Install Kimi Coding Search

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 -r requirements.txt
python server.py --transport streamable-http --host 0.0.0.0 --port 8000

claude mcp add --transport http -H "X-Kimi-Api-Key: sk-kimi-your-key" kimi-coding-search https://kimi-mcp.example.com/mcp

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

Required:KIMI_API_KEY+ 2 optional

Environment Variables

Set these before running Kimi Coding Search.

VariableDescriptionRequired

KIMI_API_KEYThe API key for accessing Kimi services.Yes

KIMI_BASE_URLThe base URL for the Kimi Coding API.No

MCP_PORTThe port for the MCP server to listen on.No

Once configured, Kimi Coding Search gives your AI agent access to:

kimi_searchPerforms a web search using the Kimi Coding Search API.

text_querylimitenable_page_crawlingtimeout_seconds

kimi_fetchFetches content from a specific URL using the Kimi Coding Fetch API.

url

After setup, try these prompts with your AI agent:

→Search for the latest updates on the Kimi Coding API documentation.

→Fetch the content from this URL: https://example.com/article and summarize it.

→Find recent news about AI development in 2025 using Kimi search.

→Search for technical tutorials on building MCP servers.

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Python 3.8+ with pip installed
Docker installed and running
KIMI_API_KEY — The API key for accessing Kimi services.

Alternative installation methods

pip install -r requirements.txt && python server.py --transport streamable-http --host 0.0.0.0 --port 8000

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