P
🤖AutomatisationIntermediate6 steps

Cline: the terminal-first open-source coding agent, MCP-native

Cline is the open-source reference for developers who want a controlled, transparent, terminal-first coding agent. The project is one of the first to make the Model Context Protocol (MCP) a first-class citizen. Unlike Cursor or Devin, Cline charges nothing: you bring your own LLM key (Anthropic, OpenAI, DeepSeek, local models via Ollama) and only pay for API calls. The tool shows real-time cost of each action, a favorite feature for cost-conscious development. Distributed as a VS Code extension or standalone client, Cline stands out for its readability (every shell command is explicit) and its MCP ecosystem letting you plug custom tools in a few lines. Particularly well-suited to experienced developers who want to understand and control every step.

open-sourcemcpterminalvscodecost-transparencybyo-llmcline

For who

Experienced developers, open-source tinkerers, cost-conscious devs, and advanced MCP users who want full control over their coding agent.

Input

Type: text
Format: libre

Objectif de tache en langage naturel, fichiers references, serveurs MCP actives.

steps (6)

1

Install Cline

info

Install the Cline extension from the VS Code marketplace or the standalone build from the GitHub repo.

2

Pick your LLM

info

Configure your preferred provider API key (Anthropic, OpenAI, DeepSeek, OpenRouter or local Ollama).

3

Enable MCP servers

info

Add MCP servers from the gallery (filesystem, github, postgres, puppeteer, etc.) to extend Cline's capabilities.

4

Start a task

info

Describe a goal in plain English. Cline proposes a plan and asks for confirmation before each shell command.

5

Watch the costs

info

Check the live cost tracker and adjust the model if spend stacks up (Claude Sonnet vs Haiku, for instance).

6

Capitalize via MCP

info

Build your own MCP servers to automate tasks recurring in your organization.

Output

Type: text
Format: structure

Commandes shell explicites, diffs de fichiers, appels MCP, et cout detaille de la session.

Example

Input

Task: "Write a Python script that reads a customer CSV, enriches each row via the Clearbit API, and writes a new augmented CSV."

Output

Cline generates the script, asks for confirmation before each file write and network call, runs the script on a sample, and displays: "Session cost: $0.27 (Claude Haiku, 18 commands, 4 files changed)."

Customization

ParameterDescriptionDefault
Fournisseur LLMChoix du provider (Anthropic, OpenAI, DeepSeek, OpenRouter, Ollama).Anthropic
Serveurs MCPListe des serveurs MCP actives sur cette session.filesystem, github
Mode auto-approveAutoriser Cline a executer certaines commandes sans confirmation explicite (lecture fichier, commandes read-only).Read-only

Technical Notes

Open-source license. Zero tool cost: only LLM APIs are billed. Compatible with macOS, Linux, Windows via VS Code. Requires basic shell command knowledge.