Tavily MCP vs Web Retrieval MCP
A side-by-side look at the Tavily MCP and Web Retrieval MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Tavily MCP for search & data extraction work over a hosted endpoint; choose Web Retrieval MCP for search & data extraction as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Tavily MCP when
- You need dedicated capabilities in the Search & Data Extraction domain.
- You prefer a remote HTTP/SSE transport.
- You have the keys it needs:
TAVILY_API_KEY.
Choose Web Retrieval MCP when
- You need dedicated capabilities in the Search & Data Extraction domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
EXA_API_KEY, FIRECRAWL_API_KEY, TAVILY_API_KEY. - You want tools like
web_search, web_fetch.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Search & Data Extraction | Search & Data Extraction |
| Quality signal | 41/100 · Fair | 53/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Local subprocess (stdio) |
| Auth | Not declared | API key required |
| Pricing | Not declared | BYOK (pay the provider) |
| Required env vars | TAVILY_API_KEY | EXA_API_KEYFIRECRAWL_API_KEYTAVILY_API_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 2,440 | 2 |
| Directory activity | 2 views 0 installs 0 upvotes | 4 views 0 installs 0 upvotes |
| Tools | Not listed | 2 |
| Full listing | View Tavily MCP | View Web Retrieval MCP |
Tools & capabilities
Tavily MCP tools
No tool names declared yet. Check the project README from the listing page.
Web Retrieval MCP tools 2
web_searchNeural web search via Exa. One block per result — each with its own title, URL, published date, highlights, and text — plus a `Sources` list. `mode` ∈ `auto` \web_fetchOne URL's readable content through the tier chain, with a `[served by: …]` provenance header.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Tavily MCP
{
"mcpServers": {
"tavily-mcp": {
"url": "https://mcp.tavily.com/mcp"
}
}
}
Web Retrieval MCP
{
"mcpServers": {
"web-retrieval-mcp": {
"command": "uvx",
"args": [
"web-retrieval-mcp"
],
"env": {
"EXA_API_KEY": "YOUR_EXA_API_KEY_HERE",
"FIRECRAWL_API_KEY": "YOUR_FIRECRAWL_API_KEY_HERE",
"TAVILY_API_KEY": "YOUR_TAVILY_API_KEY_HERE"
}
}
}
}
Frequently asked questions
Tavily MCP is categorized under Search & Data Extraction and uses a remote HTTP/SSE transport. Web Retrieval MCP belongs to Search & Data Extraction and uses a local stdio subprocess. Pick Tavily MCP for search & data extraction work and Web Retrieval MCP for search & data extraction.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Tavily MCP has no declared pricing — check the project's own site. Web Retrieval MCP is bring-your-own-key: usage is billed by the API provider you supply a key for. Auth: api key required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add tavily-mcp and web-retrieval-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Tavily MCP has a quality signal of 41/100 (Fair) with 2 views, 0 installs and 2,440 GitHub stars. Web Retrieval MCP has 53/100 (Good) with 4 views, 0 installs and 2 GitHub stars.