Kagi Search
MCP ServerFree** - Search the web using Kagi's search API
Capabilities6 decomposed
mcp-compliant web search via kagi api
Medium confidenceExposes Kagi's web search API as a standardized MCP tool that LLM clients can discover and invoke during conversations. The FastMCP framework handles MCP protocol serialization and tool registration, while the kagi_search_fetch tool translates LLM search requests into Kagi API calls and returns formatted results. This enables Claude and other MCP-compatible clients to perform web searches without direct API integration.
Implements MCP protocol as the integration layer rather than direct REST API exposure, allowing LLMs to discover and invoke Kagi search as a native tool without custom client-side bindings. Uses FastMCP framework to handle protocol complexity, reducing boilerplate compared to raw MCP server implementations.
Provides privacy-focused Kagi search integration via MCP (unlike Perplexity or Google search integrations), with standardized tool discovery that works across any MCP-compatible client rather than being locked to a single LLM platform.
multi-engine content summarization via mcp
Medium confidenceExposes Kagi's summarization API through the kagi_summarizer MCP tool, supporting four distinct summarization engines (cecil, agnes, daphne, muriel) optimized for different content types. The tool accepts URLs or raw content and returns concise summaries via the MCP protocol, allowing LLM clients to automatically summarize web pages, documents, or videos without leaving the conversation context.
Provides access to four distinct Kagi summarization engines (cecil, agnes, daphne, muriel) through a single MCP tool interface, each optimized for different content types. Configuration via environment variable allows teams to select their preferred engine without code changes, and the MCP abstraction enables seamless integration with any MCP-compatible client.
Offers multiple summarization engines optimized for different content types (unlike single-engine solutions like OpenAI's summarization), integrated via MCP for client-agnostic deployment rather than being tied to a specific LLM platform.
fastmcp-based mcp server implementation and protocol handling
Medium confidenceImplements the full Model Context Protocol (MCP) server specification using the FastMCP framework, which handles MCP protocol serialization, tool registration, schema validation, and client communication. The server instantiates FastMCP, registers the kagi_search_fetch and kagi_summarizer tools with their schemas, and manages bidirectional communication with MCP clients like Claude Desktop. This abstraction eliminates manual MCP protocol implementation, reducing complexity from hundreds of lines to a few tool definitions.
Uses FastMCP framework to abstract away MCP protocol complexity, allowing tool definitions to be expressed as simple Python functions with type hints rather than manual JSON schema construction. The framework automatically handles tool discovery, schema validation, and bidirectional communication with MCP clients.
Reduces MCP server implementation complexity by 70-80% compared to raw MCP protocol implementations, enabling faster development and easier maintenance while maintaining full MCP specification compliance.
claude desktop and claude code configuration management
Medium confidenceProvides standardized configuration mechanisms for integrating kagimcp with Claude Desktop (via claude_desktop_config.json) and Claude Code (via claude mcp add command). The configuration system manages MCP server command specification, environment variable injection (KAGI_API_KEY, KAGI_SUMMARIZER_ENGINE), and client-specific setup, enabling one-click deployment without manual protocol configuration.
Provides multiple configuration pathways (manual JSON editing, Smithery CLI one-click install, uvx direct execution, Docker containerization) allowing users to choose their preferred setup method. Configuration is declarative via JSON, enabling version control and team sharing of MCP server configurations.
Supports both Claude Desktop and Claude Code with unified configuration approach, whereas many MCP servers only target one client. Smithery integration enables one-click installation, reducing setup friction compared to manual JSON editing required by raw MCP servers.
multi-deployment method support (smithery, uvx, docker, local development)
Medium confidenceSupports four distinct deployment pathways: Smithery platform one-click installation (npx @smithery/cli install kagimcp), direct execution via uvx (uvx kagimcp), Docker containerization (uv run kagimcp), and local development setup (uv sync). Each method handles dependency management, environment variable configuration, and server startup differently, enabling deployment across different user skill levels and infrastructure constraints.
Provides four distinct deployment pathways with different dependency and configuration models, allowing users to choose based on their environment and skill level. Smithery integration enables non-technical users to install via one command, while Docker and local development paths support advanced deployment scenarios.
Offers more deployment flexibility than typical MCP servers (which usually require manual installation), with Smithery one-click setup reducing friction for end users and Docker support enabling production-grade containerized deployments.
environment variable-based configuration with sensible defaults
Medium confidenceManages server configuration through environment variables (KAGI_API_KEY, KAGI_SUMMARIZER_ENGINE, FASTMCP_LOG_LEVEL) with sensible defaults where applicable. KAGI_API_KEY is required and must be set before server startup; KAGI_SUMMARIZER_ENGINE defaults to 'cecil' if not specified; FASTMCP_LOG_LEVEL defaults to standard logging. This approach enables configuration without code changes and supports different configurations across environments (development, staging, production).
Uses environment variables as the sole configuration mechanism with sensible defaults (cecil for summarizer engine, standard logging level), enabling zero-configuration deployments in containerized environments while maintaining flexibility for advanced users. No external configuration files required.
Simpler than configuration file-based approaches (no YAML/JSON parsing), more portable across deployment environments than hardcoded configuration, and integrates naturally with container orchestration systems (Docker, Kubernetes) that manage environment variables.
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with Kagi Search, ranked by overlap. Discovered automatically through the match graph.
Search1API
** - One API for Search, Crawling, and Sitemaps
WebSearch-MCP
** - Self-hosted Websearch API
Open-Sourced MCP Servers Directory
** - A curated list of MCP servers by **[mcpso](https://mcp.so)**
MCP.ing
** - A list of MCP services for discovering MCP servers in the community and providing a convenient search function for MCP services by **[iiiusky](https://github.com/iiiusky)**
Kagi
** - Kagi search API integration
mcp.natoma.ai
** – A Hosted MCP Platform to discover, install, manage and deploy MCP servers by **[Natoma Labs](https://www.natoma.ai)**
Best For
- ✓Claude Desktop and Claude Code users needing real-time web search
- ✓LLM agent builders using MCP-compatible clients
- ✓Teams migrating from generic web search to privacy-focused Kagi search
- ✓Claude users processing large volumes of web content or documents
- ✓Research teams needing multi-engine summarization for content analysis
- ✓LLM agents that need to reduce context window usage by pre-summarizing sources
- ✓Developers building MCP servers for LLM integrations
- ✓Teams deploying Kagi services across multiple MCP-compatible clients
Known Limitations
- ⚠Search results are limited to Kagi API response format — no custom result ranking or filtering beyond Kagi's native options
- ⚠Latency depends on Kagi API response time plus MCP serialization overhead (~100-500ms typical)
- ⚠No built-in caching of search results — each query hits the Kagi API directly
- ⚠Search query complexity limited by Kagi API parameter constraints
- ⚠Summarization quality varies by engine and content type — no automatic engine selection based on content analysis
- ⚠KAGI_SUMMARIZER_ENGINE environment variable sets a single default engine; switching engines requires server restart
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
About
** - Search the web using Kagi's search API
Categories
Alternatives to Kagi Search
Are you the builder of Kagi Search?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →