# chrishayuk/mcp-cli [Health: Active]

**Category:** 🛠️ Other Tools and Integrations  
**Repository:** https://github.com/chrishayuk/mcp-cli  
**GitHub Stars:** 2019  
**Views:** 3  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/chrishayuk-mcp-cli

## Description
Yet another CLI tool for testing MCP servers

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `uvx` (confidence: high):

```json
"mcpServers": {
  "mcp-cli": {
    "command": "uvx",
    "args": ["mcp-cli"]
  }
}
```

## Documentation

## What chrishayuk/mcp-cli MCP server does

chrishayuk/mcp-cli MCP server provides a terminal interface for connecting to and exercising Model Context Protocol servers. It can discover and invoke server tools directly, or let an LLM select and use tools during a streamed conversation. The project is intended for testing, interactive operation, and scriptable automation rather than for exposing a business-system API of its own.

Four operating styles are described: chat mode for conversational work, interactive mode for command-driven sessions, command mode for Unix pipelines, and direct commands for individual operations. Responses can include Markdown formatting, syntax highlighting, progress indicators, timing information, and tool execution statistics.

## How it works

The CLI acts as the orchestration layer between MCP servers, an LLM provider, and the terminal interface. CHUK Tool Processor handles asynchronous tool execution, while CHUK-LLM supplies the unified model-provider layer. The README also identifies CHUK-Term as the terminal UI component.

In chat mode, the client streams model output and can execute multiple tools concurrently while preserving conversation order. Users can interrupt response generation or tool execution with Ctrl+C. Conversation sessions can be saved, loaded, listed, and automatically saved every 10 turns; conversations can also be exported as Markdown or JSON with metadata.

The experimental virtual-memory feature manages conversation context with configurable budgets and modes. Execution plans can represent multi-step tool-call graphs, run independent steps in parallel, support dry runs, persist checkpoints, and resume after interruption. Plans can be created through the `/plan` command or, when enabled, generated by the model.

## Setup and configuration

The default configuration uses Ollama with the `gpt-oss` reasoning model, allowing local operation without an API key according to the README. Other provider and model behavior is available through the CHUK-LLM integration, but the supplied material does not specify the required provider configuration or installation command.

Runtime behavior can be adjusted with options including `--vm`, `--vm-budget`, `--vm-mode`, `--plan-tools`, `--log-file`, `--health-interval`, `--dashboard`, and repeatable `--attach` arguments. Server-specific `tool_timeout` and `init_timeout` settings can override global and default timeout values.

## Tools and capabilities

The chrishayuk/mcp-cli MCP server includes:

- Chat, interactive, command, and direct-command modes.
- Streaming responses, reasoning visibility, concurrent tool calls, and token usage tracking.
- Image, audio, text, and code attachments through commands, flags, inline file references, or the dashboard.
- Health checks through `/health`, with optional background polling and failure diagnostics.
- Experimental virtual memory inspection through `/memory`, `/vm`, or `/mem`.
- Plan creation, inspection, execution, deletion, dry runs, checkpointing, and resume operations.
- Browser-rendered MCP Apps in sandboxed iframes with WebSocket communication.
- A real-time dashboard with conversation output, tool activity, plan progress, tool discovery, configuration controls, and file uploads.
- Secret redaction for bearer tokens, API keys, OAuth tokens, and authorization headers in log output.

## Limitations and notes

The virtual-memory functionality is explicitly experimental. The material also identifies later roadmap tiers for traces, memory scopes, skills, scheduling, and multi-agent features, so those should not be assumed to be available. The README describes this project as a CLI client; it does not establish that the package itself hosts an MCP server endpoint.

The default local Ollama setup does not require an API key, but using other model providers may require separate credentials or configuration. Exact supported provider setup, package installation instructions, license details, and MCP client compatibility are not provided in the supplied material.

_Full upstream README: https://allmcps.com/mcp/chrishayuk-mcp-cli/readme_