{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_d7z2dnerzw6v","handle":"mcp-server-nbotbb","url":"https://wellknown.network/agents/mcp-server-nbotbb","links":{"self":"https://wellknown.network/agents/mcp-server-nbotbb/record.json","html":"https://wellknown.network/agents/mcp-server-nbotbb","markdown":"https://wellknown.network/agents/mcp-server-nbotbb/record.md","api":"https://wellknown.network/api/v1/agents/mcp-server-nbotbb","status":"https://wellknown.network/api/v1/agents/mcp-server-nbotbb/status","claim":"https://wellknown.network/agents/mcp-server-nbotbb/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-server-nbotbb/claim.json","badge":"https://wellknown.network/agents/mcp-server-nbotbb/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-server-nbotbb/history","tools":"https://wellknown.network/api/v1/agents/mcp-server-nbotbb/tools"},"ard":{"identifier":"urn:air::server:mcp-server-nbotbb","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-server-nbotbb","summary":"A Model Context Protocol server providing tools for time queries and timezone conversions for LLMs","description":"# NBotbb MCP Server\n一个基于 Model Context Protocol（MCP）的上下文服务器，提供农资商品查询与收货地址提取能力。该服务器使大语言模型（LLM）能够理解用户关于农药、化肥等农资产品的自然语言查询（包括有效成分、品牌、规格等），并从本地数据库实时检索库存信息；同时可从任意消息中精准解析结构化收货地址，并内置对文本、图片、语音等多模态输入的透明支持。\n\n🔗 [Model Context Protocol 官网](https://modelcontextprotocol.io/)\n\n---\n\n## 🧰 核心能力（MCP Tools）\n\n### 1. `agro_product_search`：农资商品查询与推荐   \n从用户输入中自动识别农药/化肥产品信息，并查询本地库存。\n- **适用场景**：用户询问“有没有草甘膦？”、“滨农金特200ml有货吗？”\n- **识别字段**：\n  - 产品名称（如“烯草酮”）\n  - 有效成分（如“烟嘧磺隆+莠去津”）\n  - 品牌（如“滨农”、“先正达”）\n  - 规格（如“200毫升”、“1公斤”）\n  - 用途（如“玉米田除草”、“水稻防虫”）\n- **数据源**：本地 SQLite 数据库 products.db\n- **支持偏好**：\n  - 价格最低（`cheapest`）\n  - 生产日期最新（`recent`）\n  - 折扣优先（`discount`）\n- **输出**：结构化商品列表（含价格、库存、生产日期、折扣信息）\n\n---\n### 2. `agro_product_recommend`：智能农资推荐  \n基于作物类型、病虫害、地区气候等上下文，推荐最合适的农资产品组合。\n\n- **适用场景**：用户说“山东小麦得了锈病怎么办？”、“南方水稻防虫用什么药？”\n- **输入解析**：\n  - 作物（如“小麦”、“水稻”）\n  - 病害/虫害（如“锈病”、“稻飞虱”）\n  - 地区（如“山东”、“华南”）\n  - 生长期（可选）\n- **推荐逻辑**：\n  - 匹配农业知识库 + 当地用药习惯\n  - 排除禁用/高毒产品（符合国家法规）\n  - 优先推荐低毒、高效、登记作物匹配的产品\n- **输出**：\n  - 推荐商品列表（含使用剂量、安全间隔期）\n  - 简明使用建议（如“亩用30ml，兑水30kg喷雾”）\n\n> 💡 此工具可与 `agro_product_search` 联动：先推荐，再查库存。\n\n---\n\n### 3. `extract_delivery_address`：收货地址智能提取\n从任意用户消息中(文本/图片/语音)精准解析完整收货信息。\n- **适用场景**：用户发消息“李四 13912345678 上海浦东陆家嘴环路1000号”\n- **识别字段**：\n  - 姓名、手机号\n  - 省、市、区（自动补全层级，如“浦东” → “上海市 浦东新区”）\n  - 详细地址、邮编（可选）\n- **智能清洗**：\n  - 去重（如“北京市 北京市” → “北京市”）\n  - 纠错（如“浦東” → “浦东”）\n  - 标准化（统一“路/街/巷”格式）\n- **输出**：标准化 JSON 地址对象，供下单或确认使用\n\n---\n\n💡 多模态输入（文本/图片/语音）由服务器内部统一处理，LLM 无需额外调用 OCR 或 ASR 工具。\n图片 → 调用 Qwen-VL 识别农药包装\n语音 → 调用通义千问 ASR 转写为文本\n所有输入最终转化为结构化上下文，供上述两个工具使用\n\n## 编译\n```bash\nconda create env -n uvx python=3.10 -y\nconda activate uvx\npip install build twine\ncd ~/autodl-tmp/servers/src/nbotbb/\npython -m build .\ntwine upload dist/*\npypi-AgEIcHlwaS5vcmcCJGI1ZDBmMmY3LTAxMWEtNGZjZi04ODcyLWJjOGNlNjc4OGIzYwACKlszLCI4NWJmOWE2My0wNDdkLTQ0MjItODAzNS1iZTRlMjUxN2VhNTciXQAABiCsG6hp7zI_FRMR2C0vlYxoWoqFWDg5V7rfD4gt4NfLUQ\nsource /etc/network_turbo\nunset http_proxy && unset https_proxy\npip install --index-url https://pypi.org/simple/ your-package-name   h…","publisher":null,"homepage":null,"repository":null,"version":"0.8.17","license":"MIT","protocols":["mcp"],"tags":["llm","mcp","time","timezone"],"pricing":null,"endpoints":[{"url":"pypi:mcp-server-nbotbb","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"provenance":"derived"}],"categories":["dev"],"language":"zh"},"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-server-nbotbb","registry":"pypi","observedAt":"2026-11-09T18:25:52.150Z","publishedAt":"2025-11-29T03:53:49.650040Z","latestVersion":"0.8.17"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-server-nbotbb","url":"https://pypi.org/project/mcp-server-nbotbb/","firstSeenAt":"2026-09-10T04:21:54.182Z","fetchedAt":"2026-11-09T18:23:50.935Z","normalizedAt":"2026-11-09T18:23:50.935Z"}]},"firstSeenAt":"2026-09-10T04:21:54.182Z","updatedAt":"2026-11-09T18:25:52.150Z"}