mcpField
F
fetchmux

fetchmux

Local
fetchmux.comSearch0Updated 14w ago

About fetchmux

fetchmux is a self-hosted retrieval router for AI agents that sends search requests to eligible providers under cost and latency limits. It returns normalized results with a route receipt explaining provider selection, attempts, and estimated cost.

Key features

  1. 01Routes requests across five retrieval providers
  2. 02Enforces cost ceilings and deadlines
  3. 03Retries on eligible failures
  4. 04Returns normalized results and route receipts
  5. 05Previews ranked provider candidates

Use cases

  1. 01Route agent web searches through one endpoint
  2. 02Keep provider costs within request budgets
  3. 03Inspect routing decisions and provider attempts

MCP support

An accompanying MCP server exposes the read-only tools `search_web` and `preview_search_route` to MCP clients. It connects to a FetchMux gateway using its base URL and API key.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"krutftw-fetchmux": {
"command": "npx",
"args": [
"-y",
"@fetchmux/mcp"
],
"env": {
"FETCHMUX_BASE_URL": "<FETCHMUX_BASE_URL>",
"FETCHMUX_API_KEY": "<FETCHMUX_API_KEY>"
}
}
}
}
Run commandnpx -y @fetchmux/mcp
Environment variables to set
FETCHMUX_BASE_URLBase URL of the self-hosted FetchMux gateway.
FETCHMUX_API_KEYSecretBearer key for the gateway's protected routes.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@fetchmux/mcp0.1.0

Tools

2

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
taskenumNobalanced | fresh_facts | deep_research | page_content | scholarly
limitintegerNo
querystringYes
countrystringNo
languagestringNo
priorityenumNobalanced | quality | cost | latency
freshnessenumNo24h | 7d | 30d | 1y
maxCostUsdnumberNo
fetchContentbooleanNo
maxLatencyMsintegerNo
excludeDomainsarrayNo
includeDomainsarrayNo
providerAllowlistarrayNo

Details

From the project README

FetchMux

npm License Node MCP

One search endpoint for AI agents. Put a router in front of Brave, Tavily, Exa, Firecrawl, and Crossref. Every request carries a hard cost ceiling and deadline; every response comes back with a receipt that says which provider ran, why, and what it cost.

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.

The receipt

Nothing is a black box. Every /v1/search response carries the routing decision:

"route": {
  "selectedProvider": "brave",
  "attemptedProviders": ["brave"],
  "reasonCodes": ["TASK_MATCH", "WITHIN_BUDGET", "RELIABILITY_WEIGHT"],
  "attempts": [
    { "provider": "brave", "outcome": "success", "latencyMs": 640, "estimatedCostUsd": 0.005 }
  ],
  "estimatedCostUsd": 0.005,
  "latencyMs": 640,
  "fallbackUsed": false,
  "traceId": "rt_b400e7c8"
}

How it routes

  agent  ──▶  { query · task · maxCostUsd · maxLatencyMs }
                             │
                             ▼
                      ┌──────────────┐        your keys
                      │   FetchMux    │ ─────▶ Brave · Tavily · Exa
                      │    policy     │        Firecrawl · Crossref
                      └──────────────┘ ◀─────  (bring your own)
                             │
                             ▼
  agent  ◀──  evidence[]  +  route receipt

A provider is eligible only when its credentials, task fit, circuit state, spend, and deadline all pass. Budgets and deadlines are eligibility rules, not best-effort hints. Fallback happens only on retryable failures.

Quick start

No provider account needed — the public Crossref route runs out of the box:

git clone https://github.com/krutftw/fetchmux
cd fetchmux
npm install
npm run build

export FETCHMUX_API_KEY="a-long-random-key"
export CROSSREF_ENABLED=true
export CROSSREF_CONTACT_EMAIL="[email protected]"
npm run dev:gateway

From another shell:

curl http://127.0.0.1:8787/v1/search \
  -H "Authorization: Bearer a-long-random-key" \
  -H "Content-Type: application/json" \
  -d '{ "query": "retrieval augmented generation", "task": "scholarly", "maxLatencyMs": 8000 }'

To route real web search, set a provider key and use a web task instead:

export FETCHMUX_API_KEY="a-long-random-key"
export BRAVE_API_KEY="your-brave-key"
export BRAVE_COST_PER_REQUEST_USD="0.005"   # from your provider plan
npm run dev:gateway

New to Firecrawl? New accounts get 10% off the first month through this link (referral — FetchMux earns a small commission, no extra cost to you).

Use it from an agent

Point any MCP client (Claude, Cursor, and friends) at the published server:

{
  "mcpServers": {
    "fetchmux": {
      "command": "npx",
      "args": ["-y", "@fetchmux/mcp"],
      "env": {
        "FETCHMUX_BASE_URL": "http://127.0.0.1:8787/",
        "FETCHMUX_API_KEY": "your-gateway-key"
      }
    }
  }
}

Two read-only tools: search_web and preview_search_route.

Or use the typed SDK, @fetchmux/sdk:

import { FetchMux } from "@fetchmux/sdk";

const client = new FetchMux({
  baseUrl: "http://127.0.0.1:8787/",
  apiKey: process.env.FETCHMUX_API_KEY,
  fetch: globalThis.fetch.bind(globalThis),
});

const res = await client.search({
  query: "latest stable Node.js release",
  task: "fresh_facts",
  maxCostUsd: 0.02,
});

Providers

Bring your own key for each. Set the matching *_API_KEY, plus an optional *_COST_PER_REQUEST_USD if you want dollar budgets enforced.

ProviderUseKey
Braveweb searchBRAVE_API_KEY
Tavilyweb search, researchTAVILY_API_KEY
Exaweb search, docsEXA_API_KEY
Firecrawlpage contentFIRECRAWL_API_KEY
Crossrefscholarly metadatanone (CROSSREF_ENABLED=true)

REST endpoints

MethodPathAuthBehavior
GET/healthpublicProcess health and version
GET/readypublicProvider readiness
GET/v1/providersbearerProvider configuration status
POST/v1/route/previewbearerRanked candidates, no provider call
POST/v1/searchbearerRouted retrieval and route receipt

Full contract: docs/openapi.yaml.

All configuration variables

The process does not auto-load .env in local Node development; set variables in the shell or a process manager. Docker Compose reads the ignored .env file.

VariableDefaultPurpose
FETCHMUX_API_KEYnoneProtected-route bearer key
FETCHMUX_API_KEYSnoneComma-separated keys for rotation
FETCHMUX_AUTH_DISABLEDfalseExact true bypasses auth (trusted local use only)
FETCHMUX_ALLOWED_ORIGINSnoneComma-separated browser origins; no CORS when empty
FETCHMUX_HOST127.0.0.1Bind address
FETCHMUX_PORT8787TCP port
BRAVE_API_KEY / TAVILY_API_KEY / EXA_API_KEY / FIRECRAWL_API_KEYnoneProvider credentials
CROSSREF_ENABLEDfalseExact true enables the credential-free scholarly route
CROSSREF_CONTACT_EMAILnoneMonitored contact for Crossref's polite pool
*_COST_PER_REQUEST_USDnonePer-provider cost estimates used by dollar budgets

See provider configuration before enabling maxCostUsd.

Run in Docker

cp .env.example .env    # add your keys, never commit it
docker compose up --build -d
curl http://127.0.0.1:8787/health

Non-root Distroless image: Linux capabilities dropped, read-only root filesystem, provider credentials passed only at container start.

Benchmark

Validate every case and provider pairing with no network calls or credits:

npm run benchmark -- --workload benchmarks/workloads/founding-v1.json --mode dry-run

Live mode needs provider keys and an explicit --confirm-live. Check each provider's terms before publishing results — see the benchmark methodology.

What it is (and isn't)

Open source, self-hosted, single-tenant, BYOK. Route events go to stdout as JSON and exclude your query text, keys, and result content by default. No database, no telemetry.

It is not a hosted service, a pooled-credit reseller, or a claim that these providers are interchangeable. Provider names are the adapters it ships with, not partnerships. A hosted version is on the roadmap — star the repo to follow.

Development

npm test          # 232 tests
npm run typecheck
npm run lint
npm run build
npm run dev:gateway
npm run dev:site

More docs: product design · local development · deployment · provider configuration · data handling · incident response

Security issues: [email protected].

License

Apache-2.0. Free to self-host, modify, and redistribute.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.