Academic-Free s

免费学术智能体（Academic Agents）MCP服务（Awesome Academic Free MCP Servers）是一个专为赋能和支撑各类学术智能体应用而构建的底层能力服务平台。通过标准化的MCP协议，将专业的学术工具能力——如文本处理、信息检索与数据可视化等，以即插即用的方式提供给上层智能体调用。该服务旨在作为学术智能体生态的核心基座，让开发者与研究者能够便捷地为学术智能体注入持续进化的专业学术技能，共同推动智能学术研究的边界。

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio academicagentsstudio-academic-free-mcp-servers python -m academic_free_mcp_servers.websearch \
  --env API_KEY="your_api_key_here" \
  --env SERVICE_URL="https://websearch.freemcps.aiearth.vip/sse"

How to use

This MCP server bundle provides four independent academic services that conform to the Model Context Protocol (MCP). Each service runs as its own MCP endpoint and can be queried or streamed for results via Server-Sent Events (SSE). The FreeAcademicWrite module handles scholarly writing assistance, including polishing Chinese and English academic text, grammar checks, and bilingual translation. FreeWebSearch offers semantic search and multi-model retrieval to fetch and synthesize scholarly information from multiple sources. FreeAcademicChart creates and serves publication-grade charts and visualizations, returning chart URLs that can be embedded in documents. FreeAcademicFormatter focuses on formatting results from external tools into HTML or Markdown, optimizing content for front-end display. You can connect to each service using the MCP client, send the appropriate prompts, and receive structured results or streaming updates in real time. Each module is designed to be used standalone or composed into a larger academic workflow, such as literature reviews, manuscript preparation, or data visualization pipelines.

How to install

Prerequisites:

Python 3.8+ installed on your system
MCP client installed (per MCP protocol)
Network access to the four service endpoints

Steps:

Clone this repository or obtain the MCP module bundle for the Academic Free MCP servers.
Install Python dependencies (if provided). Example:
- python -m pip install -r requirements.txt # if a requirements file exists
Ensure the Python modules are importable. The MCP services are exposed as Python modules:
- academic_free_mcp_servers.write
- academic_free_mcp_servers.websearch
- academic_free_mcp_servers.chart
- academic_free_mcp_servers.formatter
Run each service (example):
- python -m academic_free_mcp_servers.write
- python -m academic_free_mcp_servers.websearch
- python -m academic_free_mcp_servers.chart
- python -m academic_free_mcp_servers.formatter
Validate connectivity with your MCP client and confirm each service is reachable at its SSE endpoint.
Update the mcp_config in your runtime to point to the running instances if using a containerized or orchestrated setup.

Additional notes

Tips and common issues:

Ensure API keys and service URLs in env vars are correctly set to avoid authentication errors.
If running behind a firewall, open the required ports for SSE streaming.
When upgrading, verify compatibility of MCP protocol version between client and servers.
Each service is independently deployed; if one module fails to start, others remain available.
For production, consider containerization (e.g., Docker) and proper load balancing across the four services.
If you plan to integrate with external tooling, use FreeAcademicFormatter as a sink to render tool outputs into HTML/Markdown for UI presentation.