Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
joepangallo avatar

Cloud Agent

  • Updated March 21, 2026
  • joepangallo/mcp-server-cloud-agent

Cloud Agent is a MCP server that lets your local agent invoke a hosted AI software engineer to write code, open PRs, review changes, and generate tests.

About

Cloud Agent MCP turns your local coding agent into an orchestrator for a hosted AI software engineer that can implement features, open pull requests, review diffs, and generate tests on your behalf. developers use it when they want leverage beyond single-file edits—especially when product scope in Validate has become a real codebase in Build. Register the npm package mcp-server-cloud-agent over stdio, authenticate with CLOUD_AGENT_API_KEY from the Cloud Agent web workspace, and optionally point CLOUD_AGENT_URL at a custom backend if you self-host or use a private deployment. The server does not replace your judgment on architecture or security; it extends execution capacity so you can parallelize PR-sized work while you handle integrations, docs, and ship gates locally. Think of it as agent-tooling that outsources implementation bursts, not as infrastructure monitoring or growth analytics. Pair it with your normal git workflow and review habits so merged code still matches your standards.

  • Remote AI software engineer: writes code, opens PRs, reviews code, and generates tests from agent-driven prompts
  • npm mcp-server-cloud-agent (v1.1.1) over stdio for Claude Code, Cursor, and similar clients
  • Authenticated with CLOUD_AGENT_API_KEY (ca_ prefix) from the Cloud Agent web workspace
  • Optional CLOUD_AGENT_URL override (default hosted backend: agent.leddconsulting.com)
  • Offloads heavy implementation loops while you stay in local orchestration and product decisions

Cloud Agent by the numbers

  • Data as of Jul 7, 2026 (Skillselion catalog sync)
terminal
claude mcp add --env CLOUD_AGENT_API_KEY=YOUR_CLOUD_AGENT_API_KEY --env CLOUD_AGENT_URL=YOUR_CLOUD_AGENT_URL mcp-server-cloud-agent -- npx -y mcp-server-cloud-agent

Add your badge

Show developers this MCP server is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Packagemcp-server-cloud-agent
TransportSTDIO
AuthRequired
Last updatedMarch 21, 2026
Repositoryjoepangallo/mcp-server-cloud-agent

What it does

Delegate implementation work to a remote AI software engineer from your IDE agent—code changes, pull requests, reviews, and test generation via Cloud Agent MCP.

Who is it for?

Best when you already use Cloud Agent workspaces and want PR-level coding help exposed as MCP tools in Claude Code or Cursor.

Skip if: Skip if you only want lightweight inline completions with no external service, API key, or PR-based workflow.

What you get

Your IDE agent can trigger Cloud Agent workflows so implementation, PRs, reviews, and tests progress on a remote engineer while you direct priorities from MCP.

  • Agent-triggered code changes and pull requests via Cloud Agent
  • Review feedback and test generation routed through MCP tool calls
  • Configurable backend URL for default or custom Cloud Agent deployment

By the numbers

  • Registry version 1.1.1
  • npm package mcp-server-cloud-agent with stdio transport
  • Default backend URL documented as https://agent.leddconsulting.com
README.md

mcp-server-cloud-agent

MCP server for Cloud Agent — a hosted AI software engineer that writes code, opens PRs, reviews code, generates tests, runs security scans, and answers codebase questions.

Connect from any MCP client (Claude Code, Cursor, Windsurf, or your own agents) and delegate engineering tasks.

How it works

This package is a local stdio MCP proxy that forwards requests to the Cloud Agent hosted backend at agent.leddconsulting.com. Your MCP client communicates with this server over stdio; the server makes authenticated HTTPS calls to the backend on your behalf.

Legacy cloudagent.metaltorque.dev URLs still redirect, but new configs should use agent.leddconsulting.com.

Data flow: MCP client → (stdio) → this server → (HTTPS) → Cloud Agent backend → GitHub

What data leaves your machine:

  • Task descriptions, repo names, file paths, and PR URLs you provide
  • Your API key (sent over HTTPS only, never over HTTP)

What the backend does with your data:

  • Clones repos from GitHub using its own GitHub App credentials
  • Executes tasks in isolated sandboxes
  • Opens PRs and posts reviews to GitHub on your behalf

Tools (9)

Tool Description Side effects
run_task Write code, fix bugs, add features — returns result + PR URL Creates branches and PRs
review_pr Review a GitHub PR with structured feedback Optionally posts comments to GitHub
ask_codebase Ask questions about any GitHub repo (auto-indexes on first use) Read-only
generate_tests Generate tests for a file, opens a PR Creates branches and PRs
security_scan Security + dependency scan across one or more repos Read-only
list_sessions List recent sessions with status, cost, duration, PR URLs Read-only
list_playbooks List available workflow templates Read-only
run_playbook Run a playbook against a repo Creates branches and PRs
get_usage Usage stats — sessions, cost, time saved, breakdowns Read-only

Setup

1. Get an API key

Sign in to your Cloud Agent workspace at agent.leddconsulting.com and generate an API key at /auth/api-key. Keys use the ca_* prefix.

2. Configure your MCP client

Claude Code (~/.claude.json):

{
  "mcpServers": {
    "cloud-agent": {
      "command": "npx",
      "args": ["-y", "mcp-server-cloud-agent"],
      "env": {
        "CLOUD_AGENT_API_KEY": "ca_your_key_here"
      }
    }
  }
}

Cursor / Windsurf (MCP settings):

{
  "mcpServers": {
    "cloud-agent": {
      "command": "npx",
      "args": ["-y", "mcp-server-cloud-agent"],
      "env": {
        "CLOUD_AGENT_API_KEY": "ca_your_key_here"
      }
    }
  }
}

Environment Variables

Variable Required Description
CLOUD_AGENT_API_KEY Yes API key (ca_* prefix) from your Cloud Agent workspace
CLOUD_AGENT_URL No Backend URL (defaults to https://agent.leddconsulting.com)

Usage Examples

Once configured, your MCP client can call these tools directly:

Fix a bug:

"Use cloud-agent run_task on myorg/myapp to fix the broken login flow"

Review a PR:

"Use cloud-agent review_pr on https://github.com/myorg/myapp/pull/42"

Ask about code:

"Use cloud-agent ask_codebase on myorg/myapp: how does authentication work?"

Generate tests:

"Use cloud-agent generate_tests on myorg/myapp for src/auth.ts"

Security scan:

"Use cloud-agent security_scan on myorg/myapp and myorg/api"

Sample Output

run_task response:

{
  "response": "Fixed the login redirect bug. Changed src/auth.ts to properly handle OAuth callback URLs.",
  "cost_usd": 0.42,
  "duration_ms": 45000,
  "pr_url": "https://github.com/myorg/myapp/pull/87"
}

security_scan response:

{
  "repos_scanned": 1,
  "vulnerabilities": 3,
  "secrets_found": 0,
  "findings": [...]
}

Troubleshooting

Problem Solution
"CLOUD_AGENT_API_KEY is required" Set the env var in your MCP client config
"Refusing to send API key over insecure HTTP" Use HTTPS (the default). Don't set CLOUD_AGENT_URL to an HTTP URL
"Request timed out" Tasks can take up to 10 minutes. Check list_sessions for status
"HTTP 401" Your API key is invalid or expired. Generate a new one
"HTTP 429" Rate limited. Wait and retry

License

MIT

Recommended MCP Servers

How it compares

Hosted AI engineer MCP bridge—not a local-only edit skill or a generic git CLI wrapper.

FAQ

Who is Cloud Agent for?

It is for developers and small teams who use Cloud Agent’s web workspace and want their MCP client to delegate coding, PRs, reviews, and tests to that service.

When should I use Cloud Agent?

Use it during Build when you are actively implementing features and need an external AI engineer to produce PRs and tests while you orchestrate from your agent.

How do I add Cloud Agent to my agent?

Install mcp-server-cloud-agent, set CLOUD_AGENT_API_KEY (ca_*) from your workspace, optionally set CLOUD_AGENT_URL, register stdio in your MCP config, and restart your client.

AI & LLM Toolsagentsautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.