MCP web search + tiered web fetch for AI agents (Exa, Firecrawl), SSRF-guarded, cross-platform.
Web MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. MCP web search + tiered web fetch for AI agents (Exa, Firecrawl), SSRF-guarded, cross-platform.
An agent's stock WebSearch / WebFetch tend to flatten many sources into one blurry summary, drop provenance, and silently fail on JavaScript-heavy or anti-bot pages. This server fixes that:
Once Web is connected, these are the calls the assistant has available:
Safety — —Cost — Bundled / metered by your model vendorProvider — Free tier (verified 2026)Exa — 1,000 requests / month, no cardFirecrawl — 1,000 pages / month, no cardfetches on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
You will need 2 environment variables: EXA_API_KEY, FIRECRAWL_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Among the search and retrieval options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Web's toolset — Safety, Cost, Provider and 2 more — is a fair guide to whether it matches your workflow. It is maintained by VelvetSP; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Safety | — |
| Cost | Bundled / metered by your model vendor |
| Provider | Free tier (verified 2026) |
| Exa | **1,000 requests / month**, no card |
| Firecrawl | **1,000 pages / month**, no card |
{
"mcpServers": {
"web-retrieval": {
"command": "web-retrieval-mcp",
"env": {
"EXA_API_KEY": "exa-...",
"FIRECRAWL_API_KEY": "fc-..."
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| EXA_API_KEY | Credential the server authenticates with. | Yes |
| FIRECRAWL_API_KEY | Credential the server authenticates with. | Yes |
The simplest web tool that matters — fetch any URL and get model-ready markdown back.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.