Install Gangtise Ultra

Pick your client, copy the command, done.

Manual setup required. The maintainer's config contains paths only you know — edit the placeholders below before adding it to Claude Code.

Run this once before adding it to Claude Code.

pip install -e .

claude mcp add gangtise-ultra -- python /path/to/gangtise_ultra/main.py

Replace any placeholder paths in the command with the real path on your machine.

Environment Variables

Set these before running Gangtise Ultra.

VariableDescriptionRequired

GANGTISE_API_KEYDirectly used accessToken for API authentication.No

GANGTISE_ACCESS_KEYAccess key for token generation.No

GANGTISE_SECRET_KEYSecret access key for token generation.No

FASTMCP_PORTServer port for the MCP service.No

Once configured, Gangtise Ultra gives your AI agent access to:

search_knowledgeKnowledge base search with support for resource types and time range filtering.

queryresource_typestime_rangetop

batch_searchPerform batch searches for multiple queries at once.

queriesresource_typestop

get_resource_typesRetrieve all supported resource types.

After setup, try these prompts with your AI agent:

→Search for the latest broker research reports on BYD from the last month.

→Perform a batch search for recent market sentiment on BYD, CATL, and Tesla.

→Generate a daily briefing for the new energy vehicle industry focusing on BYD.

→Summarize the latest company notices for the technology sector from the past week.

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Python 3.8+ with pip installed

Alternative installation methods

pm2 start ecosystem.config.js

Save the docs, env vars, and workflow around Gangtise Ultra in Conare so Claude Code, Codex, and Cursor remember it next time.