mcp-research-server
Provides access to research paper topics and lists via a remote SSE server, enabling users to explore folders, topics, and execute prompts.
README
MCP ChatBot L9 —— 混合传输模式
在 L7 的基础上，将 research server 从本地 stdio 子进程改为远程 SSE 服务器。
架构变化
| 组件 | L7 | L9 |
|---|---|---|
| research server | stdio 子进程 | SSE 远程 (port 8001) |
| filesystem server | stdio 子进程 | stdio 子进程 (不变) |
| fetch server | stdio 子进程 | stdio 子进程 (不变) |
| LLM API | DeepSeek (openai SDK) | DeepSeek (不变) |
运行方式
# 1. 启动远程 SSE 服务器（终端 1）
uv run research_server.py
# 2. 启动聊天机器人（终端 2）
uv run mcp_chatbot.py
命令
| 命令 | 说明 |
|---|---|
@folders |
查看可用论文主题文件夹 |
@topic_name |
查看某主题的论文列表 |
/prompts |
列出所有提示模板 |
/prompt <name> arg1=val1 ... |
执行提示模板 |
quit |
退出对话 |
🚀 部署到 Render（远程 SSE 服务）
1. 创建 GitHub 仓库
在 GitHub 创建新仓库（例如 mcp-research-server），不要勾选 "Add a README file"。
2. 推送代码
cd L9/mcp_project
# 初始化 git
git init
git add .
git commit -m "Initial commit: MCP Research Server (SSE)"
# 关联远程仓库并推送
git remote add origin https://github.com/<你的用户名>/mcp-research-server.git
git branch -M main
git push -u origin main
3. Render 关联部署
- 登录 Render Dashboard（用 GitHub 账号）
- 点击 New + → Web Service
- 选择刚推送的 GitHub 仓库
- Render 自动检测
render.yaml，或者手动配置：- Build Command:
pip install -r requirements.txt - Start Command:
python research_server.py
- Build Command:
- 点击 Deploy Web Service
4. 更新客户端配置
部署成功后，Render 会分配一个 URL（如 https://mcp-research-server.onrender.com）。
修改 server_config.json 中的 research 服务器 URL：
{
"mcpServers": {
"research": {
"transport": "sse",
"url": "https://mcp-research-server.onrender.com/sse"
}
}
}
5. 测试远程服务
# 启动 chatbot（现在连接到远程 Render 服务器）
uv run mcp_chatbot.py
注意: Render 免费层在无流量时会休眠，首次请求可能需要 30-60 秒唤醒。
项目文件说明
| 文件 | 用途 |
|---|---|
research_server.py |
FastMCP SSE 服务器（端口由 PORT 环境变量控制） |
mcp_chatbot.py |
混合传输客户端（sse_client + stdio_client） |
server_config.json |
MCP 服务器连接配置 |
render.yaml |
Render Blueprint 部署配置 |
requirements.txt |
Render 部署用的 pip 依赖 |
pyproject.toml |
本地开发用 uv 依赖 |
papers/ |
论文数据存储目录 |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.