Flagged: reads agent config files. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by kagisearch · MCP Server · ★ 472
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is kagimcp safe to install? View the security audit →
Kagi MCP server Setup Intructions 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: Windows: Installing via Smithery Alternatively, you can install Kagi for Claude Desktop via Smithery: Setup with OpenAI Codex CLI To add the Kagi mcp server to codex cli, you will need to use the following command: This will write out the configuration to , so if you need to update/rotate your API key, update your key there before running again. Codex CLI comes with its own built-in search (via flag), but it is disabled by default. So to deconflict between search and Kagi, just don't enable it. Setup with Claude Claude Desktop json // claudedesktopconfig.json // Can find l
| Stars | 472 |
| Forks | 44 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 66.5155155699442/100 |
| Open Issues | 5 |
| Last Updated | 2026-07-07 |
| Created | 2024-12-13 |
| Platforms | mcp, python |
| Est. Tokens | ~14k |
These tools work well together with kagimcp for enhanced workflows:
Explore other popular mcp server tools:
kagimcp is The Official Model Context Protocol (MCP) server for Kagi Search & other tools.. It is categorized as a MCP Server with 472 GitHub stars.
kagimcp is primarily written in Python.
You can find installation instructions and usage details in the kagimcp GitHub repository at github.com/kagisearch/kagimcp. The project has 472 stars and 44 forks, indicating an active community.
kagimcp is released under the MIT license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: