About Learning MCP
Learning MCP is an MCP server published by Marcus-Forte in the Developer Tools category: practical Example with MCP.
The repository has 12 stars and 2 forks, with the last commit 8 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.
Install
git clone https://github.com/Marcus-Forte/learning-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
Ask AI about Learning MCP
Powered by Claude · Grounded in docs
Security checks
Static checks derived from the repository 5 days ago. Heuristics on the source, not an audit.
- ✓README presentThe repository ships documentation.
- ✓License declaredUsable under a stated license.
- !Tests presentNo tests found. Behaviour changes may go unnoticed between versions.
- ✓Dependencies pinnedA lockfile pins dependency versions.
- ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
- !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.
README
Minimal MCP client and server Example.
This repository demonstrates the power and flexibility of MCP. Lan
-
In a terminal, call
uv run python -m app.serverto start MCP server. We're using HTTP streamable. -
In another terminal, call
uv run python -m app.client. Checkuv run -- python -m app.client -hfor options. If using ollama, make sure to serve and pull the models.
uv run python -m app.client --prompt "what's 9+9?" --ollama_model qwen3 --llm ollamauv run python -m app.client --prompt "what's 9+9?" --llm ollama --ollama_model deepseek-r1uv run python -m app.client --prompt "what's 9+9?" --llm google
Generate proto services
uv run python -m grpc_tools.protoc -Iproto_gen=app/proto --python_out=. --pyi_out=. --grpc_python_out=. ./app/proto/*.proto
Resources
- https://modelcontextprotocol.io/introduction: MCP Theory.
- https://python.langchain.com/api_reference/reference.html: Abstract object that represents various LLM models.
- https://docs.mcp-use.com/: Abstract interface to between MCP server and various LLM models, remotely or local (ollama).
- https://gofastmcp.com/servers/server: FastMCP documentation.
README fetched from the repository 5 days ago. The original is authoritative.