Cloud Agent MCP server
AI software engineer — writes code, opens PRs, reviews code, generates tests, and more.
Usage numbers are collected on the next scan
Reviews
Write oneNobody has reviewed Cloud Agent yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Cloud Agent tools (9, 3 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
ask_codebaseAsk a question about any GitHub repository's codebase. Auto-indexes the repo on first use. Returns an answer with file references.
generate_testsGenerate tests for a specific file in a GitHub repository. Creates test files and opens a PR with them.
get_usageGet usage statistics: total sessions, cost, estimated time saved, breakdowns by source, repo, and user. Useful for tracking ROI.
list_playbooksList available playbooks — reusable workflow templates for common engineering tasks like bug triage, security remediation, test coverage, docs sync, and more.
list_sessionsList recent agent sessions with status, cost, duration, and PR URLs. Use to check on past or running tasks.
review_prReview a GitHub pull request. Returns structured feedback with issues, verdict, and suggestions. Optionally posts review comments directly to GitHub.
run_playbookwrite actionRun a playbook (reusable workflow template) against a repository. Use list_playbooks to see available options. Built-in playbooks include: bug-triage, security-remediation, dependency-upgrade, docs-sync, test-coverage, code-migration, pr-review-cycle.
run_taskwrite actionRun a coding task: write code, fix bugs, add features, refactor. The AI agent clones the repo, makes changes, and opens a PR. Returns the result and PR URL when complete.
security_scanwrite actionRun a security and dependency scan on one or more GitHub repositories. Checks for vulnerabilities, secret exposure, and security anti-patterns.
Public scan report
scanner v0.1.10 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan4 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancerepository not readable: repo not found3/15
- Maintainer identityno repository or website to verify2/10
Install Cloud Agent in Claude Code, Cursor or VS Code
Runs npx -y mcp-server-cloud-agent on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add cloud-agent -- npx -y mcp-server-cloud-agent
Cloud Agent: common questions
- Is Cloud Agent MCP server safe?
- With care: it is graded C, so read the findings first (55/100). Read the Cloud Agent safety report
- How do I install Cloud Agent?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Cloud Agent need an API key?
- Yes. The registry entry asks for
CLOUD_AGENT_API_KEY. - Is Cloud Agent maintained?
- The latest release is v1.1.1.
- What can I use instead of Cloud Agent?
- Servers from other publishers that do the same job: qikly MCP server, Agent-Native Slides MCP server and Mockserver MCP server. Compare all Cloud Agent alternatives.
Alternatives to Cloud Agent
Same job from other publishers: the closest match first, then the best rated.
qiklyGenerates tests from acceptance criteria, then converges code with an agent that never sees them.not reviewedGrowingA- Agent-Native SlidesAgent-Native Google Slides - generate and edit React presentationsnot reviewedEstablishedA
- MockserverMock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.not reviewedEstablishedA
- REAReverse engineer anything from your terminal or agent with one CLI and MCP server.not reviewedEstablishedA
- Alibaba Cloud DashScope — QwenAlibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.not reviewedEstablishedB