GroundRoute
GroundRoute provides a single search tool that routes web search queries across multiple engines (Serper, Brave, Exa, Tavily, Firecrawl, and Perplexity), handling caching, failover, and cost optimization automatically.
Core capabilities:
Multi-engine routing — Automatically selects the best-value engine (cheapest that clears a quality bar) for each query, with automatic failover if an engine degrades.
Search modes — Supports
auto,web,news,academic,answer(AI-synthesized answer with citations), andpage(full page content via Firecrawl).Rich search parameters — Control query, max results (1–50), freshness (
fresh,semi,static), domain filters, language (ISO 639-1), and country (ISO 3166-1).Caching — Repeated queries are served from cache (exact_private, exact_pooled, or semantic) to reduce cost.
Structured results — Returns URL, title, snippet, full content (where available), publish date, and the source engine used.
Transparency metadata — Each response includes request ID, cache tier, degraded-path status, and exact billed cost in USD.
Integration — Connects via MCP (HTTP or stdio) to any compatible client (Claude, Cursor, VS Code, etc.), with support for bring-your-own-keys (BYOK) and self-hosting via Docker.
Routes search queries to the Brave search engine, providing web search results.
Routes search queries to the Perplexity AI search engine, providing web search and answer capabilities.
Give your AI agent web search across 6 engines through one MCP
searchtool. Hosted. Routed. Cached.
Why GroundRoute
One tool, six engines. Serper, Brave, Exa, Tavily, Firecrawl, Perplexity, behind a single
searchcall. Stop wiring up six APIs, six SDKs, six billing portals.Never more than going direct. Gain-share pricing: you keep ~half of every cache saving, GroundRoute keeps ~half. On a miss, you just pay the engine. BYOK supported.
Routing, caching, failover, on by default. Each query goes to the cheapest engine that clears a quality bar. Repeats serve from cache. If an engine degrades, we fall back automatically. No agent code changes.
Related MCP server: spectrawl
See it work (5 seconds)
A call to the search tool:
{
"name": "search",
"arguments": { "query": "what is RAGflow", "max_results": 3 }
}The response (trimmed):
{
"results": [
{
"url": "https://ragflow.io/docs/",
"title": "Quickstart - RAGFlow",
"snippet": "RAGFlow is an open-source RAG engine based on deep document understanding...",
"source_engine": "serper"
},
{
"url": "https://github.com/infiniflow/ragflow",
"title": "RAGFlow is a leading open-source Retrieval-Augmented Generation engine",
"snippet": "RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine...",
"source_engine": "serper"
}
],
"meta": {
"request_id": "req_abc123",
"cache_tier": "miss",
"degraded": false,
"cost_usd": 0.0021
}
}source_engine tells you which engine answered. meta exposes the cache tier and billed cost per call.
Benchmarked, not just shipped
We ran 170 real agent queries across all 6 engines, judged by an LLM, to map cost vs. quality per query class. Full methodology and per-engine results: State of AI Search.
Install
The hosted endpoint is https://api.groundroute.ai/mcp (streamable-HTTP). Get an API key at groundroute.ai/keys.
Claude Desktop / Claude Code, add to your MCP config:
{
"mcpServers": {
"groundroute": {
"type": "http",
"url": "https://api.groundroute.ai/mcp",
"headers": { "Authorization": "Bearer gr_YOUR_KEY" }
}
}
}Cursor, ~/.cursor/mcp.json:
{ "mcpServers": { "groundroute": { "url": "https://api.groundroute.ai/mcp",
"headers": { "Authorization": "Bearer gr_YOUR_KEY" } } } }VS Code (native MCP / Continue), .vscode/mcp.json:
{ "servers": { "groundroute": { "type": "http", "url": "https://api.groundroute.ai/mcp",
"headers": { "Authorization": "Bearer gr_YOUR_KEY" } } } }Local / stdio-only clients, bridge stdio to HTTP with mcp-remote:
{ "mcpServers": { "groundroute": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.groundroute.ai/mcp", "--header", "Authorization:Bearer gr_YOUR_KEY"]
} } }Run this repo's stdio server (optional)
This repo also ships a small native stdio MCP server (server.py) that forwards to the hosted API, useful for stdio-only clients or containerized runs.
pip install -r requirements.txt
GROUNDROUTE_API_KEY=gr_YOUR_KEY python server.pyOr with Docker:
docker build -t groundroute-mcp .
docker run -i -e GROUNDROUTE_API_KEY=gr_YOUR_KEY groundroute-mcpIntrospection (tool discovery) works with no key; running a search requires GROUNDROUTE_API_KEY (get one at https://groundroute.ai/keys).
The search tool
Param | Type | Notes |
| string | required |
| enum |
|
| integer | default 10, max 50 |
| enum |
|
| string[] | include-only domain filter, e.g. |
| string | ISO 639-1 language code, e.g. |
| string | ISO 3166-1 alpha-2 country code, e.g. |
Returns a structured result: ranked results (url / title / snippet / content / source_engine / published_at), an optional synthesized answer with citations (answer mode), and meta (request_id / cache_tier / degraded / cost_usd). Routed, cached, and reliable.
How it works
One endpoint in front of many search engines, with price-led routing, caching, failover, and usage governance. See the docs and the State of AI Search benchmark (170 real agent queries across all 6 engines).
Links
Homepage: https://groundroute.ai
Get a key: https://groundroute.ai/keys
Playground (try without installing): https://groundroute.ai/playground
registry-manifest.json in this repo is the listing manifest for MCP registries.
Maintenance
Tools
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/PROJECT-B-26/groundroute-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server