mcpField
M
Mcp_agent_streamlit_rag

Mcp_agent_streamlit_rag

github.com/saqadriChat Apps0Updated 86w ago
Repository

About Mcp_agent_streamlit_rag

Mcp_agent_streamlit_rag is a Streamlit chat application configured to use fetch or finder MCP servers, with an optional Qdrant RAG setup. The README provides run and configuration steps but does not describe additional capabilities.

Key features

  1. 01Streamlit application launch
  2. 02Fetch or finder MCP server setup
  3. 03API key configuration
  4. 04Optional Qdrant RAG setup

Use cases

  1. 01Run the chat application with fetch or finder servers
  2. 02Configure an API key for the application
  3. 03Enable Qdrant for a RAG setup

MCP support

The instructions describe using fetch or finder MCP servers; details of the client-server interaction are not provided.

Details

From the project README

Run instructions:

For using fetch or finder MCP servers:

  1. cp mcp_agent.secrets.yaml.example mcp_agent.secrets.yaml --> then update with your API key (openai api key is enough)
  2. uv sync
  3. uv run streamlit run main.py

For using QDrant for RAG:

  1. Uncomment line 63-70 in main.py, and comment out the current instruction and server_names
  2. docker pull qdrant/qdrant
  3. docker run -p 6333:6333 -v $(pwd)/qdrant_storage:/qdrant/storage qdrant/qdrant
  4. uv run streamlit run main.py

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.