started-in-30-seconds)\n- **Docker**: `docker pull zoharbabin/web-researcher-mcp:latest`\n- **Releases**: https://github.com/zoharbabin/web-researcher-mcp/releases\n",
  "bytes": 3604,
  "sha": "3b8d0acb07a915cea8cdb7e5c1c6659547bd6fce0adba4c8c2c9a13cc515de53",
  "repo_slug": "zoharbabin/google-researcher-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_zoharbabin_google_researcher_8965b151/readme"
}