🧠 OSDR MCP Server + Agents

Name: 🧠 OSDR MCP Server + Agents
Author: alwalt

@alwalt

代码仓库

关于 🧠 OSDR MCP Server + Agents

暂无概览

基本信息

分类

其他

运行时

python

传输方式

stdio

发布者

alwalt

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "osdr_mcp_server": {
      "command": "python",
      "args": [
        "first_example/main.py"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is 🧠 OSDR MCP Server + Agents?

This project demonstrates how to integrate MCP agents with custom tools for interacting with NASA’s Open Science Data Repository (OSDR). It includes working examples of agent workflows that fetch, analyze, and summarize biological data using the Model Context Protocol (MCP).

How to use 🧠 OSDR MCP Server + Agents?

Clone the repository, install dependencies with pip install -r requirements.txt, then run an example (e.g., python first_example/main.py) or launch the MCP server directly (python osdr_mcp/main_simple.py). Configuration is done via cp_agent.config.yaml.

Key features of 🧠 OSDR MCP Server + Agents

Exposes custom MCP tools: osdr_fetch_metadata and osdr_find_by_organism
Includes additional RNA analysis tools in osdr_viz_tools
Three example agent workflows for different integration levels
Configurable LLM backend (Ollama, OpenAI) and MCP server connections
Multi-agent pipeline: fetch, quantitative analysis, and summary writing

Use cases of 🧠 OSDR MCP Server + Agents

Fetch metadata for a specific OSDR dataset
Filter OSDR studies by organism name
Generate a tweet-sized summary using official MCP servers
Download RNA count data and create a bar plot
Produce a markdown report summarizing biological analysis

FAQ from 🧠 OSDR MCP Server + Agents

How do I configure the LLM backend?

Edit cp_agent.config.yaml to set the LLM backend (e.g., Ollama or OpenAI) and adjust system prompts, MCP server connections, and tool availability.

How do I run a specific example?

From the repo root, run python first_example/main.py, python second_example/main.py, or python third_example/main.py depending on the desired workflow.