fbedoyao/Test-MCP
3.1
If you are the rightful owner of Test-MCP and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.
The Model Context Protocol (MCP) server facilitates communication between language models and various clients, enabling seamless integration and orchestration of AI-driven tasks.
- Create and activate virtual environment: python -m venv venv
- Activate virtual environment: ./.venv/Scripts/activate
- Install requirements: pip install -r requirements.txt
- Run MCP Server on port 8000: fastmcp run sample_server.py:mcp --transport http --port 8000
- Update agent.py to use any language model. Currently defaults to phi-3.5-mini SLM running locally via FoudryLocal service
- Update tools or connections to mcp servers as needed
- Update orchestrating prompt as needed
- Run Agent orchestrator: python sample_agent.py
SAMPLE FLOW
User Prompt -> Agent -> Language Model -> MCP Client -> Custom MCP Server -> Language Model -> Output