searxng-mcp

An MCP server for private web search via a self-hosted SearXNG instance. SearXNG is the only requirement; everything else is optional and layers on top — a local ML model reranks results, a three-tier cascade (Firecrawl, Crawl4AI, in-process raw fetch) retrieves full-page content, and an Ollama instance provides query expansion and LLM-synthesized summaries.

Designed for use with Claude Code and LibreChat agents that need web search without sending queries to a third-party search API.

Built with Claude Code using the multi-agent workflow from homelab-agent — the same platform that uses searxng-mcp in production for AI-assisted research.

Quick Start

A running SearXNG instance is the only requirement. Everything else is optional and improves a specific dimension — see Prerequisites.

SearXNG only — nothing else deployed:

SEARXNG_URL=http://localhost:8081 \
  FIRECRAWL_ENABLED=false CACHE_URL= RERANKER_URL= \
  npx @tadmstr/searxng-mcp

What works in this configuration: search returns ranked results, and fetch_url / search_and_fetch return extracted page content via tier 3 (raw HTTP fetch + Readability, wholly in-process). What does not: semantic reranking (results keep SearXNG's ordering), query expansion and search_and_summarize (no LLM), caching (every call is live), JS-heavy page rendering, and offline serving.

The startup capability line reports three states per capability, not two: on (self-contained — nothing remote has to work for it to be true), unverified (configured, but this process has never contacted the backend), and off (not configured). Nothing probes at startup, so unverified is not a health failure — it's the honest absence of a health claim, not an error. The command above prints exactly this:

capabilities on=tier3 unverified=none off=tier1,tier2,cache,reranker,llm,kiwix,hister,solver,wayback,otel,nats

tier3 is the only thing on, because it is the only capability that is true without anything remote working. wayback is off until you set WAYBACK_ENABLED=true — it is a feature flag, not a default.

The three overrides are what make it a clean minimal run rather than merely a working one. FIRECRAWL_URL, CACHE_URL and RERANKER_URL all have non-empty defaults, so left alone the server spends the whole run talking to services that were never deployed — every fetch first attempts a Firecrawl that is not there and books the failure into the domain capability database, which then routes around a tier that was never broken, only absent.

FIRECRAWL_ENABLED=false is a real kill switch. CACHE_URL and RERANKER_URL have none, so the lever is an empty string.

The compose ladder

Four compose files in examples/, each a strict superset of the one above it. Start at the rung that matches what you are willing to run; every rung's header comment states what works, what does not, and which environment variable moves you up.

Rung 2 is the recommended starting point — the cache is the single largest latency win, and Crawl4AI gets you JavaScript rendering for one container instead of Firecrawl's three.

cd examples
export SEARXNG_SECRET=$(openssl rand -hex 32)
docker compose -f compose.crawl4ai.yml up -d

Moving up a rung is docker compose -f compose.<next>.yml up -d — all four share a compose project name, so compose reconciles in place rather than starting a second copy of what you already had.

As a container — published to GHCR on every release:

docker pull ghcr.io/tadmstr/searxng-mcp:latest

Tags, uid, and provenance verification: Deployment.

The reranker ships in this repo — cd docker/reranker && docker compose up, or pull ghcr.io/tadmstr/searxng-mcp-reranker. It is CPU-only, needs no API key, and has the model baked in so there is no cold start. See docker/reranker/README.md.

Two adblocking sidecars are also published as images, one per fetch-tier group:

• ghcr.io/tadmstr/searxng-mcp-adblock-proxy — ad/tracker filtering for tiers 2 and 3. It is an open forward proxy with no authentication, so loopback or a private network only — see docker/adblock-proxy/README.md for placement. Its filter lists are fetched at runtime, from ADBLOCK_FILTERS_URL (defaulted to EasyList + EasyPrivacy) and reloaded on a schedule — the opposite approach from the playwright sidecar below, deliberately: only that image sits in front of an SSRF guard.

• ghcr.io/tadmstr/searxng-mcp-playwright-adblock — EasyList/EasyPrivacy filtering for Firecrawl v2's renderer (tier 1). This is an upgrade of upstream's existing AD_SERVING_DOMAINS token list, not a new capability — that list still applies underneath. It targets the v2 renderer only; docker/puppeteer-adblock/ covers v1 and does nothing on a v2 deployment. Note FIRECRAWL_API_VERSION defaults to v1 in src/config.ts, so a stack wiring the playwright sidecar must set it to v2 explicitly or tier-1 adblocking silently does nothing — examples/compose.full.yml sets it and says why. Its filter lists are vendored at build time (docker/playwright-adblock/lists/, checksum-verified against SHA256SUMS during the build) rather than downloaded from easylist.to, so the build no longer depends on that host being reachable. Refresh with node docker/playwright-adblock/fetch-lists.mjs, or let the weekly adblock-lists-refresh.yml workflow do it — it opens a PR that carries no CI checks (GitHub does not trigger workflows for a PR opened with GITHUB_TOKEN), so review the workflow run itself rather than looking for a green check; it verifies the lists before opening the PR. ADBLOCK_FILTERS_URL still exists on this image too, as an opt-in runtime override — unset by default, so the vendored lists are what ships. See docker/playwright-adblock/README.md.

For a full local topology including Firecrawl, Crawl4AI, Ollama, Kiwix, the adblock proxy, and NATS, see rung 4 of the ladder above — examples/compose.full.yml.

Related MCP server: searxng-mcp-bridge

Why searxng-mcp?

There are a number of SearXNG MCP servers. Most wrap the search endpoint and stop there. The differentiators here are in what happens after the search:

Only SearXNG is required. Everything in the table above degrades gracefully: with nothing else deployed, fetch_url still returns extracted content from the in-process tier 3, and the startup capability line tells you exactly what's configured, what's configured but not yet verified, and what's off — see Quick Start above.

Tools

Full parameter reference: docs/tools.md.

Resources

Two read-only MCP Resources, additive to the tools above.

config://searxng-mcp never includes a credential value. Secrets are reported as a boolean — configured or not — and every URL is stripped of inline userinfo before it is emitted, because Basic Auth in SEARXNG_URL and an inline password in CACHE_URL are both supported. The payload is built from an allowlist rather than by dumping config and removing known secrets, so a newly-added field cannot leak by default.

If you're behind an MCP proxy rather than talking to this server directly, verify it forwards resources/*. Many proxies re-register upstream tools on their own server instead of forwarding the wire protocol generically, and drop Resources silently as a result — the tools still work, only the Resources go missing. See Deployment for a worked example of checking this.

Architecture

The fetch cascade, in full. Each stage is optional and skipped cleanly when unconfigured.

The llms.txt fast path (llms → llms_fetch below) matches against the host currently allowlisted in domains.json — platform.claude.com — and extracts each page's section from the document's url: front-matter (lowercase, YAML-style).

flowchart TD
    entry["fetchPage(url)"]
    cache{"Valkey cache hit?"}
    cached["→ return cached { title, url, text }"]
    github{"GitHub host?\ngithub.com · raw · api"}
    gh_fetch["GitHub API / raw.githubusercontent.com / api.github.com\n→ return"]
    llms{"llms.txt domain?"}
    llms_fetch["Probe /llms-full.txt\nextract matching section\n→ return"]
    kiwix{"Kiwix host?\nKIWIX_URL set"}
    kiwix_fetch["Local Kiwix ZIM\nWikipedia · Stack Overflow · Arch Wiki\n→ cache + return"]
    robots["robots.txt pre-check — tiers 1–3\ndisallowed → RobotsDisallowedError (cached 24h)"]
    tier_skip(["Per-domain tier skip\nsuccess rate <30% over ≥10 tries\nor tier_skip operator override"])
    t1["Tier 1 — Firecrawl\n$FIRECRAWL_URL\nserves PDFs under FIRECRAWL_API_VERSION=v2"]
    t2["Tier 2 — Crawl4AI\n$CRAWL4AI_URL · optional\ndirect — no adblock proxy"]
    t3["Tier 3 — Raw HTTP + Readability\nfallback: raw HTML slice\nadblock proxy if $ADBLOCK_PROXY_URL"]
    challenge(["Challenge detected\non this URL, this request?"])
    solver["Solver — Byparr\n$SOLVER_URL · opt-in, SOLVER_ENABLED=true\nSSRF-guarded replay"]
    t4["Tier 4 — Wayback Machine CDX API\narchived snapshot · WAYBACK_ENABLED=true"]
    post["Post-extraction\nJSON-LD Article · title cascade\nog:title → twitter:title → title → h1 → URL"]
    result["→ return { title, url, text }"]

    entry --> cache
    cache -->|hit| cached
    cache -->|miss| github
    github -->|yes| gh_fetch
    github -->|no| llms
    llms -->|yes| llms_fetch
    llms -->|no| kiwix
    kiwix -->|yes| kiwix_fetch
    kiwix -->|no| robots
    robots --> tier_skip
    tier_skip --> t1
    t1 -->|success| post
    t1 -->|"empty / error"| t2
    t2 -->|success| post
    t2 -->|"empty / error"| t3
    t3 -->|success| post
    t3 -->|"empty / error"| challenge
    challenge -->|"yes, SOLVER_ENABLED"| solver
    challenge -->|no| t4
    solver -->|success| post
    solver -->|"miss / disabled"| t4
    t4 -->|success| result
    post --> result

    style entry fill:#ffffff,stroke:#333333,color:#000000
    style cache fill:#ffffff,stroke:#333333,color:#000000
    style cached fill:#ffffff,stroke:#333333,color:#000000
    style github fill:#dae8fc,stroke:#6c8ebf,color:#000000
    style gh_fetch fill:#dae8fc,stroke:#6c8ebf,color:#000000
    style llms fill:#dae8fc,stroke:#6c8ebf,color:#000000
    style llms_fetch fill:#dae8fc,stroke:#6c8ebf,color:#000000
    style kiwix fill:#fff9c4,stroke:#b8860b,color:#000000
    style kiwix_fetch fill:#fff9c4,stroke:#b8860b,color:#000000
    style robots fill:#ffffff,stroke:#333333,color:#000000
    style tier_skip fill:#f5f5f5,stroke:#666666,color:#000000
    style t1 fill:#d5e8d4,stroke:#5a8a4a,color:#000000
    style t2 fill:#d5e8d4,stroke:#5a8a4a,color:#000000
    style t3 fill:#d5e8d4,stroke:#5a8a4a,color:#000000
    style challenge fill:#f5f5f5,stroke:#666666,color:#000000
    style solver fill:#d5e8d4,stroke:#5a8a4a,color:#000000
    style t4 fill:#f8cecc,stroke:#a03030,color:#000000
    style post fill:#e1d5e7,stroke:#7a5a8a,color:#000000
    style result fill:#ffffff,stroke:#333333,color:#000000

Read the rest — tier semantics, the domain capability database, adblocking, every fast path, resilience and observability — in docs/architecture.md.

Documentation

Index: docs/index.md.

Contributing

See CONTRIBUTING.md for setup instructions, commit conventions, and the PR process.

Integration tests

A real-Valkey integration suite covering domain-DB concurrency is gated on VALKEY_TEST_URL and skipped entirely when it's unset, so a plain pnpm test still works with no Valkey present:

VALKEY_TEST_URL=redis://:<password>@<host>:<port>/<scratch-db> pnpm test

Use a scratch database index — the suite writes and deletes domain:* keys and refuses to run against index 0 or 1 as a safety guard.

License

MIT