About jmcpx
jmcpx is a command-line client for interacting with and managing MCP servers, aimed at users who work with MCP and LLM configurations in a terminal. It starts sessions, lists tools and resources, and supports multiple LLM configurations.
Key features
- 01Start and manage interactive sessions
- 02List server tools and resources
- 03Configure multiple LLMs
- 04Render responses in Markdown
- 05Use JSON and TOML configuration
Use cases
- 01Start an MCP session from the command line
- 02Inspect tools and resources exposed by servers
- 03Configure Bedrock, Anthropic, or OpenAI models
- 04Manage MCP connections through configuration files
MCP support
jmcpx is an MCP client that connects to MCP servers and manages sessions, and can list the tools and resources they expose. MCP connections can be specified as stdio or HTTP in JSON configuration.
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 READMEjmcpx
jmcpx is a Command-Line Interface (CLI) client designed for interacting with MCP (Model Context Protocol) servers. It provides a robust set of tools to manage and interact with MCP servers while seamlessly integrating with various Large Language Model (LLM) configurations.
Features
- Session Management: Start and manage interactive sessions with MCP servers.
- Tool and Resource Listing: Retrieve and display available tools and resources provided by MCP servers.
- LLM Integration: Supports multiple LLM configurations, including OpenAI, Anthropic, and Bedrock.
- Markdown Rendering: Outputs responses in Markdown format for improved readability.
- Customizable Configurations: Easily configure MCP and LLM settings using JSON and TOML files.
Requirements
- Java: Version 21 or higher
- Maven: For dependency management and building the project
Installation
-
Clone the repository:
git clone ... cd jmcpx -
Build the project using Maven:
mvn clean package -
Run the application:
java -jar target/jmcpx-1.0-SNAPSHOT.jar
Usage
The application provides several commands to interact with MCP servers and LLM configurations. Below are the available commands:
Start a Session
Start an interactive session with an MCP server:
java -jar target/jmcpx-1.0-SNAPSHOT.jar session
Options:
-cor--mcp: Specify the location of themcp.jsonfile (default:<user.home>/.config/jmcpx/mcp.json).-lor--llm: Specify the location of thellm.tomlfile (default:<user.home>/.config/jmcpx/llm.toml).
List MCP Server Details
List available tools and resources from MCP servers:
java -jar target/jmcpx-1.0-SNAPSHOT.jar list
Options:
-cor--mcp: Specify the location of themcp.jsonfile (default:<user.home>/.config/jmcpx/mcp.json).-lor--llm: Specify the location of thellm.tomlfile (default:<user.home>/.config/jmcpx/llm.toml).
Configuration
By default, you can place both the mcp.json and llm.toml configuration files in your user's home folder,
specifically inside <user.home>/.config/jmcpx folder.
If you are using Windows, the path for your home folder by default is C:\Users\<username> (Example: C:\Users\ervin).
For OSX/Linux, this would be something like /home/<username>.
You can overwrite these paths with -c flag for the mcp.json file and with -l for the llm.toml configuration file.
MCP Configuration
The mcp.json file defines the MCP servers and their configurations. Example:
{
"mcpServers": {
"server1": {
"transport": "stdio",
"command": "path/to/server1",
"args": ["--arg1", "--arg2"],
"env": {
"ENV_VAR1": "value1"
}
},
"server2": {
"transport": "http",
"url": "https://myserver.com/mcp",
"headers": {
"Authorization": "Bearer ..."
}
}
}
}
LLM Configuration
The llm.toml file defines the LLM configurations. Example:
[[bedrock]]
modelId = "amazon.nova-pro-v1:0"
region = "us-east-1"
[[anthropic]]
modelName = "claude-sonnet-4-20250514"
apiKey = "..."
default = true
[[anthropic]]
modelName = "claude-3-7-sonnet-20250219"
apiKey = "..."
[[openai]]
modelName = "gpt-4o-2024-08-06"
apiKey = "..."
[[openai]]
modelName = "gpt-4.1-2025-04-14"
apiKey = "..."
[[google]]
modelName = "gemini-2.5-pro-preview-05-06"
apiKey = "..."
Logging
Use DEV logback Configuration
java -Dlogback.configurationFile=logback-dev.xml -jar target/jmcpx-1.0-SNAPSHOT.jar
License
This project is licensed under the MIT License. See the LICENSE file for details.
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.