mcp-shell 🐚

Created By
soniricoa year ago
Give hands to AI. MCP server to run shell commands securely, auditably, and on demand.
Overview

What is mcp-shell?

mcp-shell is a robust Model Context Protocol (MCP) server that allows AI assistants to execute shell commands securely and audibly. It acts as a bridge between AI systems and the shell environment, enabling autonomous workflows and real-world problem solving.

How to use mcp-shell?

To use mcp-shell, clone the repository from GitHub, install it, and run the command with the desired configuration. You can also deploy it using Docker for added security.

Key features of mcp-shell?

  • Security First: Configurable command allowlists and blocklists.
  • Docker Ready: Runs in a lightweight container for secure isolation.
  • Structured Responses: Outputs in JSON format with execution metadata.
  • Audit Logging: Complete command execution audit trail.
  • Context Aware: Supports command execution with proper context cancellation.

Use cases of mcp-shell?

  1. Enabling AI assistants to perform system-level tasks.
  2. Automating workflows that require shell command execution.
  3. Providing a secure environment for executing potentially harmful commands.

FAQ from mcp-shell?

  • Can mcp-shell run any shell command?

Yes, but it is configurable to allow or block specific commands for security.

  • Is mcp-shell secure?

Yes, it includes various security features like command validation and execution limits.

  • How can I deploy mcp-shell?

You can deploy it directly on a Unix-like system or use Docker for containerized deployment.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
sonirico
Star
4
Language
Go
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago
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.

6 hours ago