jan-terminal-mcp
Allows compiling and running C++ code using g++, returning compilation errors and program output.
Provides a tool for running git commands in any repository, enabling version control operations such as commit, push, pull, and status checks.
Allows executing JavaScript code and returning its output, enabling scripting and automation in JavaScript.
Allows executing Kotlin code and returning its output, enabling Kotlin scripting and automation.
Allows executing PHP code and returning its output, enabling PHP scripting and automation.
Allows executing Python code directly and returning the output, enabling Python scripting, data processing, and automation.
Allows executing Ruby code and returning its output, enabling Ruby scripting and automation.
Allows executing Rust code and returning its output, enabling Rust scripting and automation.
Allows executing Swift code and returning its output, enabling Swift scripting and automation.
Allows executing TypeScript code and returning its output, enabling scripting and automation in TypeScript.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@jan-terminal-mcp run git status in my project folder"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
jan-terminal-mcp
Jan AI has no native terminal or code execution. This gives it that.
An MCP server that gives your local Jan model real hands on your machine - run shell commands, execute code in 14 languages, read/write files, and use git. All locally, all private.
Includes a fine-tuned 4B model trained specifically to call these tools reliably instead of just describing what it would do.
Tools
Tool | Description |
| Run any PowerShell command |
| Run git commands in any repo |
| Read any file's contents |
| Write or overwrite a file |
| List files and folders in a directory |
| Replace a specific substring in a file - smarter than rewriting the whole thing |
| Execute Python code directly and return output |
| Compile and run C++ code (g++), returns errors + output |
| Execute code in any language - Python, JavaScript, TypeScript, Java, C++, C#, Go, Rust, Ruby, PHP, R, Kotlin, Swift, MATLAB |
Related MCP server: machine-root-mcp
Fine-tuned model
AItrainer1/jancoder-4b-gguf, a 4B model fine-tuned via QLoRA on tool-use conversations generated specifically for this tool schema.
Stock models at this size tend to describe what they'd do rather than actually calling tools. This model was trained to call them correctly and consistently.
Drop the GGUF into Jan and it works out of the box with this MCP server.
The Kaggle training notebook is at kaggle_finetune.ipynb.
Install
pip install jan-terminal-mcpSetup in Jan AI
Open Jan, Settings, MCP Servers
Click Add and paste this config:
{
"jan-terminal": {
"command": "jan-terminal-mcp",
"args": [],
"env": {},
"active": true
}
}Or edit %APPDATA%\Jan\data\mcp_config.json directly and add the block above inside "mcpServers".
Restart Jan - the server appears as Jan-Terminal with a green dot.
Requirements
Windows (PowerShell required for
run_shell)Python 3.10+
Jan AI v0.7.9+
pip install mcp>=2.0.0
Bugs
Report bugs and stuff to ISSUE
License
MIT
Available Tools
10 toolsedit_fileA
Edit a file by replacing old_text with new_text. Use this to fix errors instead of rewriting the whole file.
Inputs: path (required), new_text (required), old_text (required). Returns: result
gitA
Run a git command. args = e.g. 'status', 'log --oneline -10', 'commit -m "fix bug"'
Inputs: args (required), cwd. Returns: result
list_dirB
List files and folders in a directory.
Inputs: path (required). Returns: result
read_fileC
Read the contents of a file on the user's machine.
Inputs: path (required). Returns: result
run_codeA
Execute a code snippet directly without saving to disk. Use for quick one-off runs. If you already wrote the code with write_file, use run_file instead to avoid writing twice. Supported: python, javascript, typescript, java, cpp, csharp, go, rust, ruby, php, r, kotlin, swift, matlab
Inputs: code (required), language (required), cwd. Returns: result
run_cppA
Compile and run C++ code. Returns compiler errors or program output.
Inputs: code (required), cwd. Returns: result
run_fileA
Run an already-existing file. Use this after write_file — avoids writing the code twice. Language is auto-detected from extension if not provided.
Inputs: path (required), language. Returns: result
run_pythonB
Execute Python code directly and return the output.
Inputs: code (required), cwd. Returns: result
run_shellC
Run a PowerShell command on the user's machine.
Inputs: command (required), cwd. Returns: result
write_fileB
Write or overwrite a file on the user's machine. After writing code, use run_file to execute it — do NOT also call run_code with the same code.
Inputs: path (required), content (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
The run_* family is heavily overlapping: run_code, run_python, and run_cpp all execute code, with run_python and run_cpp being subsets of run_code. run_file and run_shell also blur boundaries, making it easy to select the wrong tool.
Most tools follow a clear verb_noun pattern (read_file, write_file, list_dir, edit_file, run_code, etc.). The single exception is 'git' (a plain command name) and to a lesser extent 'run_shell' which still matches the pattern, so only a minor deviation.
10 tools is within the ideal range, but the redundancy of run_python and run_cpp with run_code makes the set feel slightly over-scoped. Still, the count is reasonable for a terminal/file server.
The tool surface covers git, shell, file read/write/edit/list, and code execution, which is solid for a terminal. Minor gaps include no delete_file or rename operation, but these can be worked around with run_shell.
Related MCP Connectors
An MCP server that gives your AI access to the source code and docs of all public github repos
A MCP server built for developers enabling Git based project management with project and personal…
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
Remote MCP server exposing your Node Command fleet (files, shell, processes, browser) to AI hosts.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that enables AI clients to execute shell, Python, and Node commands on the local machine across platforms.352 PyPI1MIT
- AlicenseNot gradedqualityDmaintenanceA self-hosted MCP server that gives AI coding assistants direct shell access to your local machine, enabling execution of arbitrary bash commands for development workflows.ISC
- AlicenseBqualityCmaintenanceA comprehensive MCP server for developers providing file operations, shell execution, git integration, and smart caching to enhance AI-assisted development.11MIT
- AlicenseNot gradedqualityCmaintenanceA self-hosted MCP server that gives ChatGPT full local machine access for coding tasks, including file editing, shell commands, git operations, and project exploration via 40+ MCP tools.MIT