About MCP Recon Client
MCP Recon Client is an MCP client that uses open-source LLM models to communicate with MCP servers and access their tools. It includes alternative chat client implementations and can be configured with Google Studio API credentials.
Key features
- 01Connect to MCP servers
- 02Use server tools through an LLM
- 03Support alternative chat client implementations
- 04Configure Google Studio API key
Use cases
- 01Using MCP server tools through an LLM
- 02Trying different chat client implementations
MCP support
As an MCP client, it communicates with MCP servers and gives LLM models access to their tools.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEThis is a Model Context Protocol(MCP) Client that is able to use open-source LLM models to communicate with MCP Servers give access to tools that can be used by the LLM.
Here are the instructions to run the MCP-Client:
-
Clone the Repo
-
Install dependencies using UV pip install -r requirements.txt
-
Install Ollama Client from ollama.com and pull the LLM models you want to use with the client using the alternative chat client implementations.
-
If you have a Google Studio API Key, which you can obtain for free, update that to the '.env' file.
-
Run 'main'py' with UV run src/main.py
NOTE: I was unable to do a comprehensive test for a congenial LLM for tool calls. It is something that is quite hevily dependent upon the correct prompting. The present implementation of 'main.py' using Google Gen AI provided the best results so far as it has a very big context window. If you do want to try models other that google-gemini-2.5-pro you can use the other client implementations after changing their respective models file.
Comments
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.