{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_76s4b73sk2qc","handle":"iflow-mcp-jsfsds-pubmed-search","url":"https://wellknown.network/agents/iflow-mcp-jsfsds-pubmed-search","links":{"self":"https://wellknown.network/agents/iflow-mcp-jsfsds-pubmed-search/record.json","html":"https://wellknown.network/agents/iflow-mcp-jsfsds-pubmed-search","markdown":"https://wellknown.network/agents/iflow-mcp-jsfsds-pubmed-search/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-jsfsds-pubmed-search","status":"https://wellknown.network/api/v1/agents/iflow-mcp-jsfsds-pubmed-search/status","claim":"https://wellknown.network/agents/iflow-mcp-jsfsds-pubmed-search/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-jsfsds-pubmed-search/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-jsfsds-pubmed-search/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-jsfsds-pubmed-search/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-jsfsds-pubmed-search/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-jsfsds-pubmed-search","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_jsfsds-pubmed_search","summary":"PubMed 文献智能分析 MCP 服务","description":"**PubMed_Search 是一个基于 模型上下文协议/MCP 构建的智能医学文献分析工具。它旨在帮助科研人员、医学从业者和学生快速检索 PubMed 数据库，并利用大型语言模型 (LLM) 的能力对文献摘要进行智能分析和总结**\n\n**请注意**: 本项目目前仍有许多待完善的功能。欢迎任何形式的反馈和贡献，以帮助项目不断进步。\n\n## 功能特性\n\n- **PubMed 文献检索**: 通过关键词、作者、期刊等多种方式，使用 PubMed 高级检索语法进行文献检索。\n- **智摘要总结**: 利用 SiliconFlow 用大型语言模型对检索到的多篇文献摘要进行综合概述。\n\n## 可用工具\n\n以下为当前可用的 MCP 工具及用法示例：\n\n### 1. fetch_articles\n**功能**: 使用 PubMed 高级检索语法获取文章，默认检索 2015/01/01 至今。\n**参数**:\n- `query` (str): PubMed 高级检索查询语句\n- `email` (str, 可选): 用于 NCBI Entrez 的邮箱，默认为环境变量 `NCBI_EMAIL`\n- `from_date` (str, 可选): 查询开始日期（YYYY/MM/DD），默认为 2015/01/01\n- `to_date` (str, 可选): 查询结束日期（YYYY/MM/DD），默认为当天\n- `limit` (int, 可选): 最大返回文章数，默认为 8\n- `order_by` (str, 可选): 排序方式\n- `output` (str, 可选): 输出文件名（.txt）\n**返回**:\n```json\n{\"success\": true, \"status\": \"fetch_completed\", \"message\": \"…\", \"result_file\": \"…\", \"article_count\": n}\n```\n+**状态说明**:\n+- `fetch_completed`: 检索成功并已保存结果文件。\n+- `fetch_failed`: 检索失败，可能由于缺少邮箱或检索过程出错。\n+- `no_results`: 检索成功但未找到任何结果。\n+- `save_failed`: 结果文件保存失败，请检查路径和权限。\n\n### 2. summarize_abstracts\n**功能**: 对指定结果文件中的摘要进行综合概述\n**参数**:\n- `filenames` (List[str]): 要汇总的文件名列表\n- `model` (str): 模型名，默认为 deepseek-ai/DeepSeek-V3\n- `max_tokens` (int): 最大 tokens，默认为 512\n- `temperature` (float): 温度，默认为 0.3\n**返回**:\n```json\n{\"success\": true, \"status\": \"summary_completed\", \"summary\": \"…\"}\n```\n+**状态说明**:\n+- `summary_completed`: 摘要汇总成功。\n+- `missing_files`: 指定的结果文件未找到。\n+- `extract_failed`: 未能提取到摘要内容。\n+- `summary_failed`: 汇总过程中调用 API 或处理失败。\n\n### 3. format_citations\n**功能**: 将指定结果文件中的文章信息格式化为引用字符串列表。\n**参数**:\n- `filenames` (List[str]): 要格式化的文件名列表\n**返回**:\n```json\n{\"success\": true, \"status\": \"citations_formatted\", \"citations\": [\"…\", \"...\"]}\n```\n+**状态说明**:\n+- `citations_formatted`: 引用格式化成功。\n+- `format_failed`: 格式化失败，可能由于指定文件未找到或读取错误。\n\n## 安装与配置\n\n### 1. 环境准备\n- Python 3.8 或更高版本\n- Git\n\n### 2. 克隆项目\n```bash\ngit clone <您的项目仓库地址>\ncd pubmed_search_2\n```\n\n### 3. 创建并激活虚拟环境 (推荐)\n```bash\npython -m venv .venv\n# Windows\n.venv\\\\Scripts\\\\activate\n# macOS/Linux\nsource .venv/bin/activate\n```\n\n### 4. 安装依赖\n```bash\npip…","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_jsfsds-pubmed_search","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"research.academic","name":"Academic Research","confidence":1,"provenance":"derived"},{"slug":"content.writing","name":"Writing & Editing","confidence":0.825,"provenance":"derived"}],"categories":["content","research"],"language":"fr"},"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":"iflow-mcp_jsfsds-pubmed_search","registry":"pypi","observedAt":"2026-11-03T07:25:47.946Z","publishedAt":"2026-02-12T00:58:20.241645Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_jsfsds-pubmed_search","url":"https://pypi.org/project/iflow-mcp_jsfsds-pubmed_search/","firstSeenAt":"2026-09-09T19:24:20.580Z","fetchedAt":"2026-11-03T07:23:58.352Z","normalizedAt":"2026-11-03T07:23:58.352Z"}]},"firstSeenAt":"2026-09-09T19:24:20.580Z","updatedAt":"2026-11-03T07:25:47.946Z"}