{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_sw6zbbrbzzp5","handle":"mcp-tech-ai-tracker","url":"https://wellknown.network/agents/mcp-tech-ai-tracker","links":{"self":"https://wellknown.network/agents/mcp-tech-ai-tracker/record.json","html":"https://wellknown.network/agents/mcp-tech-ai-tracker","markdown":"https://wellknown.network/agents/mcp-tech-ai-tracker/record.md","api":"https://wellknown.network/api/v1/agents/mcp-tech-ai-tracker","status":"https://wellknown.network/api/v1/agents/mcp-tech-ai-tracker/status","claim":"https://wellknown.network/agents/mcp-tech-ai-tracker/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-tech-ai-tracker/claim.json","badge":"https://wellknown.network/agents/mcp-tech-ai-tracker/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-tech-ai-tracker/history","tools":"https://wellknown.network/api/v1/agents/mcp-tech-ai-tracker/tools"},"ard":{"identifier":"urn:air::server:mcp-tech-ai-tracker","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-tech-ai-tracker","summary":"科技AI资讯 MCP Server — 模型排行/开源趋势/AI行业速览/多源摘要, 数据源GitHub+HackerNews+arXiv+HuggingFace+TianAPI","description":"# 🤖 mcp-tech-ai-tracker\n\n**科技AI资讯 MCP Server** — 模型排行、开源趋势、AI行业速览、每日多源摘要，一个 Server 全搞定。\n\n基于扣子技能 tech-ai-tracker 重写为 MCP Server。\n\n数据源：[GitHub Search API](https://docs.github.com/en/rest/search) + [HackerNews Algolia API](https://hn.algolia.com/api) + [arXiv API](http://export.arxiv.org/api/query) + [HuggingFace API](https://huggingface.co/api) + [TianAPI](https://www.tianapi.com/)（可选）。\n\n---\n\n## 🛠 工具列表\n\n| 工具 | 功能 | 典型场景 |\n|------|------|---------|\n| `model_rank` | 模型排行与技术数据：LLM排行/开源趋势/Benchmark对比 | \"LLM下载排行\" \"AI开源趋势\" \"模型对比\" |\n| `ai_pulse` | AI行业速览：今日热点/本周回顾/热门话题 | \"今天AI圈有什么\" \"本周AI热点\" |\n| `tech_digest` | 每日多源摘要：新闻+开源+论文+模型一键聚合 | \"今天的AI摘要\" \"科技日报\" |\n\n---\n\n## 📦 安装\n\n```bash\npip install mcp-tech-ai-tracker\n```\n\n或从源码安装：\n\n```bash\ngit clone https://github.com/yourname/mcp-tech-ai-tracker.git\ncd mcp-tech-ai-tracker\npip install -e .\n```\n\n## ⚙️ 配置\n\n### 可选\n\n[TianAPI](https://www.tianapi.com/) API 密钥（免费注册即得，用于AI/科技新闻增强）：\n\n```bash\nexport TIANAPI_KEY=\"your_api_key_here\"\n```\n\n> 不设置 TIANAPI_KEY 时，`ai_pulse` 和 `tech_digest` 仍可返回 HackerNews 社区热点和开源数据（跳过新闻部分）。\n\n## 🚀 使用\n\n### 命令行\n\n```bash\n# STDIO 模式 (默认)\nmcp-tech-ai-tracker\n\n# 或\npython -m mcp_tech_ai_tracker\n```\n\n### MCP 客户端配置\n\n在 Claude Desktop / Cherry Studio / ChatBox 等 MCP 客户端中添加：\n\n```json\n{\n  \"mcpServers\": {\n    \"tech-ai-tracker\": {\n      \"command\": \"mcp-tech-ai-tracker\",\n      \"env\": {\n        \"TIANAPI_KEY\": \"your_tianapi_key\"\n      }\n    }\n  }\n}\n```\n\n### 开发测试\n\n```bash\n# 安装 FastMCP CLI\npip install \"mcp[cli]\"\n\n# 交互式测试\nmcp dev src/mcp_tech_ai_tracker/server.py\n```\n\n---\n\n## 💡 工具详细说明\n\n### model_rank — 模型排行与技术数据\n\n```python\n# LLM模型下载排行 (优先HuggingFace，不可用时降级到GitHub)\nmodel_rank(action=\"llm_rank\")\n\n# 指定分类\nmodel_rank(action=\"llm_rank\", category=\"text-generation\")\n\n# 开源AI项目趋势\nmodel_rank(action=\"trending_repos\")\n\n# 指定语言和时间范围\nmodel_rank(action=\"trending_repos\", language=\"python\", time_range=\"7d\")\n\n# Benchmark对比 (需HuggingFace，不可用时降级)\nmodel_rank(action=\"model_compare\")\n```\n\n**参数**：\n- `action`: llm_rank / trending_repos / model_compare\n- `catego…","publisher":{"name":"Tech AI Tracker Team","url":null},"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["ai","arxiv","github","hackernews","huggingface","llm","mcp","news","open-source","tech"],"pricing":null,"endpoints":[{"url":"pypi:mcp-tech-ai-tracker","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"declared"},{"slug":"ai.model-access","name":"Model Access","confidence":1,"provenance":"declared"},{"slug":"research.academic","name":"Academic Research","confidence":1,"provenance":"declared"},{"slug":"data.news","name":"News & Feeds","confidence":1,"provenance":"declared"}],"categories":["ai","data","dev","research"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-tech-ai-tracker","registry":"pypi","observedAt":"2026-10-22T12:26:25.916Z","publishedAt":"2026-05-17T11:46:45.235002Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-tech-ai-tracker","url":"https://pypi.org/project/mcp-tech-ai-tracker/","firstSeenAt":"2026-09-10T04:23:39.054Z","fetchedAt":"2026-10-22T12:24:42.680Z","normalizedAt":"2026-10-22T12:24:42.680Z"}]},"firstSeenAt":"2026-09-10T04:23:39.054Z","updatedAt":"2026-10-22T12:26:25.916Z"}