MCP Terminal Server

Created By
RinardNicka year ago
An MCP server that provides secure terminal access for Claude and other LLMs
Overview

what is MCP Terminal Server?

MCP Terminal Server is a secure terminal execution server that implements the Model Context Protocol (MCP), providing controlled command execution capabilities with enhanced security features and resource limits.

how to use MCP Terminal Server?

To use MCP Terminal Server, clone the repository, set up a virtual environment, install dependencies, and configure it with allowed commands. You can then execute shell commands securely through the server.

key features of MCP Terminal Server?

  • Command execution with output capture and error handling
  • Security controls to restrict allowed commands and prevent command injection
  • Resource controls including command timeouts and maximum output size limits
  • Support for the MCP protocol with capability advertisement and streaming output

use cases of MCP Terminal Server?

  1. Securely executing shell commands in a controlled environment.
  2. Integrating with applications that require terminal command execution.
  3. Testing and validating command execution through the MCP Inspector tool.

FAQ from MCP Terminal Server?

  • What commands can be executed?

Only the commands specified in the allowed commands list can be executed to ensure security.

  • How does MCP Terminal Server handle errors?

The server captures errors and provides detailed output for troubleshooting.

  • Is there a limit on command execution time?

Yes, command timeouts can be configured to prevent hanging processes.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
RinardNick
Star
-
Language
-
License
-

Recommend Servers

View All
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

21 minutes ago