{"id":26648602,"url":"https://github.com/kagisearch/kagimcp","last_synced_at":"2025-03-25T00:02:16.445Z","repository":{"id":271966027,"uuid":"902662933","full_name":"kagisearch/kagimcp","owner":"kagisearch","description":"A Model Context Protocol (MCP) server for Kagi search.","archived":false,"fork":false,"pushed_at":"2025-03-11T18:04:35.000Z","size":58,"stargazers_count":33,"open_issues_count":0,"forks_count":5,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-03-11T19:23:04.723Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kagisearch.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-12-13T02:41:16.000Z","updated_at":"2025-03-11T18:04:39.000Z","dependencies_parsed_at":"2025-03-03T19:40:01.854Z","dependency_job_id":null,"html_url":"https://github.com/kagisearch/kagimcp","commit_stats":null,"previous_names":["kagisearch/kagimcp","kagisearch/kagi-mcp"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kagisearch%2Fkagimcp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kagisearch%2Fkagimcp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kagisearch%2Fkagimcp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kagisearch%2Fkagimcp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kagisearch","download_url":"https://codeload.github.com/kagisearch/kagimcp/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245372380,"owners_count":20604491,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-03-25T00:02:10.890Z","updated_at":"2025-03-25T00:02:16.433Z","avatar_url":"https://github.com/kagisearch.png","language":"Python","funding_links":[],"categories":["🏢 Enterprise-Supported Implementations","Search \u0026 Extraction","Web Search MCP Servers","MCP 服务器精选列表","📚 Projects (1974 total)","Production-Ready Servers","پیاده‌سازی‌های سرور","🤖 AI/ML","MCP Servers","Search","官方 MCP 服务器列表","Official Servers","Servers","Search \u0026 Data Extraction","Cloud Services","Table of Contents","Python","🗂️ Extensions by Category","Other","Server Implementations"],"sub_categories":["Search \u0026 Data Retrieval","Web Search Engines","🔍 搜索","MCP Servers","🔎 \u003ca name=\"search\"\u003e\u003c/a\u003eجستجو و استخراج داده","Knowledge \u0026 Memory","Search \u0026 Knowledge","How to Submit","Search","📊 Analytics","🔎 \u003ca name=\"search\"\u003e\u003c/a\u003eSearch \u0026 Data Extraction"],"readme":"# Kagi MCP server\n\n[![smithery badge](https://smithery.ai/badge/kagimcp)](https://smithery.ai/server/kagimcp)\n\n\u003ca href=\"https://glama.ai/mcp/servers/xabrrs4bka\"\u003e\n  \u003cimg width=\"380\" height=\"200\" src=\"https://glama.ai/mcp/servers/xabrrs4bka/badge\" alt=\"Kagi Server MCP server\" /\u003e\n\u003c/a\u003e\n\n## Setup Intructions\n\u003e Before anything, 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.\n\nInstall uv first.\n\nMacOS/Linux:\n```bash\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n```\n\nWindows:\n```\npowershell -ExecutionPolicy ByPass -c \"irm https://astral.sh/uv/install.ps1 | iex\"\n```\n\n### Setup with Claude Desktop\n```json\n# claude_desktop_config.json\n# Can find location through:\n# Hamburger Menu -\u003e File -\u003e Settings -\u003e Developer -\u003e Edit Config\n{\n  \"mcpServers\": {\n    \"kagi\": {\n      \"command\": \"uvx\",\n      \"args\": [\"kagimcp\"],\n      \"env\": {\n        \"KAGI_API_KEY\": \"YOUR_API_KEY_HERE\"\n      }\n    }\n  }\n}\n```\n\n### Installing via Smithery\n\nAlternatively, you can install Kagi for Claude Desktop automatically via [Smithery](https://smithery.ai/server/kagimcp):\n\n```bash\nnpx -y @smithery/cli install kagimcp --client claude\n```\n\n### Ask Claude a question requiring search\ne.g. \"Who was time's 2024 person of the year?\"\n\n### Debugging\nRun:\n```bash\nnpx @modelcontextprotocol/inspector uvx kagimcp\n```\n\n## Local/Dev Setup Instructions\n\n### Clone repo\n`git clone https://github.com/kagisearch/kagimcp.git`\n\n### Install dependencies\nInstall uv first.\n\nMacOS/Linux:\n```bash\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n```\n\nWindows:\n```\npowershell -ExecutionPolicy ByPass -c \"irm https://astral.sh/uv/install.ps1 | iex\"\n```\n\nThen install MCP server dependencies:\n```bash\ncd kagimcp\n\n# Create virtual environment and activate it\nuv venv\n\nsource .venv/bin/activate # MacOS/Linux\n# OR\n.venv/Scripts/activate # Windows\n\n# Install dependencies\nuv sync\n```\n### Setup with Claude Desktop\n\n#### Using MCP CLI SDK\n```bash\n# `pip install mcp[cli]` if you haven't\nmcp install /ABSOLUTE/PATH/TO/PARENT/FOLDER/kagimcp/src/kagimcp/server.py -v \"KAGI_API_KEY=API_KEY_HERE\"\n```\n\n#### Manually\n```json\n# claude_desktop_config.json\n# Can find location through:\n# Hamburger Menu -\u003e File -\u003e Settings -\u003e Developer -\u003e Edit Config\n{\n  \"mcpServers\": {\n    \"kagi\": {\n      \"command\": \"uv\",\n      \"args\": [\n        \"--directory\",\n        \"/ABSOLUTE/PATH/TO/PARENT/FOLDER/kagimcp\",\n        \"run\",\n        \"kagimcp\"\n      ],\n      \"env\": {\n        \"KAGI_API_KEY\": \"YOUR_API_KEY_HERE\"\n      }\n    }\n  }\n}\n```\n### Ask Claude a question requiring search\ne.g. \"Who was time's 2024 person of the year?\"\n### Debugging\nRun:\n```bash\n# If mcp cli installed (`pip install mcp[cli]`)\nmcp dev /ABSOLUTE/PATH/TO/PARENT/FOLDER/kagimcp/src/kagimcp/server.py\n\n# If not\nnpx @modelcontextprotocol/inspector \\\n      uv \\\n      --directory /ABSOLUTE/PATH/TO/PARENT/FOLDER/kagimcp \\\n      run \\\n      kagimcp\n```\nThen 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`.\n\n# Notes\n- Level of logging is adjustable through the `FASTMCP_LOG_LEVEL` environment variable (e.g. `FASTMCP_LOG_LEVEL=\"ERROR\"`)\n  - Relevant issue: https://github.com/kagisearch/kagimcp/issues/4","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkagisearch%2Fkagimcp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkagisearch%2Fkagimcp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkagisearch%2Fkagimcp/lists"}