Agentsphere MCP Server

Created By
AgentSphere10 months ago
The first MCP-integrated cloud sandbox for running AI-generated code at scale. AgentSphere empowers you to spin up isolated execution environments in seconds and integrate seamlessly with your MCP clients.
Overview

What is AgentSphere?

AgentSphere is the first MCP-integrated sandbox designed for running AI-generated code in secure remote sandboxes at scale. It allows users to create isolated execution environments, execute commands and manage files in a controlled environment.

Key Features

  • Sandbox management
  • Execute commands in a secure environment
  • File operations including upload, download, and delete
  • Generate preview links for web applications running in sandboxes

Key Use Cases

  1. Data Analysis and Visualization: Turning natural language questions into interactive dashboards and data-driven insights, without writing a single line of code.
  2. Autonomous Coding Agents: Providing a secure runtime for AI agents to autonomously write, test, and execute code, automating complex development tasks.
  3. Code Generation Evaluation & Benchmarking: Establishing a standardized, secure environment to objectively measure and compare the performance and quality of code-generating AI models..
  4. AI Tooling & Copilot Backend: Acting as a secure, on-demand execution runtime for IDEs and enterprise internal copilots.

Server Config

{
  "mcpServers": {
    "agentsphere": {
      "command": "uvx",
      "args": [
        "agentsphere-mcp-server"
      ],
      "env": {
        "AGENTSPHERE_API_KEY": "your_api_key_here"
      }
    }
  }
}
Project Info
Created At
10 months ago
Updated At
10 months ago
Author Name
AgentSphere
Star
-
Language
-
License
-
Category
Homepage

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)

9 hours ago