Self-hosted retrieval router for AI agents: budgets, provider routing, route receipts.
Connect Fetchmux to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Self-hosted retrieval router for AI agents: budgets, provider routing, route receipts. The fetchmux mcp server is what makes that connection.
Your agents stop hard-coding a provider into prompts and app code. They send one request shape; the gateway picks an eligible provider under a policy you control, enforces the budget and deadline before the call, retries safely on failure, and returns normalized results plus a full trace. You keep your provider keys — they never leave your gateway.
Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Provider — UseBrave — web searchTavily — web search, researchExa — web search, docsFirecrawl — page contentCrossref — scholarly metadataMethod — PathGET — /healthPOST — /v1/route/previewVariable — DefaultFETCHMUX_API_KEY — noneFETCHMUX_API_KEYS — noneConfiguration is passed through the environment: FETCHMUX_BASE_URL, FETCHMUX_API_KEY, CROSSREF_ENABLED, CROSSREF_CONTACT_EMAIL, BRAVE_API_KEY, BRAVE_COST_PER_REQUEST_USD, TAVILY_API_KEY, EXA_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
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. Fetchmux's toolset — Provider, Brave, Tavily and 11 more — is a fair guide to whether it matches your workflow. It is maintained by krutftw; 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 |
|---|---|
| Provider | Use |
| Brave | web search |
| Tavily | web search, research |
| Exa | web search, docs |
| Firecrawl | page content |
| Crossref | scholarly metadata |
| Method | Path |
| GET | /health |
| POST | /v1/route/preview |
| Variable | Default |
| FETCHMUX_API_KEY | none |
| FETCHMUX_API_KEYS | none |
| FETCHMUX_AUTH_DISABLED | false |
| FETCHMUX_ALLOWED_ORIGINS | none |
{
"mcpServers": {
"fetchmux": {
"command": "npx",
"args": ["-y", "npm"],
"env": {
"FETCHMUX_BASE_URL": "your-value",
"FETCHMUX_API_KEY": "your-value",
"CROSSREF_ENABLED": "your-value",
"CROSSREF_CONTACT_EMAIL": "your-value",
"BRAVE_API_KEY": "your-value",
"BRAVE_COST_PER_REQUEST_USD": "your-value",
"TAVILY_API_KEY": "your-value",
"EXA_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| FETCHMUX_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| FETCHMUX_API_KEY | Credential the server authenticates with. | Yes |
| CROSSREF_ENABLED | Configuration value read at startup. | Optional |
| CROSSREF_CONTACT_EMAIL | Configuration value read at startup. | Optional |
| BRAVE_API_KEY | Credential the server authenticates with. | Yes |
| BRAVE_COST_PER_REQUEST_USD | Configuration value read at startup. | Optional |
| TAVILY_API_KEY | Credential the server authenticates with. | Yes |
| EXA_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.