ai_searchLABSCO SUMMARY
Search that already knows about your own documents.
One tool, and the interesting part sits behind it: because the query goes through Higress, the same call can reach the open web, Arxiv and an internal knowledge base without the client needing to know which is which.
What it is
A single-tool server that sends a query to Higress and returns an answer grounded in what the search brought back. Which engines are in play is set by your Higress ai-search configuration: Google, Bing and Quark for the web, Arxiv for papers, and your own internal knowledge bases.
What you get
- A question answered against live web results rather than against what the model remembers
- Academic search over Arxiv, for questions where the paper is the answer
- Internal knowledge bases searched alongside the public web, once Higress is configured for them
- The search engines and the answering model both chosen in your gateway configuration, not baked into the server
Requirements
A Higress instance with the ai-search and ai-proxy plugins configured and reachable from the machine running the server; the default address is a local one. You name the model the gateway should answer with, and describe your internal knowledge bases so the tool knows when they are worth reaching for. Installed with uv, or run from a local checkout.
Setup effort
Add the configuration to your client
USE CASES
01
Getting a current answer instead of a remembered one
The query goes out to live search first, so the answer is grounded in results rather than in training data.
02
Finding the paper behind a claim
With Arxiv in the search mix, a research question returns the source rather than a paraphrase of it.
03
Answering a question only your own documents can answer
Internal knowledge bases sit in the same call as the public web, so an employee handbook question does not need a different tool.
04
Keeping one interface as the engines behind it change
Swapping or adding a search backend is a gateway change; the tool your client calls stays the same.
1 tool
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool when we connected.
Requires
- uvx on PATH
- a Higress gateway with the ai-search and ai-proxy plugins configured
- MODEL in your environment
CONTEXT COST
Light Standing cost
Rated by the size of the one tool definition that rides along on every turn
INSTALLATION
Connect your client
This one is configured rather than run — your client needs the configuration block, not a command.
Server setup
JSON
{
"mcpServers": {
"higress-ai-search-mcp-server": {
"command": "uvx",
"args": [
"higress-ai-search-mcp-server"
],
"env": {
"HIGRESS_URL": "http://localhost:8080/v1/chat/completions",
"MODEL": "qwen-turbo",
"INTERNAL_KNOWLEDGE_BASES": "Employee handbook, company policies, internal process documents"
}
}
}
}
