mcp-client-cli

Name: mcp-client-cli
Author: adhikasp

153installs/mo · pypi678stars81forks

How to install mcp-client-cli?

adhikasp/mcp-client-cli

$git clone https://github.com/adhikasp/mcp-client-cli

Installs into the current project.

Summary

A simple CLI program to run LLM prompt and implement Model Context Protocol (MCP) client.

Files · 1

View on GitHub

README.md

1	# MCP CLI client
2
3	A simple CLI program to run LLM prompt and implement [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) client.
4
5	You can use any [MCP-compatible servers](https://github.com/punkpeye/awesome-mcp-servers) from the convenience of your terminal.
6
7	This act as alternative client beside Claude Desktop. Additionally you can use any LLM provider like OpenAI, Groq, or local LLM model via [llama](https://github.com/ggerganov/llama.cpp).
8
9	![C4 Diagram](https://raw.githubusercontent.com/adhikasp/mcp-client-cli/refs/heads/master/c4_diagram.png)
10
11	## Setup
12
13	1. Install via pip:
14	```bash
15	pip install mcp-client-cli
16	```
17
18	2. Create a `~/.llm/config.json` file to configure your LLM and MCP servers:
19	```json
20	{
21	"systemPrompt": "You are an AI assistant helping a software engineer...",
22	"llm": {
23	"provider": "openai",
24	"model": "gpt-4",
25	"api_key": "your-openai-api-key",
26	"temperature": 0.7,
27	"base_url": "https://api.openai.com/v1" // Optional, for OpenRouter or other providers
28	},
29	"mcpServers": {
30	"fetch": {
31	"command": "uvx",
32	"args": ["mcp-server-fetch"],
33	"requires_confirmation": ["fetch"],
34	"enabled": true, // Optional, defaults to true
35	"exclude_tools": [] // Optional, list of tool names to exclude
36	},
37	"brave-search": {
38	"command": "npx",
39	"args": ["-y", "@modelcontextprotocol/server-brave-search"],
40	"env": {
41	"BRAVE_API_KEY": "your-brave-api-key"
42	},
43	"requires_confirmation": ["brave_web_search"]
44	},
45	"youtube": {
46	"command": "uvx",
47	"args": ["--from", "git+https://github.com/adhikasp/mcp-youtube", "mcp-youtube"]
48	}
49	}
50	}
51	```
52
53	Note:
54	- See [CONFIG.md](CONFIG.md) for complete documentation of the configuration format
55	- Use `requires_confirmation` to specify which tools need user confirmation before execution
56	- The LLM API key can also be set via environment variables `LLM_API_KEY` or `OPENAI_API_KEY`
57	- The config file can be placed in either `~/.llm/config.json` or `$PWD/.llm/config.json`
58	- You can comment the JSON config file with `//` if you like to switch around the configuration
59
60	3. Run the CLI:
61	```bash
62	llm "What is the capital city of North Sumatra?"
63	```
64
65	## Usage
66
67	### Basic Usage
68
69	```bash
70	$ llm What is the capital city of North Sumatra?
71	The capital city of North Sumatra is Medan.
72	```
73
74	You can omit the quotes, but be careful with bash special characters like `&`, `\|`, `;` that might be interpreted by your shell.
75
76	You can also pipe input from other commands or files:
77
78	```bash
79	$ echo "What is the capital city of North Sumatra?" \| llm
80	The capital city of North Sumatra is Medan.
81
82	$ echo "Given a location, tell me its capital city." > instructions.txt
83	$ cat instruction.txt \| llm "West Java"
84	The capital city of West Java is Bandung.
85	```
86
87	### Image Input
88
89	You can pipe image files to analyze them with multimodal LLMs:
90
91	```bash
92	$ cat image.jpg \| llm "What do you see in this image?"
93	[LLM will analyze and describe the image]
94
95	$ cat screenshot.png \| llm "Is there any error in this screenshot?"
96	[LLM will analyze the screenshot and point out any errors]
97	```
98
99	### Using Prompt Templates
100
101	You can use predefined prompt templates by using the `p` prefix followed by the template name and its arguments:
102
103	```bash
104	# List available prompt templates
105	$ llm --list-prompts
106
107	# Use a template
108	$ llm p review # Review git changes
109	$ llm p commit # Generate commit message
110	$ llm p yt url=https://youtube.com/... # Summarize YouTube video
111	```
112
113	### Triggering a tool
114
115	```bash
116	$ llm What is the top article on hackernews today?
117
118	================================== Ai Message ==================================
119	Tool Calls:
120	brave_web_search (call_eXmFQizLUp8TKBgPtgFo71et)
121	Call ID: call_eXmFQizLUp8TKBgPtgFo71et
122	Args:
123	query: site:news.ycombinator.com
124	count: 1
125	Brave Search MCP Server running on stdio
126
127	#

People who liked this also viewed

6 picks

Type

fastmcp🚀 The fast, Pythonic way to build MCP servers and clients.MCP ServersJul 202686M27k
playwright-mcpPlaywright MCP serverMCP ServersJul 202626M35k
ext-appsOfficial repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP serversMCP ServersJul 20268.5M2.6k
langchain-mcp-adaptersLangChain 🔌 MCPMCP ServersJul 20267.0M3.6k
mcporterCall MCPs via TypeScript, masquerading as simple TypeScript API. Or package them as cli.MCP ServersJul 20262.5M4.8k
mcp-proxyA bridge between Streamable HTTP and stdio MCP transportsMCP ServersJul 20262.2M2.7k

mcp-client-cli

153installs/mo · pypi678stars81forks

View on GitHub

How to install mcp-client-cli?

adhikasp/mcp-client-cli

$git clone https://github.com/adhikasp/mcp-client-cli

Installs into the current project.

Summary

A simple CLI program to run LLM prompt and implement Model Context Protocol (MCP) client.

Files · 1

View on GitHub

README.md

1	# MCP CLI client
2
3	A simple CLI program to run LLM prompt and implement [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) client.
4
5	You can use any [MCP-compatible servers](https://github.com/punkpeye/awesome-mcp-servers) from the convenience of your terminal.
6
7	This act as alternative client beside Claude Desktop. Additionally you can use any LLM provider like OpenAI, Groq, or local LLM model via [llama](https://github.com/ggerganov/llama.cpp).
8
9	![C4 Diagram](https://raw.githubusercontent.com/adhikasp/mcp-client-cli/refs/heads/master/c4_diagram.png)
10
11	## Setup
12
13	1. Install via pip:
14	```bash
15	pip install mcp-client-cli
16	```
17
18	2. Create a `~/.llm/config.json` file to configure your LLM and MCP servers:
19	```json
20	{
21	"systemPrompt": "You are an AI assistant helping a software engineer...",
22	"llm": {
23	"provider": "openai",
24	"model": "gpt-4",
25	"api_key": "your-openai-api-key",
26	"temperature": 0.7,
27	"base_url": "https://api.openai.com/v1" // Optional, for OpenRouter or other providers
28	},
29	"mcpServers": {
30	"fetch": {
31	"command": "uvx",
32	"args": ["mcp-server-fetch"],
33	"requires_confirmation": ["fetch"],
34	"enabled": true, // Optional, defaults to true
35	"exclude_tools": [] // Optional, list of tool names to exclude
36	},
37	"brave-search": {
38	"command": "npx",
39	"args": ["-y", "@modelcontextprotocol/server-brave-search"],
40	"env": {
41	"BRAVE_API_KEY": "your-brave-api-key"
42	},
43	"requires_confirmation": ["brave_web_search"]
44	},
45	"youtube": {
46	"command": "uvx",
47	"args": ["--from", "git+https://github.com/adhikasp/mcp-youtube", "mcp-youtube"]
48	}
49	}
50	}
51	```
52
53	Note:
54	- See [CONFIG.md](CONFIG.md) for complete documentation of the configuration format
55	- Use `requires_confirmation` to specify which tools need user confirmation before execution
56	- The LLM API key can also be set via environment variables `LLM_API_KEY` or `OPENAI_API_KEY`
57	- The config file can be placed in either `~/.llm/config.json` or `$PWD/.llm/config.json`
58	- You can comment the JSON config file with `//` if you like to switch around the configuration
59
60	3. Run the CLI:
61	```bash
62	llm "What is the capital city of North Sumatra?"
63	```
64
65	## Usage
66
67	### Basic Usage
68
69	```bash
70	$ llm What is the capital city of North Sumatra?
71	The capital city of North Sumatra is Medan.
72	```
73
74	You can omit the quotes, but be careful with bash special characters like `&`, `\|`, `;` that might be interpreted by your shell.
75
76	You can also pipe input from other commands or files:
77
78	```bash
79	$ echo "What is the capital city of North Sumatra?" \| llm
80	The capital city of North Sumatra is Medan.
81
82	$ echo "Given a location, tell me its capital city." > instructions.txt
83	$ cat instruction.txt \| llm "West Java"
84	The capital city of West Java is Bandung.
85	```
86
87	### Image Input
88
89	You can pipe image files to analyze them with multimodal LLMs:
90
91	```bash
92	$ cat image.jpg \| llm "What do you see in this image?"
93	[LLM will analyze and describe the image]
94
95	$ cat screenshot.png \| llm "Is there any error in this screenshot?"
96	[LLM will analyze the screenshot and point out any errors]
97	```
98
99	### Using Prompt Templates
100
101	You can use predefined prompt templates by using the `p` prefix followed by the template name and its arguments:
102
103	```bash
104	# List available prompt templates
105	$ llm --list-prompts
106
107	# Use a template
108	$ llm p review # Review git changes
109	$ llm p commit # Generate commit message
110	$ llm p yt url=https://youtube.com/... # Summarize YouTube video
111	```
112
113	### Triggering a tool
114
115	```bash
116	$ llm What is the top article on hackernews today?
117
118	================================== Ai Message ==================================
119	Tool Calls:
120	brave_web_search (call_eXmFQizLUp8TKBgPtgFo71et)
121	Call ID: call_eXmFQizLUp8TKBgPtgFo71et
122	Args:
123	query: site:news.ycombinator.com
124	count: 1
125	Brave Search MCP Server running on stdio
126
127	#

People who liked this also viewed

6 picks

Type