web-retrieval-mcp — Claude Code MCP server guide
Provides agents with six read-only tools for search and multi-tier page extraction using Exa and Firecrawl. Built-in SSRF guards protect local network environments.
claude mcp add web-retrieval-mcp -e EXA_API_KEY=<EXA_API_KEY> -e FIRECRAWL_API_KEY=<FIRECRAWL_API_KEY> -- uvx web-retrieval-mcpWhat web-retrieval-mcp does
This server connects agents to six read-only tools designed for web lookups and AI research papers. Web searches run primarily through Exa or Tavily, with automatic routing to Firecrawl when issues occur. Page retrieval uses a staged fallback path: it inspects cached content first, spins up a local Camoufox instance if needed, and escalates to Tavily Extract or Firecrawl.
Every retrieval response details the serving tier and cache status. The process blocks requests targeting private network ranges through SSRF filters on initial URLs and browser redirects. You need Python 3.10 or newer. Without running camoufox fetch after installing browser extras, local page rendering will fail.
What it helps with
- Search machine learning publications with query-focused text extracts
- Inspect developer documentation, merged pull requests, and GitHub issues
- Retrieve blocked web pages through multi-tier extraction fallbacks
- Guard agent web queries against internal network SSRF vectors
Example prompts for the agent
- Find recent research papers on mixture of experts and extract citations
- Retrieve the full text from this documentation page and summarize its API
- Search closed pull requests in the project repository for related bugfixes
How to install web-retrieval-mcp
Platform CLI
claude mcp add web-retrieval-mcp -e EXA_API_KEY=<EXA_API_KEY> -e FIRECRAWL_API_KEY=<FIRECRAWL_API_KEY> -- uvx web-retrieval-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from web-retrieval-mcp <command>
Platform CLI
codex mcp add web-retrieval-mcp --env EXA_API_KEY=<EXA_API_KEY> --env FIRECRAWL_API_KEY=<FIRECRAWL_API_KEY> -- uvx web-retrieval-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from web-retrieval-mcp <command>
Config file
{
"mcpServers": {
"web-retrieval-mcp": {
"command": "uvx",
"args": [
"web-retrieval-mcp"
],
"env": {
"EXA_API_KEY": "<EXA_API_KEY>",
"FIRECRAWL_API_KEY": "<FIRECRAWL_API_KEY>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from web-retrieval-mcp <command>
Config file
{
"servers": {
"web-retrieval-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"web-retrieval-mcp"
],
"env": {
"EXA_API_KEY": "<EXA_API_KEY>",
"FIRECRAWL_API_KEY": "<FIRECRAWL_API_KEY>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from web-retrieval-mcp <command>
Platform CLI
gemini mcp add -e EXA_API_KEY=<EXA_API_KEY> -e FIRECRAWL_API_KEY=<FIRECRAWL_API_KEY> web-retrieval-mcp uvx web-retrieval-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from web-retrieval-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about web-retrieval-mcp
How do I install web-retrieval-mcp in Claude Code?
Run claude mcp add web-retrieval-mcp -e EXA_API_KEY=<EXA_API_KEY> -e FIRECRAWL_API_KEY=<FIRECRAWL_API_KEY> -- uvx web-retrieval-mcp. Insert your provider tokens directly into the command flags.
What does web-retrieval-mcp do?
It provides six tools for web search, research paper discovery, and tiered page scraping with transparent source attribution.
What are the prerequisites for web-retrieval-mcp?
The package requires Python 3.10 or newer. To enable local browser rendering, install the render extra and download the managed browser using camoufox fetch.
