Kagi Search

Official

by kagisearch

197 742 downloads Not rated yet MIT

GitHub Website

About

Integrates Kagi's advanced search capabilities into workflows, enabling high-quality, privacy-focused web information retrieval for informed decision-making and analysis.

Details

Repository: kagisearch/kagimcp
License: MIT

Explore

- Web, news, video, podcast, and image search with filters and lenses.
- Full page extraction returning content as markdown.
- Hosted HTTP server available at https://mcp.kagi.com/mcp — no install required.
- Self‑hostable via the provided Dockerfile, supporting multi‑tenant HTTP mode.
- Configurable timeouts, retries, and hidden parameters for LLM‑facing schemas.
- Supports multiple MCP clients: Claude Desktop, Claude Code, Codex CLI, Smithery, Kiro, OpenCode.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name Kagi Search

Command (node, npx, python, etc.) uvx
Arguments
- Argument 1 kagimcp
Environment
- KAGI_API_KEY YOUR_API_KEY_HERE
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

JSON

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

From the repository

Use the hosted server at https://mcp.kagi.com/mcp with any HTTP‑capable MCP client, authenticating with your Kagi API key via a Bearer token. Alternatively, install the server locally using uvx kagimcp after setting the KAGI_API_KEY environment variable. Configuration options include search/extract timeouts, retry count, and hidden search parameters.

`kagi_search_fetch`

Perform web, news, videos, podcasts, and image searches with optional page extracts, filters, and Kagi lenses.

`kagi_extract`

Fetch a page's full content as markdown.

- kagi_search_fetch - web, news, videos, podcasts, and image search with optional page extracts, filters, and Kagi lenses.
- kagi_extract - fetch a page's full content as markdown.

> Note: The previous kagi_fastgpt and kagi_summarizer tools have been removed. Both are planned to return in a future release.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "kagi search": {
            "env": {
                "KAGI_API_KEY": "YOUR_API_KEY_HERE"
            },
            "args": [
                "kagimcp"
            ],
            "command": "uvx"
        }
    }
}

Linux

{
    "env": {
        "KAGI_API_KEY": "YOUR_API_KEY_HERE"
    },
    "args": [
        "kagimcp"
    ],
    "command": "uvx"
}

Macos

{
    "env": {
        "KAGI_API_KEY": "YOUR_API_KEY_HERE"
    },
    "args": [
        "kagimcp"
    ],
    "command": "uvx"
}

Windows

{
    "env": {
        "KAGI_API_KEY": "YOUR_API_KEY_HERE"
    },
    "args": [
        "kagimcp"
    ],
    "command": "uvx"
}

- Search the web with Kagi— ask for web, news, video, podcast, or image results with optional page extracts and filters viakagi_search_fetch.
- Extract page content as markdown— get the full cleaned content of any URL usingkagi_extract.
- Apply Kagi lenses to searches— narrow results by domain, file type, or time range using the lens and filter parameters onkagi_search_fetch.

An MCP server backed by theKagi API. It exposes search and extraction tools to MCP-compatible clients.

- kagi_search_fetch- web, news, videos, podcasts, and image search with optional page extracts, filters, and Kagi lenses.
- kagi_extract- fetch a page's full content as markdown.

Note:The previouskagi_fastgptandkagi_summarizertools have been removed. Both are planned to return in a future release.

We run a hosted MCP server athttps://mcp.kagi.com/mcp— no install required. Point any HTTP-capable MCP client at it and authenticate with your Kagi API key.

OAuth2 isn't supported yet (it's on our roadmap), so for now grab your API key from the dashboardand pass it viaBearerHTTP authentication.

claude mcp add kagi https://mcp.kagi.com/mcp --transport http --header "Authorization: Bearer $(read -sp 'API key: ' k; echo $k)" --scope user

Prefer to run it yourself? See Client Setupfor the localuvxinstall, or Self-Hostingto host the HTTP server on your own infrastructure.

- A Kagi API key inKAGI_API_KEY.
- uvfor the recommendeduvxinstall path.

curl -LsSf https://astral.sh/uv/install.sh | sh

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

codex mcp add kagi --env KAGI_API_KEY=<YOUR_API_KEY_HERE> -- uvx kagimcp

Codex writes MCP configuration to~/.codex/config.toml.

curl -LsSf https://astral.sh/uv/install.sh | sh

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Then in your Claude Desktop config (found through Settings -> Developer -> Edit Config):

{ "mcpServers": { "kagi": { "command": "uvx", "args": ["kagimcp"], "env": { "KAGI_API_KEY": "YOUR_API_KEY_HERE" } } } }

claude mcp add kagi -e KAGI_API_KEY="YOUR_API_KEY_HERE" -- uvx kagimcp

npx -y @smithery/cli install kagimcp --client claude

Add to your Kiro MCP config file (~/.kiro/settings/mcp.jsonfor global, or.kiro/settings/mcp.jsonfor project-scoped) using the samemcpServersJSON asClaude Desktop. See the Kiro MCP documentationfor more details.

Edit the OpenCode configuration file in~/.config/opencode/opencode.jsonand add the following:

{ "mcp": { "kagi": { "type": "local", "command": ["uvx", "kagimcp"], "enabled": true, "environment": { "KAGI_API_KEY": "<YOUR_API_KEY_HERE>" } } } }

- Search:Who was Time's 2024 person of the year?
- Extract:extract the full content of https://en.wikipedia.org/wiki/Model_Context_Protocol

workflow, extract_count, limit, include_domains, exclude_domains, time_relative, after, before, file_type, lens_id

KAGI_HIDDEN_PARAMS="extract_count,after,before,time_relative,include_domains,exclude_domains"

git clone https://github.com/kagisearch/kagimcp.git cd kagimcp uv sync

KAGI_API_KEY=<YOUR_API_KEY_HERE> uv run kagimcp

KAGI_API_KEY=<YOUR_API_KEY_HERE> uv run kagimcp --http --host 0.0.0.0 --port 8000

HTTP mode is multi-tenant: each request supplies its API key via theAuthorization: Bearer <key>header instead of a server-wide env var, so one instance can serve multiple users. The repo ships aDockerfilethat installs a pinnedkagimcpfrom PyPI and runs it in HTTP mode. The container respects$PORTso it works on any platform that injects one (Railway, Render, Cloud Run, Fly.io, etc.).

docker build -t kagimcp-hosted . docker run --rm -p 8000:8000 kagimcp-hosted

curl -sL http://127.0.0.1:8000/mcp -X POST \ -H "authorization: Bearer $KAGI_API_KEY" \ -H "content-type: application/json" \ -H "accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

To bump the version in production, edit the pin in theDockerfileand redeploy.

npx @modelcontextprotocol/inspector uvx kagimcp

npx @modelcontextprotocol/inspector uv --directory /ABSOLUTE/PATH/TO/kagimcp run kagimcp

The inspector is usually available athttp://localhost:5173.

If using a prerelease build, the same installation instructions apply, but useuvx --prerelease allow --from kagimcp==1.0.0rc2 kagimcpinstead ofuvx kagimcp(replace1.0.0rc2with whatever version you're wanting to install).

Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.

Multi-provider search broker for AI agents. Routes across SearXNG, Brave, Serper, Tavily, and Exa with automatic fallback, RRF ranking, content extraction, and budget enforcement.

A search server for the Model Context Protocol (MCP) that uses the Baidu Wenxin API.

Perform web, news, and image searches using the Microsoft Bing Search API.

An MCP server for web and local search using the Brave Search API.

Integrates the Brave Search API for both web and local search capabilities. Requires a BRAVE_API_KEY.

An MCP server for the Brave Search API, providing web and local search capabilities via a streaming SSE interface.

An MCP server for the Brave Search API, providing both web and local search capabilities.

Search for cocktail recipes using the cezzis.com API.

Free search API for AI agents — 105 engines, 22 profiles, 94.3% SimpleQA accuracy, MCP server with 5 tools

Free search API for AI agents with 105 engines, 22 search profiles, and 94.3% SimpleQA accuracy. MCP server included.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Explore

Setting up with Highlight

From the repository

kagi_search_fetch

kagi_extract

Claude Desktop / Cursor

Linux

Macos

Windows

More like this

Sequential Thinking

Sentry

Github

Brave Search

`kagi_search_fetch`

`kagi_extract`