ModelsAtlas
Explore
Atlas / MCP servers / theailanguage / Terminal

TerminalSAFE

mcp/theailanguage/terminal-1
MCP server by theailanguage · claude desktop · docker · mcp server · Audited 2026-10-07
⚑ Report / re-scanSource ↗

MCP server that can execute terminal commands

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
2 0r · 2w · 0d
Transport
stdio
License
NOASSERTION
Stars
91
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Introduction

Welcome to The AI Language project! In this repository, you'll find multiple examples of setting up MCP Servers. MCP (Model Context Protocol) is a framework for AI models that enables them to store data, run tools, and use prompts for specific tasks.

Available Server Examples

We provide four examples to help you set up your MCP server in different environments. The table below summarizes each configuration:

If you enjoy learning about AI, coding, and automation, please like and subscribe to the channel — it really helps us make more great content for you! SUBSCRIBE

What is MCP?

MCP (Model Context Protocol) is a protocol that allows AI models to:

  • Store data (like files or API responses)
  • Run tools (functions that AI can execute)
  • Use prompts (predefined templates for tasks)

Option 1: Setup Without Docker (Local Python)

This option demonstrates how to set up an MCP server locally using Python without Docker. Follow the video tutorial: Tutorial 1

Option 2: Setup With Docker

This option shows how to containerize the MCP server with Docker and run it locally. Follow the video tutorial: Tutorial 2

Option 3: Setup with SSE (Local, Docker)

Thi

Read from source at commit 87ff0fe887f7OBSERVED · 2026-10-07
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add sse-server -- uvx sse-server
claude-desktop
{
  "mcpServers": {
    "sse-server": {
      "command": "uvx",
      "args": [
        "sse-server"
      ]
    }
  }
}
03

Exposed tools (2)

0 read · 2 write · 0 destructive.

ToolRiskDescription
add_numberswrite
run_commandwrite
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
declared (2 observation(s))
Dependencies
pinned
Secrets in source
none-found

Findings (3)

LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
streamable_http_server/streamable_http_sequence_diagram.md:20
Client->>Server: POST /mcp InitializeRequest<br><br>Accept: application/json & text/event-stream<br>No Mcp-Session-Id<br>... request ...
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
streamable_http_server/streamable_http_sequence_diagram.md:26
Client->>Server: POST /mcp InitializedNotification<br>Mcp-Session-Id<br>... notification ...
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
streamable_http_server/streamable_http_sequence_diagram.md:37
Client->>Server: POST /mcp<br>Mcp-Session-Id<br>Accept: application/json, text/event-stream<br>body:... request ...
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha 87ff0fe887f7full audit observations/trust-audit/mcp-server/theailanguage__terminal-1.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-0787ff0fe887f7SAFEB89first audit
06

Questions

What is the Terminal MCP server?

MCP server that can execute terminal commands

What tools does Terminal expose?

2 in total: 0 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Terminal safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Terminal need?

No credential environment variables were found in its source, so it appears to need none.

How does Terminal run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as sse-server.

How current is this page?

The grade is for one exact copy of the source (87ff0fe887f7), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement