What is Local Mcp Client

Local_MCP_Client is a cross-platform web and API interface designed for interacting with configurable MCP servers using natural language. It is powered by Ollama and any local LLM of choice, facilitating structured tool execution and dynamic agent behavior.

Use cases

Use cases for Local_MCP_Client include automating tasks in cybersecurity analysis, enhancing software development workflows, creating interactive data analysis tools, and facilitating user-friendly interfaces for complex server interactions.

How to use

To use Local_MCP_Client, first create a virtual environment and install the required dependencies. Then, install Ollama and pull the desired LLM model. After setting up the MCP servers, run the Ollama service and execute the Local_MCP_Client script with your API token.

Key features

Key features of Local_MCP_Client include cross-platform compatibility, natural language processing capabilities, support for various local LLMs, structured tool execution, and dynamic agent behavior.

Where to use

Local_MCP_Client can be utilized in various fields such as software development, cybersecurity, data analysis, and any domain that requires interaction with configurable MCP servers using natural language.

Local MCP Client

Local MCP Client is a cross-platform web and API interface for interacting with configurable MCP servers using natural language, powered by Ollama and any local LLM of choice, enabling structured tool execution and dynamic agent behavior.

Step 1a: Create Virtual Env & Install Requirements - MAC/Linux

curl -LsSf https://astral.sh/uv/install.sh | sh
cd Local_MCP_Client
uv init .
uv venv
source .venv/bin/activate
uv pip install -r requirements.txt

Step 1b: Create Virtual Env & Install Requirements - Windows

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
cd Local_MCP_Client
uv init .
uv venv
.venv\Scripts\activate
uv pip install -r requirements.txt

Step 2a: Install Ollama & Pull LLM Model - MAC

brew install ollama
ollama serve
ollama pull llama3:8b

Step 2b: Install Ollama & Pull LLM Model - Linux

curl -fsSL https://ollama.com/install.sh | sh
ollama serve
ollama pull llama3:8b

Step 2c: Install Ollama & Pull LLM Model - Windows

Download Ollama HERE

ollama serve
ollama pull llama3:8b

Step 3a: Clone MCP Servers - MAC/Linux

cd ~/Documents
git clone https://github.com/mytechnotalent/MalwareBazaar_MCP.git
git clone https://github.com/Invoke-RE/binja-lattice-mcp

Step 3b: Clone MCP Servers - Windows

cd "$HOME\Documents"
git clone https://github.com/mytechnotalent/MalwareBazaar_MCP.git
git clone https://github.com/Invoke-RE/binja-lattice-mcp

Step 4: Run Ollama

ollama serve

Step 5a: Run MCP Client - MAC/Linux

export BNJLAT = "<your-binja-api-token>"
uv run local_mcp_client.py

Step 5b: Run MCP Client - Windows

$env:BNJLAT = "<your-binja-api-token>"
uv run local_mcp_client.py

Step 6: Run Tests

python -m unittest discover -s tests

uv pip install coverage==7.8.0
coverage run --branch -m unittest discover -s tests
coverage report -m
coverage html
open htmlcov/index.html  # MAC
xdg-open htmlcov/index.html  # Linux
start htmlcov\index.html  # Windows
coverage erase

License

Apache License, Version 2.0