mcp-retriever MCP server

mcp-retriever

One MCP server for web search, page extraction, and cited research. Use your own providers, combine their results, and keep API keys out of client configs.

and merge rankings with websearchfused.

• Search together: query two or three providers, deduplicate URLs,

from Wayback Machine snapshots when archive fallback is enabled.

• Read more: extract pages, crawl sites, and recover 404/410 pages

usage, cooldowns, and paged access to large results.

• Control usage: optional spending caps for provider-reported

Supports Tavily, Brave, Exa, You.com, SearXNG, GitHub, Linkup, Firecrawl, and Context.dev. Configure only what you use.

Quickstart

Requires Node.js 22+ and a provider key, or your own SearXNG instance.

npx -y mcp-retriever setup

Choose providers, save keys privately, and connect your MCP client. The wizard writes Claude Desktop and Cursor entries, or shows the command/configuration for Claude Code and Codex. Billable key checks require consent.

Keys are stored in ~/.config/mcp-retriever/credentials.env, not in client configs. Restart your client after setup.

Client connection and key management

Add, test, or remove keys:

npx mcp-retriever keys

Screenshots show a demo session with fixture credentials and a mocked key-check response, not a live provider validation.

Example

Call websearchfused with two configured search providers:

{
	"query": "reciprocal rank fusion hybrid search",
	"providers": ["brave", "exa"],
	"limit": 3
}

Results include source providers and merged rankings. If a provider fails, available results are returned with per-provider status.

Documentation

keys, manual client setup, providers, and spending controls.

• Configuration:

retrieving pages and handling large results.

• Search and read:

choose which capabilities to expose.

• Tool groups:

remote HTTP access and operations.

• Deployment:

build from source and run checks.

• Contributing:

Each server instance shares one trust boundary. Do not use its result store for mutually untrusted clients. Spending caps depend on provider-reported usage, not estimated costs.

License and origins

MIT. Formerly named mcp-omnisearch; a maintained fork of Scott Spence's mcp-omnisearch. When upgrading this fork, rename OMNISEARCH settings to RETRIEVER, omnisearch:// resources to retriever://, and meta.omnisearch to meta.retriever. Preserve the old result store and spending ledger when moving to ~/.cache/mcp-retriever/results; Docker/MCPO clients must also change /omnisearch to /retriever.