web-retrieval-mcp server

<!-- mcp-name: io.github.VelvetSP/web-retrieval-mcp -->

web-retrieval-mcp — reliable MCP web search and web fetch for AI agents

An open-source Model Context Protocol (MCP) server for source-grounded web research. Connect Codex CLI and the Codex IDE extension, Claude Code, Claude Desktop, Cursor, ChatGPT desktop, or any other compatible MCP client to six read-only tools for Exa or Tavily search, resilient Exa → Camoufox → Tavily → Firecrawl page retrieval, AI/ML paper discovery, and developer-source search—with explicit provenance, optional local caching, and SSRF guards.

Why use it? · Quick start · Tools · Routing · Configuration · Security · FAQ

Why use web-retrieval-mcp?

Web research is more reliable when an agent can see where every result came from, choose the right retrieval strategy, and recover when one provider or page-access method fails. web-retrieval-mcp makes those controls part of the tool contract:

title, URL, highlights, and text, followed by a Sources trailer. Exa deep modes additionally return a clearly labeled synthesized answer, with grounding when Exa provides it, before the source-separated result blocks.

• Keep sources separate. Default search returns one block per result with its own

Firecrawl. Full-page fetches can escalate from indexed content to a local Camoufox browser, optional Tavily Extract, and Firecrawl.

• Use more than one retrieval path. Search can use Exa or Tavily and fall back to

cache state, semantic mode, and truncation instead of hiding the route.

• Know what actually served the answer. Fetch responses identify the serving tier,

grounded answer to a question. Control freshness, rendering, domains, dates, result count, and per-result text size.

• Ask for the right shape. Fetch a readable page body, a concise summary, or a

full-text passages, expand to related papers, and search developer documentation, READMEs, issues, and merged pull requests.

• Search specialist corpora. Discover AI/ML papers, inspect query-relevant

service; select providers and secret storage yourself; optionally cache completed fetches in a private Valkey sidecar.

• Own the deployment boundary. Run locally over stdio or host a loopback HTTP

unavailable credentials fail in the tool result. Tavily mappings, Firecrawl fallback filter gaps, and Exa category migrations are caller-visible; other Exa filter drops are written to server diagnostics.

• Fail explicitly. Unsupported provider choices, missing optional packages, and

How it compares with built-in agent web tools

Built-in capabilities vary by agent and can improve over time. The useful comparison is therefore not “all defaults are bad”; it is whether you need a portable, inspectable retrieval layer with controls your current client does not expose.

Shortened. The full README is on GitHub.