Data · Local MCP server

web-retrieval-mcp

MCP web search + tiered web fetch for AI agents (Exa, Firecrawl), SSRF-guarded, cross-platform.

Visit web-retrieval-mcp's website

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.VelvetSP/web-retrieval-mcp
Version
0.1.2
Status
Active
Category
data
Transport
stdio (local process)
Package
PyPI
Published
2026-06-02
Updated
2026-06-02
Publisher
VelvetSP (GitHub)
Listed under
Firecrawl MCP servers
Website
github.com/VelvetSP/web-retrieval-mcp
Repository
github.com/VelvetSP/web-retrieval-mcp
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPIweb-retrieval-mcp0.1.2stdioEXA_API_KEY (required, secret), FIRECRAWL_API_KEY (required, secret)

How to connect web-retrieval-mcp

web-retrieval-mcp runs locally from a Python package published to PyPI: web-retrieval-mcp version 0.1.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx web-retrieval-mcp. It reads these environment variables: EXA_API_KEY (required, secret) and FIRECRAWL_API_KEY (required, secret); set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "web-retrieval-mcp": {
      "command": "uvx",
      "args": [
        "web-retrieval-mcp"
      ],
      "env": {
        "EXA_API_KEY": "<secret>",
        "FIRECRAWL_API_KEY": "<secret>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More data servers

All 4,395 →
ServerRunsEndpoint or package
Web Search & Data APIWeb search, scraping, Google Trends and data lookups. Paid per call in USDC on Base via x402.Remote · HTTPapi.kadec0.xyz
Web Search APIWeb search returning structured results — titles, URLs, snippets. x402 micropayment.Remote · SSEweb-search.api.klymax402.com
Web Search API for all your agents and LLMsLive web search, image search, topic filters and full-text fetch over our own crawled index.Remote · HTTPmcp.blopus.ai
Web Validator by DigestSEOAudit public webpages and supplied markup for HTML, CSS, SEO, JSON-LD, and link issues.Remote & Local · HTTP, stdioweb-validator-mcp.digestseo.com
webfetchSelf-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching.Local · stdioPyPI: webfetch-llm
WebhoundBudgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness.Remote & Local · HTTP, stdioapi.webhound.ai
WebLensScrape, crawl, map and extract the web. Pay per call in USDC, no account or API key.Remote · HTTPapi.weblens.dev
WebMCP TodayYour agent gets trustworthy tools on sites without WebMCP — data-only packages you approve.Local · stdionpm: @webmcp-today/mcp-bridge