by kagisearch
Provides web search and video summarization capabilities via the Model Context Protocol, integrating with Claude and other AI tools.
Enables AI agents to perform real‑time web searches and generate summaries of URLs (including videos) through a standardized MCP interface. It connects Kagi's search and summarizer APIs with Claude Desktop, Claude Code, and any other client that supports MCP.
uv venv
.uv sync
.uvx kagimcp
and supplies KAGI_API_KEY
(and optionally KAGI_SUMMARIZER_ENGINE
).cecil
).FASTMCP_LOG_LEVEL
.Q: Do I need a Kagi account? A: Yes, access to the search API is in closed beta; request an invite via support@kagi.com.
Q: Which summarizer engines are supported?
A: Set KAGI_SUMMARIZER_ENGINE
to any engine listed in Kagi’s API docs (e.g., cecil
, daphne
). The default is cecil
.
Q: How do I disable Claude's built‑in web search to avoid conflicts?
A: Add a deny
entry for WebSearch
in Claude’s settings.json
permissions.
Q: Can I run the server on Windows?
A: Yes. Install UV using PowerShell, create the virtual environment, then activate .venv\Scripts\activate
before running uv sync
and uvx kagimcp
.
Q: Where can I see debugging information?
A: Run the inspector with npx @modelcontextprotocol/inspector uvx kagimcp
and open the web UI at http://localhost:5173
.
Before anything, unless you are just using non-search tools, ensure you have access to the search API. It is currently in closed beta and available upon request. Please reach out to support@kagi.com for an invite.
Install uv first.
MacOS/Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
Windows:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Alternatively, you can install Kagi for Claude Desktop via Smithery:
npx -y @smithery/cli install kagimcp --client claude
// claude_desktop_config.json
// Can find location through:
// Hamburger Menu -> File -> Settings -> Developer -> Edit Config
{
"mcpServers": {
"kagi": {
"command": "uvx",
"args": ["kagimcp"],
"env": {
"KAGI_API_KEY": "YOUR_API_KEY_HERE",
"KAGI_SUMMARIZER_ENGINE": "YOUR_ENGINE_CHOICE_HERE" // Defaults to "cecil" engine if env var not present
}
}
}
}
Add the Kagi mcp server with the following command (setting summarizer engine optional):
claude mcp add kagi -e KAGI_API_KEY="YOUR_API_KEY_HERE" KAGI_SUMMARIZER_ENGINE="YOUR_ENGINE_CHOICE_HERE" -- uvx kagimcp
Now claude code can use the Kagi mcp server. However, claude code comes with its own web search functionality by default, which may conflict with Kagi. You can disable claude's web search functionality with the following in your claude code settings file (~/.claude/settings.json
):
{
"permissions": {
"deny": [
"WebSearch"
]
}
}
e.g. "Who was time's 2024 person of the year?" for search, or "summarize this video: https://www.youtube.com/watch?v=jNQXAC9IVRw" for summarizer.
Run:
npx @modelcontextprotocol/inspector uvx kagimcp
git clone https://github.com/kagisearch/kagimcp.git
Install uv first.
MacOS/Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
Windows:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Then install MCP server dependencies:
cd kagimcp
# Create virtual environment and activate it
uv venv
source .venv/bin/activate # MacOS/Linux
# OR
.venv/Scripts/activate # Windows
# Install dependencies
uv sync
# `pip install mcp[cli]` if you haven't
mcp install /ABSOLUTE/PATH/TO/PARENT/FOLDER/kagimcp/src/kagimcp/server.py -v "KAGI_API_KEY=API_KEY_HERE"
# claude_desktop_config.json
# Can find location through:
# Hamburger Menu -> File -> Settings -> Developer -> Edit Config
{
"mcpServers": {
"kagi": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/kagimcp",
"run",
"kagimcp"
],
"env": {
"KAGI_API_KEY": "YOUR_API_KEY_HERE",
"KAGI_SUMMARIZER_ENGINE": "YOUR_ENGINE_CHOICE_HERE" // Defaults to "cecil" engine if env var not present
}
}
}
}
e.g. "Who was time's 2024 person of the year?" for search, or "summarize this video: https://www.youtube.com/watch?v=jNQXAC9IVRw" for summarizer.
Run:
# If mcp cli installed (`pip install mcp[cli]`)
mcp dev /ABSOLUTE/PATH/TO/PARENT/FOLDER/kagimcp/src/kagimcp/server.py
# If not
npx @modelcontextprotocol/inspector \
uv \
--directory /ABSOLUTE/PATH/TO/PARENT/FOLDER/kagimcp \
run \
kagimcp
Then access MCP Inspector at http://localhost:5173
. You may need to add your Kagi API key in the environment variables in the inspector under KAGI_API_KEY
.
FASTMCP_LOG_LEVEL
environment variable (e.g. FASTMCP_LOG_LEVEL="ERROR"
)
KAGI_SUMMARIZER_ENGINE
environment variable (e.g. KAGI_SUMMARIZER_ENGINE="daphne"
)
Please log in to share your review and rating for this MCP.
Discover more MCP servers with similar functionality and use cases
by exa-labs
Provides a Model Context Protocol server that enables AI assistants to perform real‑time web searches via the Exa AI Search API, with optional company research, LinkedIn lookup, and deep research workflows.
by perplexityai
Provides real-time web search capabilities to AI models via the Perplexity Sonar API, enabling seamless integration within the Model Context Protocol ecosystem.
by brightdata
Provides real‑time web access, bypasses geo‑restrictions, handles bot detection, and offers browser automation for LLMs and AI agents via the Model Context Protocol.
by mamertofabian
mcp-everything-search is a cross-platform MCP server that provides fast and flexible file searching capabilities. It leverages native system tools to efficiently locate files and folders across Windows, macOS, and Linux.
by apify
mcp-server-rag-web-browser is an MCP server for the RAG Web Browser Actor, enabling AI agents and LLMs to perform web searches and extract information from web pages.
by fatwang2
Provides web and news search, URL crawling, sitemap extraction, reasoning, and trending tools via Search1API, exposed as an MCP server for seamless integration with clients such as LibreChat, Claude Desktop, Cursor, and other MCP‑compatible tools.
by meilisearch
Enables LLMs to manage Meilisearch indexes, perform searches, and handle documents through natural‑language conversations via a Model Context Protocol server.
by ihor-sokoliuk
mcp-searxng is an MCP (Model Context Protocol) server that integrates with SearXNG to provide web search capabilities for AI models and applications.
by adityak74
mcp-scholarly is a MCP server designed to facilitate the search for accurate academic articles, initially supporting arXiv and with plans to integrate more scholarly vendors.