Guardian Search MCP

The web’s search layer for AI agents.

Search the public web through one structured interface. Guardian fans queries across multiple engines, isolates failures, deduplicates results, and returns agent-ready JSON instead of making your model drive a search page.

8 search verticals 6 default web engines MCP + JSON interfaces
search_shopping
{
  "query": "paper towels",
  "vertical": "shopping",
  "results": [
    {
      "rank": 1,
      "title": "Paper towels — 6 rolls",
      "host": "store.example",
      "price": "$18.49",
      "agent_capabilities": {
        "webmcp": {
          "supported": true,
          "tools": ["search_catalog", "update_cart"]
        }
      }
    }
  ],
  "meta": {
    "elapsed_ms": 812,
    "provider": "guardian_search"
  }
}
Built for agent runtimes
LokiAgent MCP Claude Codex Cursor Custom agents
Structured by default

Search results your model can use immediately.

Every response carries stable result fields, ranking, host information, intent metadata, engine diagnostics, pagination, and vertical-specific attributes such as price, publisher, image, or ticker data.

01

Search, not browser automation

Agents call a typed search tool instead of opening Google, Bing, or DuckDuckGo and trying to scrape a rendered results page.

02

Multi-engine resilience

Guardian fans queries out engine-by-engine, keeps successful upstreams when another fails, normalizes URLs, and merges rankings.

03

Commerce-aware discovery

Shopping search can annotate top merchant origins with WebMCP capability metadata, helping agents choose structured site tools before DOM clicking.

One contract

From low-latency lookup to richer vertical search.

Use one MCP endpoint for general web search, product discovery, destination discovery, and finance snapshots. The JSON API remains available for systems that do not speak MCP.

  • search_web — web, news, images, video, travel, discussions and more
  • search_shopping — products, prices, merchants and optional WebMCP enrichment
  • discover_sites — destination discovery deduplicated by host
  • finance_quote — current finance snapshot
Result object
{
  "rank": 1,
  "title": "...",
  "url": "https://...",
  "host": "example.com",
  "description": "...",
  "price": "$18.49",
  "engine": "google",
  "engines": ["google", "bing"],
  "score": 0.91
}
Developers

Connect in minutes.

Use the Streamable HTTP MCP endpoint directly, or call Guardian’s agent-search JSON API. No search-engine-specific scraping code required.

# Guardian Search ships connected by default in LokiAgent.
# Verify the remote MCP and its tools:
loki mcp test guardian_search

# Then start shopping mode:
loki chat
/go shopping
Operational control

Designed for production agent traffic.

Failure isolation

One upstream engine timing out does not discard the successful results returned by the rest of the pool.

Safe-search controls

Clients can select the Safe Search level per request and can pass region and language hints when needed.

Diagnostics included

Responses identify queried, successful, and failed engines plus elapsed time, making retrieval behavior observable to agent runtimes.

Agent-oriented discovery

OpenAPI, llms.txt, an agent manifest, OpenSearch metadata, the MCP endpoint, and the JSON API are all published from the same service.

Guardian Search MCP

Stop teaching agents how to use search pages.

Give them one typed search surface and let the browser do browser work only when it is actually needed.